[go: up one dir, main page]

CN114820663B - Assistant positioning method for determining radio frequency ablation therapy - Google Patents

Assistant positioning method for determining radio frequency ablation therapy Download PDF

Info

Publication number
CN114820663B
CN114820663B CN202210737793.XA CN202210737793A CN114820663B CN 114820663 B CN114820663 B CN 114820663B CN 202210737793 A CN202210737793 A CN 202210737793A CN 114820663 B CN114820663 B CN 114820663B
Authority
CN
China
Prior art keywords
pixel point
image
abdominal
value
pixel
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.)
Active
Application number
CN202210737793.XA
Other languages
Chinese (zh)
Other versions
CN114820663A (en
Inventor
张永琳
刘玉芳
李绍霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Rizhao Tianyi Biomedical Technology Co ltd
Original Assignee
Rizhao Tianyi Biomedical Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Rizhao Tianyi Biomedical Technology Co ltd filed Critical Rizhao Tianyi Biomedical Technology Co ltd
Priority to CN202210737793.XA priority Critical patent/CN114820663B/en
Publication of CN114820663A publication Critical patent/CN114820663A/en
Application granted granted Critical
Publication of CN114820663B publication Critical patent/CN114820663B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
    • A61B6/03—Computed tomography [CT]
    • A61B6/032—Transmission computed tomography [CT]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • 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
    • G06T2207/10081—Computed x-ray tomography [CT]
    • 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
    • G06T2207/30096—Tumor; Lesion

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Radiology & Medical Imaging (AREA)
  • Animal Behavior & Ethology (AREA)
  • Optics & Photonics (AREA)
  • Pathology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Pulmonology (AREA)
  • Multimedia (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

The invention relates to the field of image processing, and provides an auxiliary positioning method for determining radio frequency ablation treatment, which comprises the following steps: acquiring an abdominal CT image; the richness of each pixel point is obtained through the CT value of each pixel point and the neighborhood pixel points on the abdominal CT image; partitioning the abdominal CT image, and taking the historical tumor probability of each region on the abdominal CT image as the attention of each pixel point of the region; obtaining a first enhancement coefficient of each pixel point; obtaining the adjusted CT values of all the pixel points; obtaining a second enhancement coefficient of each pixel point; acquiring a CT reconstruction value of each pixel point, and acquiring a new abdomen CT image through the CT reconstruction values of all the pixel points; and carrying out threshold segmentation on the new abdomen CT image to obtain a tumor region. The invention can obtain clearer tumor boundary and has simple method.

