CN113380381A - Method and device for acquiring medical diagnosis information, electronic equipment and storage medium - Google Patents
Method and device for acquiring medical diagnosis information, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113380381A CN113380381A CN202110791497.3A CN202110791497A CN113380381A CN 113380381 A CN113380381 A CN 113380381A CN 202110791497 A CN202110791497 A CN 202110791497A CN 113380381 A CN113380381 A CN 113380381A
- Authority
- CN
- China
- Prior art keywords
- image
- medical image
- medical
- training
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10101—Optical tomography; Optical coherence tomography [OCT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Radiology & Medical Imaging (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
本申请提供了一种获取医学诊断信息的方法、装置、电子设备及存储介质，涉及图像处理技术领域，能够直观的展示对象组织，并获得较为准确的医学诊断信息。该方法包括：获取医学设备采集的第一医学图像，所述第一医学图像中包括对象组织；将所述第一医学图像输入至目标图像合成模型中进行处理，得到第二医学图像，所述第二医学图像用于描述所述对象组织对光束的衰减程度，所述光束是由用于对所述对象组织进行扫描的光源发射的；根据所述第二医学图像，获取所述对象组织的医学诊断信息。
The present application provides a method, device, electronic device and storage medium for obtaining medical diagnosis information, which relate to the technical field of image processing, which can intuitively display object organization and obtain relatively accurate medical diagnosis information. The method includes: acquiring a first medical image collected by a medical device, where the first medical image includes object tissue; inputting the first medical image into a target image synthesis model for processing to obtain a second medical image, the The second medical image is used to describe the degree of attenuation of the light beam by the object tissue, and the light beam is emitted by the light source used for scanning the object tissue; according to the second medical image, the object tissue is acquired Medical diagnostic information.
Description
Technical Field
The present application belongs to the field of image processing technologies, and in particular, to a method and an apparatus for acquiring medical diagnostic information, an electronic device, and a storage medium.
Background
In the medical field, in order to detect whether a certain target tissue has a lesion or not, a light beam is generally emitted to the target tissue through an image imaging device (or called a light source) by using a basic principle of a weak coherent optical interferometer, so that the image imaging device generates a medical image including the target tissue, and then medical diagnosis information is determined based on the medical image and optical hardware parameters of the image imaging device.
However, since the optical hardware parameters may slightly differ when the image imaging apparatus is manufactured, the medical diagnosis information determined based on the medical image and the optical hardware parameters may also have errors, which is not favorable for the diagnosis of diseases.
Disclosure of Invention
The embodiment of the application provides a method, a device, electronic equipment and a storage medium for acquiring medical identification information, which can acquire more accurate medical diagnosis information.
In a first aspect, an embodiment of the present application provides a method for processing an image, including:
acquiring a first medical image acquired by medical equipment, wherein the first medical image comprises image information of object tissues;
inputting the first medical image into a target image synthesis model for processing, so as to obtain a second medical image, wherein the second medical image is used for describing the attenuation degree of the object tissue to a light beam, and the light beam is emitted by a light source used for scanning the object tissue;
medical diagnostic information of the subject tissue is acquired from the second medical image.
According to the method for acquiring the medical diagnosis information, the first medical image which is acquired by the medical equipment and used for describing the object tissue is acquired, the first medical image is input into the target image synthesis model to be processed, the second medical image which can be used for describing the attenuation degree of the object tissue to the light beam is acquired, the situation that the medical image which can accurately know the situation of the object tissue cannot be acquired due to the problem of system errors of the image imaging equipment can be effectively avoided, the medical diagnosis information of the object tissue is acquired according to the attenuation degree of the object tissue to the light beam recorded in the second medical image, the situation of the object tissue can be conveniently and accurately known, and treatment of diseases is facilitated.
In a second aspect, an embodiment of the present application provides an apparatus for acquiring medical diagnostic information, including:
the medical device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a first medical image acquired by medical equipment, and the first medical image comprises image information of object tissues;
a processing module, configured to input the first medical image into a target image synthesis model for processing, so as to obtain a second medical image, where the second medical image is used to describe the degree of attenuation of the object tissue to a light beam emitted by a light source used for scanning the object tissue;
a second obtaining module for obtaining medical diagnosis information of the object tissue according to the second medical image.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor, when executing the computer program, implements the method for acquiring medical diagnostic information according to any one of the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for acquiring medical diagnostic information according to any one of the first aspect is implemented.
In a fifth aspect, the present application provides a computer program product, which when run on an electronic device, causes the electronic device to execute the method for acquiring medical diagnostic information according to any one of the first aspect.
It is understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description of the first aspect, and are not described herein again.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart illustrating a method for acquiring medical diagnostic information according to an embodiment of the present application.
Fig. 2 is an exemplary diagram of a first medical image and a second medical image provided by an embodiment of the present application.
Fig. 3 is a flowchart illustrating a specific implementation of step S13 of the method for acquiring medical diagnostic information according to an embodiment of the present application.
Fig. 4 is a flowchart illustrating a specific implementation of step S23 of the method for acquiring medical diagnostic information according to an embodiment of the present application.
Fig. 5 is a flowchart illustrating a specific implementation of step S33 of the method for acquiring medical diagnostic information according to an embodiment of the present application.
Fig. 6 is a schematic diagram of a generated carpet display map provided by an embodiment of the present application.
Fig. 7 is a flowchart illustrating a method for training a target image synthesis model according to another embodiment of the present application.
Fig. 8 is an exemplary diagram of performing forward loop training according to another embodiment of the present application.
Fig. 9 is an exemplary diagram of performing reverse loop training according to another embodiment of the present application.
Fig. 10 is a schematic structural diagram of an apparatus for acquiring medical diagnostic information according to another embodiment of the present application.
Fig. 11 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
Referring to fig. 1, fig. 1 is a flowchart illustrating an implementation of a method for acquiring medical diagnostic information according to an embodiment of the present application. In this embodiment, the main execution body of the method for acquiring medical diagnosis information is an electronic device. The electronic device may be the medical device itself for acquiring the first medical image, or may be a device other than a medical device. When the electronic device is other than the medical device, the electronic device and the medical device can perform data communication to realize data interaction between the electronic device and the medical device, control over the medical device and other operations.
The following embodiments are described taking the example that the electronic device is a medical device itself:
as shown in fig. 1, an embodiment of the present application provides a method for acquiring medical diagnostic information, which includes the following steps:
s11: a first medical image acquired by a medical device is acquired, the first medical image including image information of a subject tissue.
In step S11, the medical device is a device capable of image acquisition. For example, an Optical Coherence Tomography (OCT) apparatus.