Description

Assistant positioning method for determining radio frequency ablation therapy
Technical Field
The invention relates to the field of artificial intelligence, in particular to an auxiliary positioning method for determining radio frequency ablation treatment.
Background
The liver is one of the five internal organs of the human body, mainly has metabolic function, and is an important organ for maintaining the life of the human body. Due to the influence of other factors such as poor eating habits, irregular work and rest and the like, tumor lesions of some tumors occur in liver parts, and then liver cancer is formed, which seriously threatens the life health of human beings. China is one of the high incidence areas of liver cancer, and the incidence rate and the fatality rate are high.
The radio frequency ablation treatment method is an effective treatment method for treating liver tumors, and the treatment method is to insert an electrode catheter into the center of a liver tumor through the femoral artery and vein, the internal jugular vein and the subclavian vein, then spread an electrode and start to perform radio frequency ablation. An important step before determining the radio frequency ablation treatment plan is to scan and locate the liver by CT, and (percutaneously) puncture the tumor after determining the tumor position and size. However, in clinical application, doctors still observe the tumor region in the CT image through their own knowledge and experience, but in the abdominal CT image, the tumor morphology is different between different individuals, and the gray scale difference between the tumor itself and the liver is small, so it is difficult to distinguish the clear tumor boundary, and therefore, a tumor CT image processing method is needed to improve the accuracy of the doctors in tumor identification.
The invention carries out image preprocessing on the liver region on the basis of carrying out liver segmentation on the abdominal CT image, so that the gray characteristic of the tumor is better extracted, the tumor boundary is clearer, and reliable early-stage data support and treatment assistance are provided for determining a radio frequency ablation treatment method and a treatment plan.
Disclosure of Invention
The invention provides an auxiliary positioning method for determining radio frequency ablation treatment, which aims to solve the problem that the boundary of the existing abdomen CT image is not clear.
The invention discloses an auxiliary positioning method for determining radio frequency ablation treatment, which adopts the following technical scheme that the method comprises the following steps:
acquiring an abdominal CT image;
obtaining the abundance of each pixel point on the abdominal CT image through the CT values of each pixel point and the adjacent pixel points on the abdominal CT image;
partitioning the abdominal CT image, and taking the historical tumor probability of each region on the abdominal CT image as the attention of each pixel point of the region;
obtaining a first enhancement coefficient of each pixel point according to the abundance and the attention of each pixel point on the abdominal CT image;
obtaining the adjusted CT values of all the pixel points through the first enhancement coefficient of each pixel point on the abdominal CT image and the CT values of all the pixel points on the abdominal CT image;
obtaining a second enhancement coefficient of each pixel point through the first enhancement coefficient of each pixel point and the maximum value in the adjusted CT values of all the pixel points;
reconstructing the CT value of each pixel point through the CT value, the first enhancement coefficient and the second enhancement coefficient of each pixel point on the abdominal CT image to obtain the CT reconstruction value of each pixel point, and obtaining a new abdominal CT image through the CT reconstruction values of all the pixel points;
and performing threshold segmentation on the new abdominal CT image to obtain a tumor region.
Further, according to the auxiliary positioning method for determining the radio frequency ablation therapy, the abdomen CT image is any one abdomen CT image in an abdomen CT image sequence of the same person, and other abdomen CT images in the abdomen CT image sequence are processed in the same way according to the processing method of the abdomen CT image.
Further, in the auxiliary positioning method for determining the radio frequency ablation therapy, the method for partitioning the abdominal CT image is:
and establishing a coordinate system on the abdominal CT image, and dividing each pixel point on the abdominal CT image into regions by using the coordinates of each pixel point on the abdominal CT image to obtain the region where each pixel point is located.
Further, in the auxiliary positioning method for determining the radio frequency ablation treatment, the CT value of each pixel point on the abdominal CT image is the redefined CT value of the pixel point;
the expression of the CT value redefined by the pixel point is as follows:
Figure DEST_PATH_IMAGE002
in the formula:
Figure DEST_PATH_IMAGE004
to represent
Figure DEST_PATH_IMAGE006
The newly defined CT value of the pixel point is processed,
Figure DEST_PATH_IMAGE008
to represent
Figure 656964DEST_PATH_IMAGE006
The CT value of the pixel point is located,
Figure DEST_PATH_IMAGE010
representing the maximum CT value in the abdominal CT image,
Figure DEST_PATH_IMAGE012
representing the minimum CT value in an abdominal CT image.
Further, in the auxiliary positioning method for determining the rf ablation therapy, the expression of the CT reconstruction value of the pixel point is:
Figure DEST_PATH_IMAGE014
in the formula:
Figure DEST_PATH_IMAGE016
to represent
Figure 26634DEST_PATH_IMAGE006
The reconstructed value of the CT at the pixel point,
Figure DEST_PATH_IMAGE018
a first enhancement coefficient representing a pixel point,
Figure DEST_PATH_IMAGE020
and a second enhancement coefficient representing a pixel point.
Further, in the method for determining an auxiliary location for rf ablation therapy, the expression of the second enhancement factor of the pixel point is:
Figure DEST_PATH_IMAGE022
in the formula:
Figure DEST_PATH_IMAGE024
and expressing the maximum value in the adjusted CT values of all the pixel points obtained by the first enhancement coefficients of the pixel points and the redefined CT values of all the pixel points on the abdominal CT image.
Furthermore, in the method for determining the auxiliary positioning for the radiofrequency ablation therapy, the first enhancement coefficient of each pixel point is obtained by dividing the richness and the attention of each pixel point;
the expression of the first enhancement coefficient of the pixel point is as follows:
Figure DEST_PATH_IMAGE026
in the formula:
Figure DEST_PATH_IMAGE028
the attention degree of the pixel point is represented,
Figure DEST_PATH_IMAGE030
and expressing the richness of the pixel points.
Further, in the method for determining an auxiliary location for rf ablation therapy, the richness of the pixel points is expressed as:
Figure DEST_PATH_IMAGE032
in the formula:
Figure DEST_PATH_IMAGE034
the first window of the central pixel point
Figure 445852DEST_PATH_IMAGE034
A central pixel point of
Figure 637799DEST_PATH_IMAGE006
The position of the pixel point is determined,
Figure DEST_PATH_IMAGE036
the window in which the central pixel point is positioned is expressed
Figure 514488DEST_PATH_IMAGE034
The redefined CT value of each pixel point,
Figure DEST_PATH_IMAGE038
the window in which the central pixel point is positioned is expressed
Figure DEST_PATH_IMAGE040
The redefined CT value of each pixel point is the redefined CT value of the central pixel point,
Figure DEST_PATH_IMAGE042
and representing the redefined CT mean value of all pixel points on the abdominal CT image.
The beneficial effects of the invention are: the invention provides an auxiliary positioning method for determining radio frequency ablation treatment, which is characterized in that the abundance of each pixel point is obtained through the CT value of the pixel point, the attention of each pixel point is obtained by utilizing the probability of a tumor in each region in a database, and then the CT reconstruction value of each pixel point is determined, so that a new abdominal CT image is obtained, and treatment assistance is provided for the subsequent determination of the radio frequency ablation treatment method.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart diagram of an embodiment of an assisting localization method for determining a radio frequency ablation treatment according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
An embodiment of an assisting positioning method for determining a radio frequency ablation therapy of the present invention, as shown in fig. 1, includes:
101. an abdominal CT image is acquired.
Multi-sequence abdominal CT images containing the liver region are acquired, the multi-sequence being that the probe performs a cross-sectional scan one after the other around a part. The multi-sequence abdominal CT images have various text information and other noise interferences, and therefore, the interferences of such noises need to be removed before the CT images are preprocessed. The embodiment uses a DNN semantic segmentation network method to extract a human tissue area image in an image, namely an abdomen area image, and removes text background noise.
The content of the used DNN semantic segmentation network is:
the input data set of the network is an abdomen CT image set which is screened by a professional diagnostician and contains the liver.
Each CT image in the image set is manually marked, and the CT images are divided into two types: marking the target class of the human tissue area as 1; the text region background class is labeled 0.
In the embodiment, the DNN semantic is used to divide the network for classification, so the cross entropy function adopted by the network is a loss function.
Thus, a multi-sequence abdominal CT image is obtained by the semantic segmentation.
102. And obtaining the abundance of each pixel point on the abdominal CT image through the CT values of each pixel point and the adjacent pixel points on the abdominal CT image.