The first medical image is an image acquired by a medical device comprising tissue of the object after determining the position of the tissue of the object. For example, fig. 2A in fig. 2 is an OCT image of a blood vessel in a human body acquired by an OCT apparatus.
The first medical image is used to show the surface condition of the tissue of the subject. For example, the surface condition of a blood vessel is shown by an OCT image of a blood vessel of a human body, such as a plaque formed on the inner wall surface of the blood vessel due to lipid accumulation is shown by a first medical image.
The subject tissue may be biological tissue in a human or animal. Such as blood vessels or the heart in the human body.
In the present embodiment, a light beam is emitted to a subject tissue by a light source of a medical device so as to obtain a first medical image based on a situation when the light beam irradiates the subject tissue, and therefore, image information of the subject tissue is included in the first medical image so as to describe the subject tissue by the image information of the subject tissue, with the object of determining the subject tissue to be medically diagnosed from the first medical image and providing a basis for data processing based on the first medical image.
The timing for acquiring the first medical image acquired by the medical device may include, but is not limited to, the following two scenarios.
Scene 1: when the medical equipment is detected to acquire a first medical image, the first medical image is acquired.
Scene 2: when the number of the first medical images acquired by the medical equipment reaches a preset image number threshold value, acquiring the first medical images acquired by the medical equipment according to the time sequence of acquiring the first medical images.
The preset image quantity threshold value can be set according to actual requirements.
In some embodiments, in order to improve the efficiency of data processing, when the acquired first medical image is a curved surface image, the first medical image is subjected to dimension reduction processing, and a plan view of the first medical image is obtained.
Preferably, the curved surface view is a three-dimensional view and the plan view is a two-dimensional view.
S12: and inputting the first medical image into the target image synthesis model for processing to obtain a second medical image, wherein the second medical image is used for describing the attenuation degree of the target tissue to the light beam, and the light beam is emitted by a light source used for scanning the target tissue.
In step S12, the attenuation degree is used to describe the situation that when the light beam irradiates the object tissue, the object tissue absorbs part of the energy of the light beam, resulting in attenuation of the light beam.
The light source is a light source disposed on the medical device. For example, a light source arranged in a medical device for emitting X-rays.
In the embodiment, when the light beam irradiates the target tissue, the target tissue absorbs part of energy of the light beam, so that the light beam is attenuated, and therefore the condition of the target tissue can be known based on the attenuation condition of the light beam at each position in the target tissue, in order to know the attenuation degree of the light beam by the target tissue, after the first medical image is acquired, the first medical image is input into the target image synthesis model for image synthesis processing, so as to obtain the second medical image which corresponds to the first medical image and can be used for describing the attenuation degree of the light beam by the target tissue, so that the condition of each position in the target tissue can be known more clearly. For example, the first medical image 2A in fig. 2 is input into the target image synthesis model for processing, resulting in the second medical image 2B.
For example, when a diseased tissue exists in the target tissue, the energy of the absorbed light beam of the diseased tissue may be different from that of other portions in the target tissue, and thus the position of the diseased tissue may be obtained, and medical diagnostic information of the target tissue may be obtained.
It is understood that, in the application, a pre-trained target image synthesis model is stored in the medical device in advance. The target image synthesis model can be trained by medical equipment in advance, and files corresponding to the target image synthesis model can be transplanted to the medical equipment after being trained by other equipment in advance. That is, the subject of execution for training the target image synthesis model may be the same as or different from the subject of execution for image synthesis using the target image synthesis model. For example, when the image synthesis model which is not trained is trained by other equipment, after the training of the image synthesis model which is not trained is finished by other equipment, the model parameters of the image synthesis model which is not trained are fixed to obtain a file corresponding to the target image synthesis model, and then the file is transplanted to the medical equipment.
S13: medical diagnostic information of the subject tissue is acquired from the second medical image.
In step S13, the medical diagnosis information is used to describe whether a lesion appears in the target tissue, and one or more of information such as the location of the lesion, the size of the lesion region, and the type of the lesion.
In this embodiment, since the second medical image is used to describe the attenuation degree of the target tissue to the light beam, whether the target tissue has a lesion or not is known according to the attenuation degree of the target tissue to the light beam at different positions, so as to obtain the medical diagnosis information of the target tissue.
According to the method for acquiring the medical diagnosis information, the first medical image which is acquired by the medical equipment and used for describing the object tissue is acquired, the first medical image is input into the target image synthesis model to be processed, the second medical image which can be used for describing the attenuation degree of the object tissue to the light beam is acquired, the situation that the medical image which can accurately know the situation of the object tissue cannot be acquired due to the problem of system errors of the image imaging equipment can be effectively avoided, the medical diagnosis information of the object tissue is acquired according to the attenuation degree of the object tissue to the light beam recorded in the second medical image, the situation of the object tissue can be accurately known, and treatment of diseases is facilitated.
In some embodiments, after the first medical image is input into the target image synthesis model for processing, and the second medical image is obtained, the second medical image is subjected to image staining processing in order to better understand the condition of the object tissue.
Wherein the second medical image is subjected to a staining process according to a degree of attenuation of the light beam by the object tissue described in the second medical image. Specifically, the second medical image is dyed with a preset color according to different described light attenuation degrees.
For example, a second medical image depicting a blood vessel is stained using a staining strategy of a blue to red to yellow gradient, wherein closer to blue indicates a smaller degree of attenuation, a smaller lipid plaque content of the blood vessel, and closer to yellow indicates a larger degree of attenuation, a larger lipid plaque content of the blood vessel.
In some embodiments, in order to facilitate observation of the tissue of the object, the first medical image and the second medical image are subjected to image fusion processing, and a fused second medical image is obtained.
Specifically, according to the corresponding positions of the pixels of the first medical image and the second medical image, the pixel values in the first medical image are converted into attenuation degree values, and thus a fused image is obtained.
In an embodiment of the present application, with reference to fig. 3, the acquiring medical diagnostic information of the tissue of the subject according to the second medical image includes:
s21: and performing linear interpolation on the coordinate information of the pixel points in the second medical image to obtain the interpolated second medical image.
S22: and projecting the interpolated second medical image to a polar coordinate to obtain a third medical image, wherein the third medical image comprises a plurality of lines of attenuation degree values, each line of attenuation degree values corresponds to one light beam, and each line of attenuation degree values is used for indicating the attenuation degree of the object tissue to the light beam corresponding to each line of attenuation degree values.
S23: medical diagnostic information of the subject tissue is acquired from the third medical image.
In the present embodiment, the attenuation degree value is used to describe the degree of attenuation of the light beam by the tissue point of the target tissue in the irradiation direction of the light beam when the light beam irradiates the target tissue. Therefore, it can be understood that, by each column of attenuation degree values, the attenuation degree of the light beam corresponding to each column of attenuation degree values by the object tissue can be described.