Due to the influence of CT equipment, environmental noise, tumor gray scale characteristics and the like, the boundary of the tumor in the CT image is fuzzy, and the texture of the tumor area is unclear. Therefore, before the step of extracting the liver tumor image, the liver tumor image needs to be preprocessed, the contrast between the tumor region and the liver region is enhanced, and the effect of threshold segmentation is improved, so that the extraction of the liver tumor region is facilitated. The abdominal CT image preprocessing method comprises the following steps:
the CT values in the abdominal CT image are distributed in the range of-1000 to 1000. In order to improve the calculation efficiency and reduce the calculation amount, the CT range is defined to be within the range of 0-255, and the expression of the redefined CT value is as follows:
Figure DEST_PATH_IMAGE002A
in the formula:
Figure 270040DEST_PATH_IMAGE004
to represent
Figure 333811DEST_PATH_IMAGE006
The redefined CT value of the pixel point is in the range of 0 to 255,
Figure 63870DEST_PATH_IMAGE008
to represent
Figure 263907DEST_PATH_IMAGE006
The CT value of the pixel point is located,
Figure 991692DEST_PATH_IMAGE010
represents the maximum CT value in the CT image,
Figure 277180DEST_PATH_IMAGE012
representing the minimum CT value in the CT image.
And analyzing the CT image, wherein the CT value of the area where the tumor is located is different from other tissues of the human body. In the tumor region, the image is expressed in a shadow shape, and the difference between a target pixel point and other pixel points in the neighborhood exists among the pixel points; for the pixels located at the edge of the tumor region, the target pixel and the rest pixels in the neighborhood are different, and the target pixels are not the same type of CT value pixels. And the textural features of the tumor region are also expressed as the difference of the CT values of the pixel points in the tumor range, namely the CT values of the pixel points in the tumor region are also different.
The embodiment establishes
Figure DEST_PATH_IMAGE044
And counting the difference of the CT values among the pixel points of the CT image through the neighborhood window with the size. Performing sliding window operation on the CT image, counting the CT values of neighborhood pixels of the target pixel point, and calculating the richness of the target pixel point according to the CT values of the pixels in the window
Figure 76508DEST_PATH_IMAGE030
. In the neighborhood of the target pixel point, the larger the difference of CT values among the pixel points is, the larger the richness is, and the better the image effect is; the smaller the difference of CT values is, the less the richness is, and the less obvious the image effect is. Richness degree
Figure 131052DEST_PATH_IMAGE030
The expression of (a) is:
Figure DEST_PATH_IMAGE046
in the formula:
Figure 951109DEST_PATH_IMAGE034
the window in which the central pixel point is positioned is expressed
Figure 927156DEST_PATH_IMAGE034
A central pixel point of
Figure 530175DEST_PATH_IMAGE006
The position of the pixel point is determined,
Figure DEST_PATH_IMAGE048
the window in which the central pixel point is positioned is expressed
Figure 235963DEST_PATH_IMAGE034
The redefined CT value of each pixel point,
Figure 305550DEST_PATH_IMAGE038
the window in which the central pixel point is positioned is expressed
Figure 565630DEST_PATH_IMAGE040
The redefined CT value of each pixel point is the redefined CT value of the central pixel point,
Figure DEST_PATH_IMAGE050
and representing the redefined CT mean value of all pixel points on the abdominal CT image.
Performing sliding window operation on all pixel points in the CT image, and obtaining the richness of each pixel point in the CT image according to the method
Figure 706762DEST_PATH_IMAGE030
。
According to the steps, the richness of each pixel point in the CT image is obtained
Figure 735897DEST_PATH_IMAGE030
The richness is calculated according to the redefined CT value of each pixel point in the CT image.
103. And partitioning the abdominal CT image, and taking the historical tumor probability of each region on the abdominal CT image as the attention of each pixel point of the region.
According to the embodiment, on the basis of partitioning the liver, the condition that tumors occur in different areas of the liver is counted according to a big data counting technology.
By analyzing a large number of multi-sequence abdominal liver CT images, due to the difference of human postures and the morphological difference between individuals during CT scanning, the acquired CT image sets are not in a uniform orientation, which may hinder the subsequent analysis. Therefore, the attention degree of each pixel point is calculated
Figure DEST_PATH_IMAGE052
It is previously necessary to subject the images in the image set to a rotational translation operation.
In this embodiment, a coordinate system is established for each image with the vertebra as a center of the coordinate system, and the following rotational and translational alignment is performed, which specifically includes the steps of: 1) a CT image which is artificially corrected is taken as a standard, the center of a vertebral body (a pixel point row with the most central abscissa is selected by scanning pixel points of the image, a CT value sequence of the pixel point row is obtained, an area with a larger CT value is obtained, and the most central point of the area is found to be the center) is taken as a coordinate origin, and a coordinate system is established. 2) And establishing a coordinate system in each CT image, comparing the abscissa axis or the ordinate axis in the image with the abscissa axis or the ordinate axis of the standard image, and calculating the offset angle. 3) And carrying out translation rotation on the coordinate axis of the image according to the obtained offset angle to obtain a CT image set of a unified coordinate system.
After the coordinate system is established, the coordinates of each pixel point can be obtained
Figure DEST_PATH_IMAGE054
. From a priori knowledge, it can be known that: the liver is located in the upper left and upper right positions of the vertebra. Therefore, straight lines are constructed at angles of 30 °, 60 °, 120 ° and 150 ° to the positive direction of the abscissa axis, respectively, with the origin of the coordinate system as an end point. The image liver area is divided into 6 sections and each section is numbered separately.
After the partition, the area of the pixel point can be judged according to the coordinate of the pixel point, and the expression is as follows:
Figure DEST_PATH_IMAGE056
through the expression, the area where the pixel point is located can be judged. For example, if
Figure 225654DEST_PATH_IMAGE054
Coordinates of the pixel point satisfy
Figure DEST_PATH_IMAGE058
Judging the pixel point as the first
Figure DEST_PATH_IMAGE060
Pixel points of the region.
The embodiment adopts a big data statistical method and is realized by a professional doctorAnd judging the area of the liver tumor. The method comprises the following specific steps: setting each subarea accumulator, counting the frequency of the tumors in each area in all individuals in the database by the subarea accumulator, and using the frequency of the tumors in each area
Figure DEST_PATH_IMAGE062
Is shown (therein)
Figure DEST_PATH_IMAGE064
Representing I, II, … and VI), the sequence number of the CT image sequence set is
Figure DEST_PATH_IMAGE066
Is represented by
Figure 363243DEST_PATH_IMAGE066
And (3) classifying the tumor regions of the CT images in each CT image sequence set by each individual through interpretation of a professional doctor, counting the number of the regions of each individual with tumors in the corresponding CT image sequence to obtain the frequency of the tumors in each region of all the individuals, and calculating the frequency of the tumors in each region to be used as the probability of the tumors in each region. Calculating the probability of the tumor in each region
Figure DEST_PATH_IMAGE068
. Wherein
Figure 573644DEST_PATH_IMAGE068
The calculation expression of (a) is:
Figure DEST_PATH_IMAGE070
in the formula:
Figure 254024DEST_PATH_IMAGE068
indicates that the tumor is in the first place
Figure 993310DEST_PATH_IMAGE064
The probability of an individual region or regions is,
Figure 962403DEST_PATH_IMAGE062
indicates that the tumor is in the first place
Figure 914179DEST_PATH_IMAGE064
Number of image sequences of each region.
After big data statistics, the probability of the tumor in each region is obtained. If the probability is higher, the probability that the tumor appears in the region is higher, so that the attention degree of the pixel points in the region is higher. Thus, passing probability
Figure 917907DEST_PATH_IMAGE068
And obtaining the attention of each pixel point.
Obtaining the attention of each pixel point according to the area of the pixel point, wherein the attention of each pixel point is the probability counted by big data
Figure 562515DEST_PATH_IMAGE064
The attention of the pixel points of each region is
Figure 222166DEST_PATH_IMAGE068
I.e. the tumor is on the first
Figure 977633DEST_PATH_IMAGE064
The probability of the region is taken as
Figure 570288DEST_PATH_IMAGE064
Attention of each pixel point in each region. For the pixel points which do not belong to the I, II, … and VI areas, the attention degree is directly set to be 0.001.
In this embodiment, the image is preprocessed in a linear variation manner, and according to the richness of each pixel point in the obtained CT image
Figure 385797DEST_PATH_IMAGE030
And degree of attention
Figure 329482DEST_PATH_IMAGE052
And calculating the enhancement degree of each pixel point. Wherein the smaller the richness, the greater the attention, the greater the degree of enhancement; the greater the richness, the less attention, and the less enhancement. The expression for the linear variation is:
Figure DEST_PATH_IMAGE014A
in the formula:
Figure DEST_PATH_IMAGE072
a first enhancement coefficient representing a linear transformation,
Figure 278853DEST_PATH_IMAGE020
a second enhancement coefficient representing a linear variation,
Figure 991594DEST_PATH_IMAGE016
and the CT value of the pixel point after the linear change is represented, namely the CT reconstruction value of the pixel point.