In this embodiment, in order to better process the second medical image, linear interpolation is performed on the coordinate information of each pixel point in the second medical image to obtain the coordinate information of each pixel point of the second medical image in the polar coordinate, and the interpolated second medical image is obtained based on the coordinate information of each pixel point in the polar coordinate. Furthermore, the interpolated second medical image is projected to the polar coordinate to obtain a third medical image, so that the distribution of a plurality of lines of attenuation degree values included in the third medical image in the polar coordinate can be better utilized to quickly know whether each attenuation degree value describing the object tissue is abnormal or not, or the abnormal attenuation degree value is distributed at the position of the third medical image, or the area occupied by the abnormal attenuation degree value, and further the medical diagnosis information of the object tissue can be obtained.
It can be understood that, in order to determine the coordinate information of each pixel point of the second medical image in the polar coordinate, for each pixel point, the relationship between the pixel point and the adjacent pixel point is utilized, and the coordinate of the pixel point is interpolated based on a preset difference algorithm to obtain the coordinate information of the pixel point after interpolation, and then the second medical image is projected to the polar coordinate based on the interpolated coordinate information corresponding to each pixel point, so as to obtain the third medical image in the polar coordinate.
The second medical image is used for describing the attenuation degree of the object tissue to the plurality of light beams, each light beam corresponds to a plurality of tissue points in the object tissue, and each tissue point can absorb the energy of the light beam, so that the attenuation degree of each tissue point to the light beam can be recorded in the second medical image, the attenuation degree of the tissue point to the light beam is recorded through the attenuation degree values corresponding to the pixel points and the pixel points, and the attenuation degree of the tissue point to the light beam of the object tissue can be recorded in the interpolated second medical image corresponding to the second medical image. Furthermore, after the third medical image is obtained by projection based on the interpolated second medical image, the attenuation degree of the tissue point of the target tissue to the light beam is recorded in the third medical image, and the third medical image includes a plurality of rows of attenuation degree values because of the plurality of light beams.
The preset difference algorithm may be, but is not limited to, one of a nearest neighbor interpolation algorithm, a bilinear interpolation algorithm, and a bicubic interpolation algorithm, and the specific implementation process may refer to an implementation process of an interpolation algorithm in the prior art, which is not described herein again.
In an embodiment of the present application, with reference to fig. 4, the acquiring medical diagnostic information of the tissue of the subject according to the third medical image includes:
s31: and determining a target vector corresponding to the first medical image, wherein the target vector comprises the maximum attenuation degree value in each column of attenuation degree values in the third medical image.
S32: and determining a target proportion corresponding to the first medical image based on the target vector, wherein the target proportion refers to the proportion of the attenuation degree value larger than the preset attenuation degree value in the target vector.
S33: medical diagnostic information of the subject tissue is determined based on the target ratio.
In this embodiment, when the attenuation degree value is greater than the preset attenuation degree value, it indicates that there is abnormal degree of attenuation of the light by the abnormal tissue in the target tissue, for example, a diseased tissue point in the target tissue may absorb more light energy, so that the degree of attenuation of the light beam by the tissue point is greater than that of other normal tissue points. The preset attenuation degree value can be set according to actual requirements.
The target proportion corresponding to the first medical image is used for describing the proportion occupied by the abnormal attenuation degree value, and the purpose is to determine whether the object tissue described by the first medical image is abnormal through the target proportion, for example, whether a pathological tissue exists in the object tissue is known through the target proportion.
In this embodiment, in order to improve the efficiency of data processing and determine whether an abnormal tissue point exists in the direction irradiated by each beam irradiating the target tissue, the maximum attenuation degree value in each column of attenuation degree values in the third medical image is determined, so as to describe whether each beam irradiates the abnormal tissue point through each maximum attenuation degree value, further obtain a target vector from each maximum attenuation degree value, and describe the condition of the target tissue corresponding to the first medical image through the target vector. Meanwhile, in order to determine whether the target tissue described by the first medical image is abnormal, the proportion of the attenuation degree value larger than the preset attenuation degree value in the target vector is determined, so that the overall condition of the target tissue is determined according to the target proportion, that is, whether the target tissue described by the first medical image has a lesion is determined according to whether the target proportion is larger than the preset proportion, and thus the medical diagnosis information of the target tissue is determined.
In some embodiments, the target proportion corresponding to the first medical image is calculated by the following formula (1):
wherein, IPAxRepresenting the target proportion, mu, corresponding to the first medical imagetI.e. the value in the target vector, N (mu)t>x) representing a value of μ greater than a preset attenuation level value xtTotal number of (2), NtotalThe total number of the light beams corresponding to the third medical image, that is, the number of columns included in the third medical image, is represented, and M is a parameter preset for magnifying the calculation result.
In an embodiment of the present application, in conjunction with fig. 5, the number of the first medical images is plural;
determining medical diagnostic information of the tissue of the subject based on the target ratio, comprising:
s41: and determining a target value according to the target proportion corresponding to each first medical image in the plurality of first medical images, wherein the target value is used for indicating the number of the first medical images of which the corresponding target proportion is larger than the preset proportion in the plurality of first medical images.
S42: and when the target value is larger than the preset value, determining the pathological change information of the target tissue and obtaining the medical diagnosis information of the target tissue.
In the present embodiment, the preset ratio refers to a minimum ratio value for determining whether or not there is an abnormality in the tissue of the subject included in the first medical image. It is understood that when the target ratio is larger than the preset ratio, the attenuation degree of the light beam by the object tissue is also larger than a certain attenuation degree, that is, the object tissue has an abnormality.
The preset numerical value describes the minimum number of the first medical images in which the target proportion is larger than the preset proportion when the lesion tissue exists in the tissue of the diagnosis target. For example, when the length of the lesion is greater than or equal to 4mm, it is determined that the lesion exists in the target tissue, and since the length of the target tissue corresponding to one first medical image is 0.2mm, 20 corresponding first medical images whose target ratio is greater than the preset ratio are required to be combined to determine that the lesion exists in the target tissue.
In order to be able to diagnose the lesion position in the human body or the animal completely and accurately, the number of the first medical images acquired by the medical equipment is multiple, and the target value is determined according to the target proportion corresponding to each first medical image in the multiple first medical images, so as to determine the first medical image of which the corresponding target proportion is greater than the preset proportion from the multiple first medical images, so that the lesion information of the object tissue is obtained by combining the one or more first medical images of which the corresponding target proportion is greater than the preset proportion, thereby obtaining the medical diagnosis information corresponding to the object tissue.