104. And obtaining a first enhancement coefficient of each pixel point according to the abundance and the attention of each pixel point on the abdominal CT image.
The richness of each pixel point has been calculated
Figure 712425DEST_PATH_IMAGE030
And degree of attention
Figure 346669DEST_PATH_IMAGE052
By richness of each pixel
Figure 443938DEST_PATH_IMAGE030
And degree of attention
Figure 276765DEST_PATH_IMAGE052
Obtaining a first enhancement coefficient of each pixel point
Figure 965235DEST_PATH_IMAGE018
The expression is:
Figure DEST_PATH_IMAGE026A
105. and obtaining the adjusted CT value of all the pixel points through the first enhancement coefficient of each pixel point on the abdominal CT image and the CT values of all the pixel points on the abdominal CT image.
Due to the enhanced coefficient
Figure 957548DEST_PATH_IMAGE018
After the CT image is stretched, the histogram of the obtained CT image is not necessarily distributed in [0,255%]Within the range. Thus by another enhancement factor
Figure 858508DEST_PATH_IMAGE020
The images are adjusted so that the CT images are distributed as much as possible over [0,255 ]]Within. Thus, the first enhancement factor is passed through each pixel
Figure 280262DEST_PATH_IMAGE018
Stretching each pixel point in the CT image to obtain the range of CT values [ a, b ] of all pixel points after stretching]。
106. And obtaining a second enhancement coefficient of each pixel point through the first enhancement coefficient of each pixel point and the maximum value in the adjusted CT values of all the pixel points.
Second enhancement factor of each pixel
Figure 608475DEST_PATH_IMAGE020
The expression of (a) is:
Figure DEST_PATH_IMAGE022A
for example, if a certain pixel point
Figure DEST_PATH_IMAGE074
Richness of
Figure DEST_PATH_IMAGE076
Attention degree
Figure DEST_PATH_IMAGE078
Passing through the pixel point
Figure 138682DEST_PATH_IMAGE074
The richness and the attention degree of the pixel point are obtained
Figure 843333DEST_PATH_IMAGE074
A first enhancement coefficient of (i), i.e.
Figure DEST_PATH_IMAGE080
Stretching each pixel point in the CT image through the first enhancement coefficient to obtain the stretched CT value of all the pixel points, namely multiplying the redefined CT value of each pixel point by the first enhancement coefficient to obtain the stretched CT value range of all the pixel points, and selecting the maximum value of the stretched CT value range
Figure DEST_PATH_IMAGE082
I.e. b =
Figure 447490DEST_PATH_IMAGE082
By passing
Figure 946604DEST_PATH_IMAGE082
And a first enhancement coefficient of the pixel
Figure 573895DEST_PATH_IMAGE018
Obtaining pixel points
Figure 82237DEST_PATH_IMAGE074
Second enhancement coefficient of
Figure 478583DEST_PATH_IMAGE020
。
107. And reconstructing the CT value of each pixel point through the CT value, the first enhancement coefficient and the second enhancement coefficient of each pixel point on the abdominal CT image to obtain the CT reconstructed value of each pixel point, and obtaining a new abdominal CT image through the CT reconstructed values of all the pixel points.
The expression of linear transformation of each pixel point is obtained through the steps
Figure DEST_PATH_IMAGE084
And reconstructing the CT value of each pixel point of the CT image by a linear transformation expression to obtain the CT reconstructed value of each pixel point, thereby obtaining a preprocessed image, namely a new abdomen CT image.
So far, the CT value of each pixel point after enhancement is obtained through the linear transformation
Figure 679757DEST_PATH_IMAGE016
Thereby obtaining an enhanced image.
108. And performing threshold segmentation on the new abdominal CT image to obtain a tumor region.
Performing threshold segmentation according to the obtained preprocessed image, extracting a liver tumor mask: and (3) segmenting according to the selected threshold by adopting an OTSU threshold selection method, setting the value of the pixel point which is greater than the threshold as 1, and setting the value of the pixel point which is less than the threshold as 0, thereby obtaining a mask of the tumor region.
The obtained mask of the tumor region and the CT image are covered to obtain the CT image of the tumor, so that a doctor can conveniently interpret the CT image, the diagnosis efficiency is improved, the position and the size of the tumor are further obtained, and reliable early-stage data support and treatment assistance are provided for determining a radio frequency ablation treatment method and a treatment plan.
The invention provides an auxiliary positioning method for determining radio frequency ablation treatment, which is characterized in that the abundance of each pixel point is obtained through the CT value of the pixel point, the attention of each pixel point is obtained by utilizing the probability of a tumor in each region in a database, and then the CT reconstruction value of each pixel point is determined, so that a new abdominal CT image is obtained, and treatment assistance is provided for the subsequent determination of the radio frequency ablation treatment method.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (3)