In some embodiments, in order to better determine the lesion information of the subject tissue and obtain the medical diagnosis information of the subject tissue, the test is performed in advance through a test experiment to obtain the preset ratio. For example, a plurality of test medical image samples are obtained in advance, a medical expert marks lesion information in the test medical image samples, then the reference attenuation degree value is changed to confirm a target proportion corresponding to each test medical image sample, and each test medical image sample is distinguished through a reference proportion corresponding to the reference attenuation degree value set each time, so that a distinguishing effect corresponding to the set reference proportion is known, that is, each test medical sample recorded with the lesion information can be distinguished and processed more accurately through the set reference proportion. By analogy, when a reference proportion is determined to meet the actual requirement, the reference proportion is fixed to serve as a preset proportion, and the reference proportion and the corresponding reference attenuation degree value are fixed to serve as a preset attenuation degree value.
In some embodiments, the target value is indicative of a number of consecutive first medical images of the plurality of first medical images for which the corresponding target proportion is greater than a preset proportion.
In an embodiment of the present application, in order to more intuitively display a target tissue, the embodiment provides a method for acquiring medical diagnosis information, and the specific implementation manner includes:
generating a carpet exhibition diagram for displaying the object tissue according to the plurality of first medical images, wherein the carpet exhibition diagram is one of a plane carpet exhibition diagram or a curved carpet exhibition diagram.
In this embodiment, in order to better show the condition of the object tissue, an attenuation degree value matrix is constructed and obtained based on the target vector corresponding to each first medical image, and the attenuation degree value matrix is used as a carpet exhibition diagram to show the medical condition of the object tissue through the carpet exhibition diagram.
In this embodiment, since the carpet extension map can be used for the medical condition of the object tissue, and each first medical image in each carpet extension map records a part of the object tissue, and the first medical image with the target proportion larger than the preset proportion describes the region where the lesion occurs in the object tissue, when the object tissue has the lesion, the lesion region in the object tissue can be located based on the position of the first medical image with the target proportion larger than the preset proportion in the carpet extension map, so as to obtain the lesion information of the object tissue and the medical diagnosis information of the object tissue.
It is to be understood that the planar carpet representation is a two-dimensional carpet representation and the curved carpet representation is a three-dimensional curved carpet representation, wherein the planar carpet representation is converted into the three-dimensional curved carpet representation for a more intuitive viewing of the entire object tissue.
Illustratively, in conjunction with fig. 6, the object tissue is a blood vessel, and a planar carpet-out fig. 8A, or a three-dimensional curved carpet-out fig. 8B is generated from the respective first medical images describing the blood vessel.
In an example, when a lesion is determined to be present from the lesion information, a carpet display map is generated.
In an embodiment, the specific implementation of generating the carpet display map according to the plurality of first medical images includes:
and inputting each first medical image into a target image synthesis model for processing according to a preset sequence to obtain a second medical image corresponding to each first medical image.
And performing linear interpolation on the coordinate information of the pixel points in the second medical image corresponding to each first medical image to obtain the interpolated second medical image corresponding to each first medical image.
And projecting the interpolated second medical image corresponding to each first medical image to a polar coordinate to obtain a third medical image.
And determining the maximum attenuation degree value in each column of attenuation degree values of the third medical image corresponding to each first medical image, and obtaining the target vector corresponding to each first medical image according to the maximum attenuation degree value in each column of attenuation degree values of the third medical image corresponding to each first medical image.
And constructing an attenuation degree value matrix according to the target vector corresponding to each first medical image, and taking the attenuation degree value matrix as a carpet exhibition diagram.
With reference to fig. 7, in an embodiment of the present application, the process of training to obtain a target image synthesis model includes:
s51: the method comprises the steps of obtaining a plurality of groups of training samples, wherein each group of training samples in the plurality of groups of training samples comprises a first medical image sample and a second medical image sample, the first medical image sample is obtained by acquiring a target tissue sample through medical equipment, the second medical image sample is determined based on the first medical image sample and optical hardware testing parameters of the medical equipment, and the second medical image sample is used for describing the attenuation degree of the target tissue sample to light beams.
S52: and training the image synthesis model which is not trained on the basis of the plurality of groups of training samples to obtain the target image synthesis model.
In this embodiment, the first medical image sample comprises image information of a subject tissue sample.
The optical hardware testing parameters of the medical equipment are obtained by performing testing calculation on the medical equipment which acquires the first medical image sample.
It can be understood that, in order to know whether there is an abnormality in the target tissue, after acquiring the medical image including the image information of the target tissue by the medical device, the optical hardware test parameters of the medical device need to be measured manually, so as to determine the medical diagnostic information of the target tissue by determining the attenuation degree of the target tissue to the light beam based on the acquired medical image and the optical hardware test parameters of the medical device, which is time-consuming and labor-consuming, therefore, a plurality of sets of training samples are acquired, and the image synthesis model which is not trained is trained based on the plurality of sets of training samples to obtain the target image synthesis model, which aims to directly synthesize the acquired medical image by the target image synthesis model to obtain the medical image capable of describing the attenuation degree of the target tissue to the light beam, and further obtain the medical diagnostic information of the target tissue, therefore, the data processing efficiency is improved, and the situation that medical diagnosis information determined based on the medical image and the optical hardware parameters has errors and is not beneficial to disease diagnosis can be avoided due to errors of the optical hardware parameters of the medical equipment caused by the manufacturing process during the manufacturing of the medical equipment.
It is understood that the first medical image sample in each set of training samples may be acquired based on the same medical device or may be acquired based on different medical devices.
In some embodiments, since hardware parameters of the medical device used for acquiring the first medical image may be different, for each set of training samples, calibration may be performed using optical hardware test parameters of the medical device that acquires the first medical image sample in the training samples, so that the training samples can be distinguished to facilitate a training operation on an unfinished training image synthesis model.
In some embodiments, in practical applications, since the number of the first medical image samples labeled with the lesion information by the expert is small, the training sample size may be expanded by rotating, flipping, adjusting the contrast, and the like, so as to obtain multiple groups of training samples.
In an embodiment of the present application, training an image synthesis model that is not trained based on a plurality of sets of training samples to obtain a target image synthesis model includes:
and extracting a group of training samples from the plurality of groups of training samples according to a specified extraction mode to obtain a training sample group.
The method comprises the steps of carrying out forward circulation training on an unfinished image synthesis model based on a training sample group to obtain a first training result and first image loss information, carrying out reverse circulation training on the unfinished image synthesis model based on the training sample group to obtain a second training result and second image loss information, wherein the first image loss information is used for indicating the loss information of images synthesized by the unfinished image synthesis model in the forward circulation training, and the second image loss information is used for indicating the loss information of images synthesized by the unfinished image synthesis model in the reverse circulation training.
And if the training end condition is determined not to be reached according to the first training result and the second training result, adjusting model parameters of the image synthesis model which is not trained on the basis of the first image loss information and the second image loss information, and returning to the step of extracting a group of training samples from the groups of training samples according to a specified extraction mode to obtain a training sample group.
And determining the image synthesis model obtained by training as the target image synthesis model until the training end condition is determined to be reached according to the first training result and the second training result.
In this embodiment, the specified extraction manner describes a manner of training an image synthesis model that has not been trained by using a plurality of sets of training samples. For example, a training sample set is obtained by extracting a set of training samples from a plurality of sets of training samples according to the storage sequence of the training samples or the time sequence of constructing the training samples.
The first training result is used for describing whether a training target of forward cycle training is achieved.
The second training result is used for describing whether the training target of the reverse cycle training is achieved.
In this embodiment, in the process of performing forward loop training on the image synthesis model that is not trained based on the training sample set, because parameters of the model are not accurate enough, a part of image information is lost when performing forward loop training on the medical image samples in the training sample set to obtain a synthesized image, and a part of image information is lost when performing reverse loop training to obtain a synthesized image. Therefore, in order to enable the image synthesis model to synthesize better images, when it is determined that the training end condition is not reached according to the first training result and the second training result, model parameters of the image synthesis model which is not trained are continuously adjusted based on the first image loss information and the second image loss information, and a set of training samples are continuously extracted from a plurality of sets of training samples according to a specified extraction mode to obtain a training sample set, so that model parameters of the image synthesis model which is not trained are continuously adjusted based on the first image loss information and the second image loss information, so that the image synthesis model which is not trained can better perform synthesis processing on input medical images based on the adjusted model parameters, thereby reducing the loss of image information and enabling the synthesized images to be more accurate.
In some embodiments, a set of training samples is extracted from a plurality of sets of training samples according to a specified extraction mode to obtain a training sample set, and forward loop training and reverse loop training are performed on the unfinished image synthesis model based on the training sample set, wherein after the forward loop training and the reverse loop training are performed on the unfinished image synthesis model based on the training sample set, another set of training samples is extracted, and then the forward loop training and the reverse loop training are performed on the unfinished image synthesis model until a training end condition is reached.
It can be understood that, when each group of training samples in the plurality of groups of training samples is extracted according to the designated extraction mode, forward cycle training and reverse cycle training are respectively performed on the image synthesis model which is not trained yet, and the training end condition is not reached yet, the step of extracting one group of training samples from the plurality of groups of training samples according to the designated extraction mode is continuously performed to obtain the training sample group.
In an embodiment of the present application, based on a training sample set, performing forward loop training on an unfinished training image synthesis model, and specifically implementing to obtain a first training result and first image loss information may include:
based on a first medical image sample in the training sample group, a first synthesized medical image is determined through a first synthesizer in the image synthesis model which is not trained, and the similarity between the first synthesized medical image and a second medical image sample in the training sample group is determined through a first discriminator in the image synthesis model which is not trained, so that a first training result is obtained.
Determining, by a second synthesizer in the unfinished trained image synthesis model, a second synthesized medical image based on the first synthesized medical image, and determining first image loss information based on the second synthesized medical image and the first medical image sample in the training sample set.
In this embodiment, after determining the first synthesized medical image by the first synthesizer in the unfinished training image synthesis model based on the first medical image sample in the training sample set, in order to verify the synthesis accuracy of the first synthesizer, the similarity between the first synthesized medical image and the second medical image sample in the training sample set is determined by the first discriminator in the unfinished training image synthesis model, and the first training result is obtained, so that the accuracy of the synthesis processing operation of the first synthesizer can be known by the first training result.
Meanwhile, in order to determine a processing defect point when the first synthesizer processes the medical image, based on the first synthesized medical image, the second synthesized medical image is determined through the second synthesizer in the image synthesis model which is not trained, so that the first image loss information is determined based on the second synthesized medical image and the first medical image sample in the training sample group, and the image processing defect point of the first synthesizer is described through the first image loss information, so that the model parameter of the first synthesizer is adjusted based on the first image loss information, so that the subsequent first synthesizer can better process the medical image input to the first synthesizer based on the adjusted model parameter, namely the first synthesizer can perform emphasis processing based on the pixel point in the image described by the first image loss information, to avoid loss of the image of the part when the composite medical image is obtained.
Illustratively, referring to FIG. 8, a first medical image sample (Img)OCT) Input to a first synthesizer (Syn)IPA) To obtain a first synthetic medical image (Syn)IPA(ImgOCT) Then, via a first discriminator (Dis)IPA) Determining a first synthetic medical image (Syn)IPA(ImgOCT) And a second medical image sample (Real) in the training sample setIPAImg) similarity between them, resulting in a first training result.
In addition, the second synthesizer (Syn) in the model is synthesized by the images not trained yetOCT) For the first synthetic medical image (Syn)IPA(ImgOCT) Performing a synthesis process to obtain a second synthetic medical image (Syn)OCT(SynIPA(ImgOCT) And) and based on the second synthetic medical image (Syn)OCT(SynIPA(ImgOCT) ))) with the first medical image sample (Img) in the training sample setOCT) First image loss information is determined.
In some embodiments, the similarity between the first composite medical image and the second medical image sample in the training sample set is determined by the following equation (2):
LossIPA＝(1-DisIPA(ImgIPA))2+DisIPA(SynIPA(ImgOCT))2 (2)
therein, DisIPA() Shown is a discriminator for discriminating whether an input image is authentic or not. Dis (disease)IPA(ImgIPA) Indicating that the first discriminator judges the second medical image sample to determine whether the second medical image sample is authentic. SynIPA(ImgOCT) Representing that a first medical image sample is subjected to synthesis processing by a first synthesizer in the unfinished training image synthesis model to obtain a first synthesized medical image, DisIPA(SynIPA(ImgOCT))2Indicating that the first discriminator discriminates the first composite medical image to determine whether the first composite medical image is authentic. ImgOCTRepresenting a first medical image sample, ImgIPARepresenting a second medical image sample.
Exemplary, DisIPA(ImgIPA) Indicates the first discriminationWhen the discriminator judges the second medical image sample, the image input into the discriminator is the real second medical image sample DisIPA() The output of (1) indicates that the input image is a real image, DisIPA(SynIPA(ImgOCT))2Indicating that the first discriminator is judging the first composite medical image, due to the input of the first discriminator DisIPA() The synthesized image of (1), if DisIPA() The output result is 0, which indicates that the synthesized image is completely different from the second medical image sample, and if the first synthesized medical image obtained by the first synthesizer performing synthesis processing on the first medical image sample is not greatly different from the second medical image sample, DisIPA() The closer the output result will be to 1, e.g. the better the combining performance of the first combiner, the Dis will beIPA(SynIPA(ImgOCT))2The corresponding output result is 0.5, so that the synthesis performance of the first synthesizer is measured based on the output result.