1. An assisted localization method for determining a radio frequency ablation treatment, comprising:
acquiring an abdominal CT image;
the richness of each pixel point on the abdominal CT image is obtained through the CT values of each pixel point on the abdominal CT image and the neighborhood pixel points;
the CT value of each pixel point on the abdominal CT image is the redefined CT value of the pixel point;
the expression of the CT value redefined by the pixel point is as follows:
Figure DEST_PATH_IMAGE001
in the formula:
Figure 708391DEST_PATH_IMAGE002
to represent
Figure 973150DEST_PATH_IMAGE003
The redefined CT value of the pixel point is processed,
Figure 195184DEST_PATH_IMAGE004
to represent
Figure 810973DEST_PATH_IMAGE003
The CT value of the pixel point is located,
Figure 776655DEST_PATH_IMAGE005
representing the maximum CT value in the abdominal CT image,
Figure 895921DEST_PATH_IMAGE006
represents the minimum CT value in an abdominal CT image;
the expression of the richness of the pixel points is as follows:
Figure 23277DEST_PATH_IMAGE007
in the formula:
Figure 1729DEST_PATH_IMAGE008
the richness of the pixel points is represented,
Figure 505522DEST_PATH_IMAGE009
the window in which the central pixel point is positioned is expressed
Figure 10453DEST_PATH_IMAGE009
A central pixel point of
Figure 574289DEST_PATH_IMAGE003
The position of the pixel point is determined,
Figure 893232DEST_PATH_IMAGE010
the window in which the central pixel point is positioned is expressed
Figure 466296DEST_PATH_IMAGE009
The redefined CT value of each pixel point,
Figure 294575DEST_PATH_IMAGE011
the window in which the central pixel point is positioned is expressed
Figure 29312DEST_PATH_IMAGE012
The redefined CT value of each pixel is the redefined CT value of the central pixel,
Figure 716777DEST_PATH_IMAGE013
representing the redefined CT mean value of all pixel points on the abdominal CT image;
partitioning the abdominal CT image, and taking the historical tumor probability of each region on the abdominal CT image as the attention of each pixel point of the region;
the historical tumor probability of each region on the abdominal CT image is the historical tumor frequency of each region on the abdominal CT image;
obtaining a first enhancement coefficient of each pixel point according to the abundance and the attention of each pixel point on the abdominal CT image;
the expression of the first enhancement coefficient of the pixel point is as follows:
Figure 827952DEST_PATH_IMAGE014
in the formula:
Figure 41896DEST_PATH_IMAGE015
a first enhancement coefficient representing a pixel point,
Figure 947535DEST_PATH_IMAGE016
the attention degree of the pixel point is represented,
Figure 981350DEST_PATH_IMAGE008
representing the richness of pixel points;
obtaining the adjusted CT values of all the pixel points through the first enhancement coefficient of each pixel point on the abdominal CT image and the CT values of all the pixel points on the abdominal CT image;
obtaining a second enhancement coefficient of each pixel point through the first enhancement coefficient of each pixel point and the maximum value of the adjusted CT values of all the pixel points;
the expression of the second enhancement coefficient of the pixel point is as follows:
Figure 630637DEST_PATH_IMAGE017
in the formula:
Figure 699088DEST_PATH_IMAGE018
a second enhancement coefficient representing a pixel point,
Figure 41207DEST_PATH_IMAGE015
a first enhancement coefficient representing a pixel point,
Figure 562318DEST_PATH_IMAGE019
expressing the maximum value of the adjusted CT values of all the pixel points obtained by the first enhancement coefficients of the pixel points and the redefined CT values of all the pixel points on the abdominal CT image;
reconstructing the CT value of each pixel point through the CT value, the first enhancement coefficient and the second enhancement coefficient of each pixel point on the abdominal CT image to obtain the CT reconstruction value of each pixel point, and obtaining a new abdominal CT image through the CT reconstruction values of all the pixel points;
the expression of the CT reconstruction value of the pixel point is as follows:
Figure 749717DEST_PATH_IMAGE020
in the formula:
Figure 831197DEST_PATH_IMAGE021
represent
Figure 78639DEST_PATH_IMAGE003
The reconstructed value of the CT at the pixel point,
Figure 946101DEST_PATH_IMAGE002
represent
Figure 78136DEST_PATH_IMAGE003
The newly defined CT value of the pixel point is processed,
Figure 855599DEST_PATH_IMAGE015
a first enhancement coefficient representing a pixel point,
Figure 273942DEST_PATH_IMAGE018
a second enhancement coefficient representing a pixel point;
and performing threshold segmentation on the new abdominal CT image to obtain a tumor region.
2. An auxiliary positioning method for determining radio frequency ablation treatment according to claim 1, wherein the abdominal CT image is any one of abdominal CT images in an abdominal CT image sequence of the same person, and other abdominal CT images in the abdominal CT image sequence are processed in the same way according to the processing method of the abdominal CT image.
3. An aided location method for determining radio frequency ablation treatment according to claim 1, wherein the method of partitioning the abdominal CT image is:
and establishing a coordinate system on the abdominal CT image, and dividing each pixel point on the abdominal CT image into regions by using the coordinates of each pixel point on the abdominal CT image to obtain the region where each pixel point is located.
CN202210737793.XA 2022-06-28 2022-06-28 Assistant positioning method for determining radio frequency ablation therapy Active CN114820663B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210737793.XA CN114820663B (en) 2022-06-28 2022-06-28 Assistant positioning method for determining radio frequency ablation therapy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210737793.XA CN114820663B (en) 2022-06-28 2022-06-28 Assistant positioning method for determining radio frequency ablation therapy

Publications (2)

Publication Number Publication Date
CN114820663A CN114820663A (en) 2022-07-29
CN114820663B true CN114820663B (en) 2022-09-09

Family

ID=82522620

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210737793.XA Active CN114820663B (en) 2022-06-28 2022-06-28 Assistant positioning method for determining radio frequency ablation therapy

Country Status (1)

Country Link
CN (1) CN114820663B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116385315B (en) * 2023-05-31 2023-09-08 日照天一生物医疗科技有限公司 Image enhancement method and system for simulated ablation of tumor therapeutic instrument
CN116993628B (en) * 2023-09-27 2023-12-08 四川大学华西医院 A CT image enhancement system for tumor radiofrequency ablation guidance

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7522779B2 (en) * 2004-06-30 2009-04-21 Accuray, Inc. Image enhancement method and system for fiducial-less tracking of treatment targets
CN100573581C (en) * 2006-08-25 2009-12-23 西安理工大学 Semi-automatic segmentation method for lung CT image lesions
DE102007028270B4 (en) * 2007-06-15 2013-11-14 Siemens Aktiengesellschaft Method for segmenting image data to identify a liver
CN107464250B (en) * 2017-07-03 2020-12-04 深圳市第二人民医院 Automatic segmentation method of breast tumor based on 3D MRI images
CN108596887B (en) * 2018-04-17 2020-06-02 湖南科技大学 Automatic segmentation method for liver tumor region image in abdominal CT sequence image
CN113674281B (en) * 2021-10-25 2022-02-22 之江实验室 Liver CT automatic segmentation method based on deep shape learning

Also Published As

Publication number Publication date
CN114820663A (en) 2022-07-29

Similar Documents

Publication Publication Date Title
CN114820663B (en) Assistant positioning method for determining radio frequency ablation therapy
CN115345893B (en) Ovarian tissue canceration region segmentation method based on image processing
CN117974692B (en) Ophthalmic medical image processing method based on region growing
CN105488781A (en) Dividing method based on CT image liver tumor focus
CN117237342B (en) Intelligent analysis method for respiratory rehabilitation CT image
CN111340825A (en) Method and system for generating mediastinal lymph node segmentation model
CN118096794B (en) An intelligent segmentation method based on thoracic surgery CT images
CN109544528B (en) Lung nodule image identification method and device
Pisupati et al. Segmentation of 3D pulmonary trees using mathematical morphology
Kamil et al. Analysis of tissue abnormality in mammography images using gray level co-occurrence matrix method
CN118411528B (en) Stomach CT image feature recognition and segmentation system
CN114764809B (en) Self-adaptive threshold segmentation method and device for lung CT density elevation
CN118154626B (en) A method for image processing under ultrasound guidance for nerve block anesthesia
CN112541907A (en) Image identification method, device, server and medium
Mustafa et al. Mammography image segmentation: Chan-Vese active contour and localised active contour approach
TWI629046B (en) Progressive medical gray-level image subject segmentation method
Priyadarsini et al. Automatic Liver Tumor Segmentation in CT Modalities Using MAT-ACM.
CN120107243B (en) Pulmonary vascular tree reconstruction method based on multi-scale watershed segmentation
Supe et al. Image processing for medical image analysis: a review
Hossain et al. Brain tumor location identification and patient observation from MRI images
CN120298437B (en) Computer-aided plastic surgery navigation method and system
CN120163928B (en) Chest image three-dimensional reconstruction method for early lung cancer patient
Manikandan et al. Lobar fissure extraction in isotropic CT lung images—an application to cancer identification
Gao et al. Classification of pulmonary nodules by using improved convolutional neural networks
Jose et al. Liver cancer detection based on various sustainable segmentation techniques for CT images

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