It is understood that, since the first discriminator is used to judge the authenticity of the input image, when the first discriminator is used to judge the authentic second medical image sample, the output result is 1, and when the first discriminator is used to judge the first composite medical image, since the first composite medical image is synthesized and a part of image information may be lost when the first composite medical image is synthesized, so that there may be a certain difference between the first composite medical image and the second medical image sample, the output result of the first discriminator is between 0 and 1. Thus, LossIPACan be used to describe the similarity between the first synthesized medical image and the second medical image sample in the training sample set, and use this as the first training result to characterize the synthesis accuracy of the first synthesizer.
In an embodiment of the present application, based on the training sample set, performing reverse loop training on the image synthesis model that is not trained, and obtaining the second training result and the second image loss information may include:
determining a third synthetic medical image through a second synthesizer in the image synthesis model which is not trained based on a second medical image sample in the training sample group, and determining the similarity between the third synthetic medical image and the first medical image sample in the training sample group through a second discriminator in the image synthesis model which is not trained to obtain a second training result;
a fourth synthetic medical image is determined by the first synthesizer in the unfinished training image synthesis model based on the third synthetic medical image, and second image loss information is determined based on the fourth synthetic medical image and a second medical image sample in the training sample set.
In this embodiment, after determining the third synthesized medical image by the second synthesizer in the unfinished training image synthesis model based on the second medical image sample in the training sample set, in order to verify the synthesis accuracy of the second synthesizer, the similarity between the third synthesized medical image and the first medical image sample in the training sample set is determined by the second discriminator in the unfinished training image synthesis model, and the second training result is obtained, so that the accuracy of the synthesis processing operation of the second synthesizer can be known by the second training result.
Meanwhile, in order to determine a processing defect point when the second synthesizer processes the medical image, based on the third synthesized medical image, the fourth synthesized medical image is determined through the first synthesizer in the image synthesis model which is not trained, so that the second image loss information is determined based on the fourth synthesized medical image and the second medical image sample in the training sample group, and the image processing defect point of the second synthesizer is described through the second image loss information, so that the model parameter of the second synthesizer is adjusted based on the second image loss information, so that the subsequent second synthesizer can better process the medical image input to the second synthesizer based on the adjusted model parameter, that is, the second synthesizer can perform the processing with emphasis based on the pixel point in the image described by the second image loss information, to avoid loss of the image of the part when the composite medical image is obtained.
Illustratively, referring to FIG. 9, a second medical image sample (Img)IPA) Input to a second synthesizer (Syn)OCT) To obtain a third synthetic medical image (Syn)OCT(ImgIPA) Then, through a second discriminator (Dis)OCT) Determining a third synthetic medical image (Syn)OCT(ImgIPA) With the first medical image sample (Real) in the training sample setOCTImg) similarity between the two, and a second training result is obtained.
In addition, the first synthesizer (Syn) in the model is synthesized by the images which are not trainedIPA) For the third synthetic medical image (Syn)OCT(ImgIPA) Performing a synthesis process to obtain a fourth synthetic medical image (Syn)IPA(SynOCT(ImgIPA) And) and based on a fourth synthetic medical image (Syn)IPA(SynOCT(ImgIPA) ))) with a second medical image sample (Img) in the training sample setIPA) And determining second image loss information.
In some embodiments, the similarity between the third synthetic medical image and the first medical image sample in the training sample set is determined by the following equation (3):
LossOCT＝(1-DisOCT(ImgOCT))2+DisOCT(SynOCT(ImgOCT))2 (3)
therein, DisOCT() Shown is a discriminator for discriminating whether an input image is authentic or not. Dis (disease)OCT(ImgOCT) Indicating that the second discriminator performs a decision on the first medical image sample to determine whether the first medical image sample is authentic. SynOCT(ImgOCT) Representing the processing of the second medical image sample by the second synthesizer to obtain a third synthesized medical image, DisOCT(SynOCT(ImgOCT))2Indicating that the second discriminator discriminates the third composite image to determine whether the third composite medical image is authentic.
Exemplary, DisOCT(ImgOCT) Representing the judgment of the first medical image sample by the second discriminatorWhen it is determined that the image input to the second discriminator is a true first medical image sample, DisOCT() The result of (1) is 1, i.e., an image indicating that the input image is real. Dis (disease)OCT(SynOCT(ImgOCT))2Indicating that the second discriminator is judging the third synthetic medical image, however, due to the input of the second discriminator DisOCT() The synthesized image of (1), if DisOCT() The output result is 0, which indicates that the synthesized image is completely different from the first medical image sample, and if the third synthesized medical image obtained by synthesizing the second medical image sample by the second synthesizer is not much different from the first medical image sample, then DisOCT() The closer the output result will be to 1. For example, when the second synthesizer has better synthesis performance, less image information is lost in the process of synthesizing the third synthesized medical image, so that the difference between the third synthesized medical image and the first medical image sample is not large, and Dis is generated at this timeOCT(SynOCT(ImgOCT))2The corresponding output result is 0.8, and the combining performance of the second combiner can be measured based on the output result.
It can be understood that, since the second discriminator can be used to judge the authenticity of the input image, when the second discriminator is used to judge the authentic first medical image sample, the output result is 1, and when the second discriminator is used to judge the third synthesized medical image, since the third synthesized medical image is synthesized and a part of image information may be lost when the third synthesized medical image is synthesized, so that there may be a certain difference between the third synthesized medical image and the first medical image sample, the output result of the second discriminator is between 0 and 1. Thus, LossOCTCan be used to describe the similarity between the third synthesized medical image and the first medical image sample in the training sample set, and use this as the second training result to characterize the synthesis accuracy of the second synthesizer.
In some embodiments, in order to determine the training effect when the unfinished image synthesis model is trained based on the training samples, a third training result is further calculated to describe whether the training end condition is reached through the third training result.
Specifically, the third training result is calculated by the following formula (4):
therein, SynOCT(SynIPA(ImgOCT) Representing that the first synthetic medical image is synthesized by a second synthesizer in the image synthesis model which is not trained to obtain a second synthetic medical image, | SynOCT(SynIPA(ImgOCT))-ImgOCTI denotes determining first image loss information based on the second synthetic medical image and first medical image samples in the training sample set, SynIPA(SynOCT(ImgIPA) Representing that the third synthetic medical image is subjected to synthetic processing through a first synthesizer in the image synthetic model which is not trained, so that a fourth synthetic medical image is obtained; | SynIPA(SynOCT(ImgIPA))-ImgIPAAnd | represents determining second image loss information based on the fourth synthesized medical image and a second medical image sample in the training sample set.
Representing a predetermined weight coefficient for the first medical image sample,
representing a predetermined weight coefficient for the second medical image sample.
It can be understood that when the third training result LossCycleAnd when the image loss is indicated to reach the preset image loss value, the training end condition is reached. Therefore, it is determined that the training end condition is reached according to the first training result, the second training result, and the third training result, and the image synthesis model obtained by training is determined as the target image synthesis model. Wherein the default image loss value can be the rootAnd presetting according to actual requirements.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Fig. 10 shows a block diagram of a device for acquiring medical diagnostic information according to an embodiment of the present application, which corresponds to the method for acquiring medical diagnostic information according to the above embodiment, and only shows the relevant parts according to the embodiment of the present application for convenience of description.
Referring to fig. 10, the apparatus 100 includes:
a first obtaining module 101, configured to obtain a first medical image acquired by a medical device, where the first medical image includes image information of a target tissue;
a processing module 102, configured to input the first medical image into the target image synthesis model for processing, so as to obtain a second medical image, where the second medical image is used to describe an attenuation degree of the object tissue to a light beam emitted by a light source used for scanning the object tissue;
a second obtaining module 103, configured to obtain medical diagnostic information of the object tissue according to the second medical image.
In an embodiment, the second obtaining module 103 is further configured to perform linear interpolation on coordinate information of a pixel point in the second medical image to obtain an interpolated second medical image; projecting the interpolated second medical image to a polar coordinate to obtain a third medical image, wherein the third medical image comprises a plurality of rows of attenuation degree values, each row of attenuation degree values corresponds to one light beam, and each row of attenuation degree values is used for indicating the attenuation degree of the object tissue to the light beam corresponding to each row of attenuation degree values; medical diagnostic information of the subject tissue is acquired from the third medical image.
In an embodiment, the second obtaining module 103 is further configured to determine a target vector corresponding to the first medical image, where the target vector includes a maximum attenuation degree value in each column of attenuation degree values in the third medical image; determining a target proportion corresponding to the first medical image based on the target vector, wherein the target proportion refers to the proportion of attenuation degree values larger than a preset attenuation degree value in the target vector; medical diagnostic information of the subject tissue is determined based on the target ratio.
In an embodiment, the number of the first medical images is plural.
The second obtaining module 103 is further configured to determine a target value according to a target proportion corresponding to each of the plurality of first medical images, where the target value is used to indicate the number of the first medical images in which the corresponding target proportion in the plurality of first medical images is greater than a preset proportion; and when the target value is larger than the preset value, determining the pathological change information of the target tissue and obtaining the medical diagnosis information of the target tissue.
In an embodiment, the apparatus further comprises a generation module.
A generating module, configured to generate a carpet display map according to the plurality of first medical images, where the carpet display map is used to display the object tissue, and the carpet display map includes any one of a planar carpet display map or a three-dimensional curved carpet display map.
In one embodiment, the apparatus 100 further comprises a training module.
The training module is used for acquiring a plurality of groups of training samples, each group of training samples in the plurality of groups of training samples comprises a first medical image sample and a second medical image sample, the first medical image sample is acquired by medical equipment on a target tissue sample, the second medical image sample is determined based on the first medical image sample and optical hardware testing parameters of the medical equipment, and the second medical image sample is used for describing the attenuation degree of the target tissue sample on a light beam; and training the image synthesis model which is not trained on the basis of the plurality of groups of training samples to obtain the target image synthesis model.
In an embodiment, the training module is further configured to extract a set of training samples from the plurality of sets of training samples according to a specified extraction manner, so as to obtain a training sample set; performing forward cycle training on the image synthesis model which is not trained on the basis of a training sample group to obtain a first training result and first image loss information, and performing reverse cycle training on the image synthesis model which is not trained on the basis of the training sample group to obtain a second training result and second image loss information, wherein the first image loss information is used for indicating the loss information of the images which are synthesized by the image synthesis model which is not trained in the forward cycle training, and the second image loss information is used for indicating the loss information of the images which are synthesized by the image synthesis model which is not trained in the reverse cycle training; if the training end condition is determined not to be met according to the first training result and the second training result, adjusting model parameters of the image synthesis model which is not trained on the basis of the first image loss information and the second image loss information, and returning to the step of extracting a group of training samples from a plurality of groups of training samples according to a specified extraction mode to obtain a training sample group; and determining the image synthesis model obtained by training as the target image synthesis model until the training end condition is determined to be reached according to the first training result and the second training result.
In an embodiment, the training module is further configured to determine, based on a first medical image sample in the training sample set, a first synthesized medical image through a first synthesizer in the image synthesis model that is not trained, and determine, through a first discriminator in the image synthesis model that is not trained, a similarity between the first synthesized medical image and a second medical image sample in the training sample set to obtain a first training result; determining, by a second synthesizer in the unfinished trained image synthesis model, a second synthesized medical image based on the first synthesized medical image, and determining first image loss information based on the second synthesized medical image and the first medical image sample in the training sample set.
In an embodiment, the training module is further configured to determine, based on a second medical image sample in the training sample set, a third synthetic medical image through a second synthesizer in the unfinished training image synthesis model, and determine, through a second discriminator in the unfinished training image synthesis model, a similarity between the third synthetic medical image and the first medical image sample in the training sample set to obtain a second training result; a fourth synthetic medical image is determined by the first synthesizer in the unfinished training image synthesis model based on the third synthetic medical image, and second image loss information is determined based on the fourth synthetic medical image and a second medical image sample in the training sample set.
The apparatus for acquiring medical diagnostic information provided in this embodiment is used to implement a method for acquiring medical diagnostic information in the method embodiment, where the functions of each module may refer to corresponding descriptions in the method embodiment, and the implementation principle and technical effect thereof are similar, and are not described herein again.
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 11, the electronic apparatus 7 of this embodiment includes: at least one processor 70 (only one processor is shown in fig. 11), a memory 71, and a computer program 72 stored in the memory 71 and executable on the at least one processor 70, the steps in any of the various above-described method embodiments for obtaining medical diagnostic information being implemented by the processor 70 when the computer program 72 is executed by the processor.
The electronic device 7 may be a computing device such as a medical device, a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device may include, but is not limited to, a processor 70, a memory 71. Those skilled in the art will appreciate that fig. 11 is merely an example of the electronic device 7, and does not constitute a limitation of the electronic device 7, and may include more or less components than those shown, or combine some of the components, or different components, such as an input-output device, a network access device, and the like.
The Processor 70 may be a Central Processing Unit (CPU), and the Processor 70 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), off-the-shelf Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 71 may in some embodiments be an internal storage unit of the electronic device 7, such as a hard disk or a memory of the electronic device 7. The memory 71 may also be an external storage device of the electronic device 7 in other embodiments, such as a plug-in hard disk provided on the electronic device 7, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 71 may also include both an internal storage unit of the electronic device 7 and an external storage device. The memory 71 is used for storing an operating system, an application program, a BootLoader (BootLoader), data, and other programs, such as program codes of a computer program. The memory 71 may also be used to temporarily store data that has been output or is to be output.
It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.
The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments may be implemented.
Embodiments of the present application provide a computer program product, which when executed on an electronic device, enables the electronic device to implement the steps in the above method embodiments.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791497.3A CN113380381B (en) | 2021-07-13 | 2021-07-13 | Method, device, electronic device and storage medium for obtaining medical diagnosis information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791497.3A CN113380381B (en) | 2021-07-13 | 2021-07-13 | Method, device, electronic device and storage medium for obtaining medical diagnosis information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113380381A true CN113380381A (en) | 2021-09-10 |
| CN113380381B CN113380381B (en) | 2024-12-06 |
Family
ID=77581869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110791497.3A Active CN113380381B (en) | 2021-07-13 | 2021-07-13 | Method, device, electronic device and storage medium for obtaining medical diagnosis information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113380381B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094922A (en) * | 2022-05-11 | 2023-11-21 | 深圳市中科微光医疗器械技术有限公司 | Multi-mode image display optimization method and device and terminal equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180235563A1 (en) * | 2015-08-17 | 2018-08-23 | Samsung Electronics Co., Ltd. | Medical image display device and medical image processing method |
| CN109461495A (en) * | 2018-11-01 | 2019-03-12 | 腾讯科技（深圳）有限公司 | A kind of recognition methods of medical image, model training method and server |
| US20200184639A1 (en) * | 2018-12-11 | 2020-06-11 | Medicalip Co., Ltd. | Method and apparatus for reconstructing medical images |
| WO2020202680A1 (en) * | 2019-03-29 | 2020-10-08 | キヤノン株式会社 | Information processing device and information processing method |
| US20210343012A1 (en) * | 2019-06-21 | 2021-11-04 | Tencent Technology (Shenzhen) Company Limited | Medical image classification method, model training method, computing device, and storage medium |
| CN113631080A (en) * | 2019-03-29 | 2021-11-09 | 佳能株式会社 | Information processing apparatus and information processing method |
-
2021
- 2021-07-13 CN CN202110791497.3A patent/CN113380381B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180235563A1 (en) * | 2015-08-17 | 2018-08-23 | Samsung Electronics Co., Ltd. | Medical image display device and medical image processing method |
| CN109461495A (en) * | 2018-11-01 | 2019-03-12 | 腾讯科技（深圳）有限公司 | A kind of recognition methods of medical image, model training method and server |
| WO2020088469A1 (en) * | 2018-11-01 | 2020-05-07 | 腾讯科技（深圳）有限公司 | Medical image identifying method, model training method, and computer device |
| US20200184639A1 (en) * | 2018-12-11 | 2020-06-11 | Medicalip Co., Ltd. | Method and apparatus for reconstructing medical images |
| WO2020202680A1 (en) * | 2019-03-29 | 2020-10-08 | キヤノン株式会社 | Information processing device and information processing method |
| CN113631080A (en) * | 2019-03-29 | 2021-11-09 | 佳能株式会社 | Information processing apparatus and information processing method |
| US20210343012A1 (en) * | 2019-06-21 | 2021-11-04 | Tencent Technology (Shenzhen) Company Limited | Medical image classification method, model training method, computing device, and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王天任 等: "医学图像数据增强技术的研究现状与进展", 中国当代医药, vol. 28, no. 3, pages 34 - 37 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094922A (en) * | 2022-05-11 | 2023-11-21 | 深圳市中科微光医疗器械技术有限公司 | Multi-mode image display optimization method and device and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113380381B (en) | 2024-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11941812B2 (en) | Diagnosis support apparatus and X-ray CT apparatus | |
| US11423554B2 (en) | Registering a two-dimensional image with a three-dimensional image | |
| JP5814504B2 (en) | Medical image automatic segmentation system, apparatus and processor using statistical model | |
| Röhl et al. | Dense GPU‐enhanced surface reconstruction from stereo endoscopic images for intraoperative registration | |
| JP2022544229A (en) | 3D Object Segmentation of Localized Medical Images Using Object Detection | |
| JP6448356B2 (en) | Image processing apparatus, image processing method, image processing system, and program | |
| CN112150524A (en) | A two-dimensional and three-dimensional medical image registration method and system based on deep learning | |
| US20130257910A1 (en) | Apparatus and method for lesion diagnosis | |
| US9504450B2 (en) | Apparatus and method for combining three dimensional ultrasound images | |
| CN107464231A (en) | For the system and method for the optimal operation parameter for determining medical imaging | |
| US20200327979A1 (en) | Medical information processing apparatus and medical information processing method | |
| JP6824845B2 (en) | Image processing systems, equipment, methods and programs | |
| JP2017035469A (en) | Image processing apparatus, image processing method, and program | |
| JP6888041B2 (en) | How to get a medical sagittal image, how to train a neural network to get a medical sagittal image, and a computer device | |
| US20230410270A1 (en) | Image processing apparatus, image processing method, and program | |
| KR20200110111A (en) | Method and devices for diagnosing dynamic multidimensional disease based on deep learning in medical image information | |
| CN114820483A (en) | Image detection method and device and computer equipment | |
| Kim et al. | Deep-learning-based cerebral artery semantic segmentation in neurosurgical operating microscope vision using indocyanine green fluorescence videoangiography | |
| US11138736B2 (en) | Information processing apparatus and information processing method | |
| JP2024536163A (en) | Methods for survey scanning in diagnostic medical imaging - Patents.com | |
| US8805122B1 (en) | System, method, and computer-readable medium for interpolating spatially transformed volumetric medical image data | |
| US9585569B2 (en) | Virtual endoscopic projection image generating device, method and program | |
| CN113380381B (en) | Method, device, electronic device and storage medium for obtaining medical diagnosis information | |
| US11227399B2 (en) | Analysis apparatus, ultrasound diagnostic apparatus, and analysis method | |
| US20210150739A1 (en) | Capturing a misalignment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |