CN109498046A - The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography - Google Patents
The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography Download PDFInfo
- Publication number
- CN109498046A CN109498046A CN201811377527.0A CN201811377527A CN109498046A CN 109498046 A CN109498046 A CN 109498046A CN 201811377527 A CN201811377527 A CN 201811377527A CN 109498046 A CN109498046 A CN 109498046A
- Authority
- CN
- China
- Prior art keywords
- image
- cta
- pet
- fusion
- registration
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 208000010125 myocardial infarction Diseases 0.000 title claims abstract description 30
- 238000002586 coronary angiography Methods 0.000 title claims abstract description 23
- 206010061216 Infarction Diseases 0.000 claims abstract description 24
- 230000007574 infarction Effects 0.000 claims abstract description 24
- 230000000747 cardiac effect Effects 0.000 claims abstract description 18
- 230000002107 myocardial effect Effects 0.000 claims abstract description 18
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 230000002861 ventricular Effects 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 239000000700 radioactive tracer Substances 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000011158 quantitative evaluation Methods 0.000 claims abstract 2
- 238000009877 rendering Methods 0.000 claims abstract 2
- 210000004165 myocardium Anatomy 0.000 claims description 30
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 210000004351 coronary vessel Anatomy 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 2
- 230000005489 elastic deformation Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000013145 classification model Methods 0.000 claims 1
- 238000002372 labelling Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 2
- 210000005240 left ventricle Anatomy 0.000 description 12
- 238000010586 diagram Methods 0.000 description 6
- 230000001225 therapeutic effect Effects 0.000 description 6
- 238000005481 NMR spectroscopy Methods 0.000 description 5
- 238000004445 quantitative analysis Methods 0.000 description 5
- 210000004413 cardiac myocyte Anatomy 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000302 ischemic effect Effects 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 206010061818 Disease progression Diseases 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000005750 disease progression Effects 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 244000309715 mini pig Species 0.000 description 2
- 238000004393 prognosis Methods 0.000 description 2
- 238000007634 remodeling Methods 0.000 description 2
- 231100000241 scar Toxicity 0.000 description 2
- 208000028399 Critical Illness Diseases 0.000 description 1
- 208000012661 Dyskinesia Diseases 0.000 description 1
- 208000009525 Myocarditis Diseases 0.000 description 1
- 206010042434 Sudden death Diseases 0.000 description 1
- 241000282898 Sus scrofa Species 0.000 description 1
- 208000033774 Ventricular Remodeling Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000010102 embolization Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 208000028867 ischemia Diseases 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013160 medical therapy Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012764 semi-quantitative analysis Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- 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
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/037—Emission tomography
-
- 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
- A61B6/44—Constructional features of apparatus for radiation diagnosis
- A61B6/4417—Constructional features of apparatus for radiation diagnosis related to combined acquisition of different diagnostic modalities
-
- 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
- A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
- A61B6/503—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of the heart
-
- 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
- A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
-
- 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
- A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
- A61B6/5235—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image combining images from the same or different ionising radiation imaging techniques, e.g. PET and CT
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Optics & Photonics (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- High Energy & Nuclear Physics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- Theoretical Computer Science (AREA)
- Cardiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
本发明属于医学图像处理领域，公开了一种基于核素图像与CT冠脉造影融合的心肌梗死定量评估方法及评估系统；获取心脏PET/CT和CTA数据；对PET/CT图像进行三维DCT频域插值；利用多图谱分割法获取PET/CT图像与CTA图像中的心脏区域；利用阈值法获取PET图像中左心室心肌区域；在CTA图像中逐层手动分割左心室心肌区域；进行图像配准；根据配准后图像上像素点的位置与示踪剂摄取值对像素点进行分类；将梗死区域逆变换到原CTA空间中，变换后梗死区域体积与左心室心肌体积相除；将融合后图像以体绘制的方式三维显示。本发明在整个配准过程中实现了全自动化，客观性好，结果更加直观，便于临床医生分析。
The invention belongs to the field of medical image processing, and discloses a quantitative evaluation method and evaluation system for myocardial infarction based on fusion of radionuclide images and CT coronary angiography; obtaining cardiac PET/CT and CTA data; performing three-dimensional DCT frequency analysis on the PET/CT images Domain interpolation; use multi-atlas segmentation method to obtain cardiac region in PET/CT image and CTA image; use threshold method to obtain left ventricular myocardial region in PET image; manually segment left ventricular myocardial region layer by layer in CTA image; perform image registration ; Classify the pixel points according to the position of the pixel points on the registered image and the uptake value of the tracer; inversely transform the infarct area into the original CTA space, and divide the volume of the infarct area after the transformation with the left ventricular myocardial volume; The image is displayed in three dimensions in volume rendering. The present invention realizes full automation in the whole registration process, has good objectivity, more intuitive results, and is convenient for clinicians to analyze.
Description
Technical field
It a kind of is merged the invention belongs to field of medical image processing more particularly to CT coronary angiography based on nucleic image
Myocardial infarction quantitative evaluating method and assessment system.
Background technique
Currently, the prior art commonly used in the trade is such that myocardial infarction is one kind since coronary ischemia anoxic is drawn
The disease for playing myocardial necrosis, eventually leading to sudden death (acute) and Myocardial Remodeling (chronic) seriously threatens human life, influences life
Quality.And infarct size be Myocardial Remodeling and the heart function imbalance deciding factor, be heart infarction survival be effectively predicted because
Son.After heart infarction occurs, the accurate positionin of ischemic range is quantified, and is facilitated clinic and is effectively opened infarction related coronary artery, utmostly
Save dying cardiac muscle.Moreover myocardial infarct size is different, and therapeutic scheme and prognosis target are different, and accurate evaluation myocardial infarct size helps
In the correct formulation of individuation rescue protocol.It is reported that still thering is about 30% patient left ventricular remodeling, infarct 6 occur after heart infarction treatment
About 30% patient occurs measuring myocardial infarction area after Left Ventricular Ejection Fraction is brought down below 40%, then logical treatment after a month, to face
Bed evaluation curative effect, understanding disease progression provide quantizating index.Thus seek the myocardial infarction area that objectivity is good, repeatability is high
Appraisal procedure is significant.
Myocardial infarction area non-intrusion type appraisal procedure includes electrocardiogram, echocardiogram, spiral CT, nuclear magnetic resonance at present
Imaging and radioisotope scanning etc..Wherein electrocardiogram is low to the sensibility and specificity of myocardial infarction, and super cardiogram is transported with eye recognition
It moves abnormal ventricle wall and is used as the foundation for defining infarcted myocardium, but the specific findings of segmental dyskinesia simultaneously non-salary motivation
(such as transient ischemic, Stunning myocardium, myocarditis can also occur), it is horizontal by picture quality and operator's experience, operating technology
Equal many factors influence, and can only make coarse localization and semi-quantitative analysis to infarct size.Magnetic resonance imaging is current reflection scar
The best method of trace transmural degree and area.But current pacemaker and implantable cardioverter defibrillator are the taboos of nuclear magnetic resonance
Card.Furthermore nuclear magnetic resonance check room is without critical illness monitoring, and emergency measures is limited, therefore nuclear magnetic resonance is imaged and assesses in load
Application in critical patient myocardial activity is limited.PET not only has quantization myocardial activity, scar, left ventricular ejection fraction and ventricle
Advantages such as volume, and have outstanding time, spatial resolution and correction for attenuation, can delicately quantify tracer uptake rate and
Heart muscle perfusion.PET tracer half-life period is shorter (only several minutes), and imaging is fast, raying is few, more universal than Magnetic resonance imaging
Rate is high, and detection process is relatively easy, quick.CT spatial resolution is apparently higher than nuclear magnetic resonance, up to 0.5mm, and can carry out three
Dimension is rebuild.CT blood vessel imaging, i.e. CTA can position more diseases of coronary artery.CTA and nucleic image co-registration can get more comprehensively
Information, preferably assessment myocardial infarct size.
No matter which kind of cardiac image is based on, and non-intrusion type myocardial infarction quantitative analysis at present is needed via specialized medical image
Doctor analyzes, and analysis result relies on the experience of image doctor, and repeatability is poor, and interpretation is low.Moreover.It is existing
Myocardium 17 segmentation methods divide myocardial region by even length and homogeneous angular, do not consider patient's myocardial infarction rear left heart
Room reconstructs phenomenon, and myocardial segments inaccuracy causes infarcted region positioning inaccurate, final to influence therapeutic scheme and therapeutic effect.Cause
There is an urgent need to accurate and reliable, full automatic infarct size quantitative analysis methods for this, mention for clinical evaluation curative effect, understanding disease progression
For quantizating index.
In conclusion problem of the existing technology is:
(1) existing non-intrusion type myocardial infarction quantitative analysis uses the image of single mode, retrievable Limited information.
The judgement and analysis of lesion analyze the experience that result relies on image doctor via specialized medical image doctor, high to manual request,
Repeatability is poor.Ischemic or infarct determine that result is provided with two-dimentional target center diagram form, and interpretation is poor, are unfavorable for clinician's solution
It reads, hinders formulation and the prognosis evaluation of therapeutic scheme.
(2) two-dimentional target center map generalization needs to recommend myocardium of left ventricle according to American Heart Association in existing analysis method
17 segmentation methods divided with even length and homogeneous angular.This division methods do not consider patient's myocardial infarction rear left heart
Room reconstructs phenomenon, and myocardial segments inaccuracy causes infarcted region positioning inaccurate, final to influence therapeutic scheme and therapeutic effect.
Solve the difficulty and meaning of above-mentioned technical problem:
The different angle different levels that existing cardiac imaging technology is organically combined, while being provided using multiple modalities image
Information, qualitative positioning quantitatively to lesion carry out automated analysis, it is possible to provide accurate, comprehensive lesion development process, for system
Determine medical therapy scheme and technological means is provided.However the cardiac image sweep time of different modalities is different, scanning device is different, disease
The factors such as the variation of the physiological parameters such as heart rate, the blood flow of people can all cause the difference between different modalities image, in addition heart
Non-rigid shape deformations so that the cardiac image registration problems under different modalities become extremely complex.
Summary of the invention
In view of the problems of the existing technology, it is merged with CT coronary angiography the present invention provides a kind of based on nucleic image
Myocardial infarction quantitative evaluating method,
The invention is realized in this way a kind of myocardial infarction merged based on nucleic image with CT coronary angiography is quantitatively evaluated
Method, which is characterized in that should include as follows based on the myocardial infarction quantitative evaluating method that nucleic image is merged with CT coronary angiography
Step:
Step 1: obtaining heart PET/CT and CTA data；
Keep it consistent with CTA image pixel size Step 2: carrying out three-dimensional DCT frequency domain interpolation to PET/CT image；
Step 3: obtaining the heart area in PET/CT image and CTA image using multichannel chromatogram split plot design, heart area is obtained
Domain mark figure；
Step 4: obtaining myocardium of left ventricle region in PET image using threshold method, PET myocardial region mark figure is obtained；
Step 5: the layer-by-layer manual segmentation myocardium of left ventricle region in CTA image, obtains CTA myocardial region mark figure；
Step 6: the whole heart area mark from PET/CT and CTA image is schemed and myocardium of left ventricle region respectively
Mark figure fusion, and in this, as the input of image registration, image registration is carried out, CTA cardiac myocytes are merged into mark image and are matched
Standard merges on mark figure to PET cardiac myocytes；
Step 7: position and tracer uptake value pair using random forest grader according to pixel in images after registration
Pixel is classified, and realizes the differentiation of infarcted region；
Step 8: infarcted region inversion is changed in the former space CTA, infarcted region volume and myocardium of left ventricle body after transformation
Product is divided by, and heart infarction ratio quantitative result is obtained；
Step 9: by fused image in a manner of volume drawing Three-dimensional Display so that whole heart, myocardium of left ventricle, stalk
Flesh of giving up the idea is shown on same width three-dimensional figure with coronary artery.
Further, which is characterized in that the step 3 specifically:
(1) it makes atlas: successively marking heart area manually on two-dimensional surface, belong to cardiac component is labeled as 1,
Be not belonging to cardiac component is labeled as 0, obtains heart mark figure, and mark figure and original gradation figure are one group of map, atlas by
Multiple map compositions；
(2) grayscale image in atlas is registrated on image to be split by image registration；
(3) Deformation Field that registration generates is respectively acting on the corresponding mark figure of grayscale image；
(4) the mark figure after multiple deformation determines cut zone using the combined strategy of most ballots.
Further, which is characterized in that step (2) image registration specifically:
(a) translation is carried out to floating image using affine transformation and stretches rotation process, so that floating image and figure to be matched
Mutual information as between is maximum, realizes Rigid Registration；
(b) it for the floating image after Rigid Registration, reuses the elastic deformation based on B-spline and interpolation is carried out to image,
So that the mutual information between floating image and image to be matched is maximum, non-rigid registration is completed.
Further, which is characterized in that the step 7 specifically:
Step 1: making sample collection: infarcted region position and size are manually successively selected according to images after registration,
K 3 × 3 sized images blocks are randomly selected in infarcted region as positive sample, K 3 × 3 size figures are chosen in non-infarcted region constituency
As block is as negative sample；
Step 2: random forest grader training: each data point for participating in training is defined asWherein CkFor the three-dimensional coordinate of 9 points of image block,It is image block in CTA cardiac myocytes
Value on fusion mark image, PETkFor the tracer uptake value of image block corresponding position；Sampling, model instruction by data
Practice, after model optimization, obtains random forest disaggregated model；
Step 3: inputting unfiled image data, is classified using obtained disaggregated model and thrown using relative majority
The combined strategy of ticket determines last classification results.
In conclusion advantages of the present invention and good effect are as follows:
First, the myocardial infarction proposed by the present invention merged based on nucleic image with CT coronary angiography is quantitatively evaluated, and is passed through
Map fusion is realized with Deformation Field propagation merges across modality image co-registration, using random forest grader to fused image point
It analyses, entirety myocardium of left ventricle area ratio shared by automatically derived infarct size, it is fixed for the fusion of subsequent heart multi-modality images and lesion
Amount analysis is laid a good foundation.
Second, the present invention realizes full-automation in entire registration process, is not necessarily to human-computer interaction, avoids human factor
Interference, be registrated high-efficient, objectivity is good, repeated height, high degree of automation.
Third, since the present invention is shown heart, myocardium of left ventricle, infarcted region and coronary artery three-dimensional by volume drawing
Show, it is as a result more intuitive, it is analyzed convenient for clinician.
Detailed description of the invention
Fig. 1 is that the myocardial infarction provided in an embodiment of the present invention merged based on nucleic image with CT coronary angiography is quantitatively evaluated
Method flow schematic diagram.
Fig. 2 is heart CT coronary angiography image and nucleic image schematic diagram provided in an embodiment of the present invention.
Fig. 3 is both modalities which image cardiac provided in an embodiment of the present invention and myocardium segmentation result schematic diagram.
Fig. 4 is CT coronary angiography provided in an embodiment of the present invention and nucleic image registration results schematic diagram.
Fig. 5 is heart, myocardium of left ventricle layer, infarcted myocardium and coronary artery artery three-dimensional visualization provided in an embodiment of the present invention
Result schematic diagram.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, the myocardial infarction quantitative evaluating method of the invention merged based on nucleic image with CT coronary angiography
Specific step is as follows:
Step 1 inputs heart CT coronary angiography image and heart nucleic image, adjusts image pixel size:
Heart CT coronary angiography image and cardiac image are obtained from certain hospital, as shown in Fig. 2, wherein Fig. 2 (a) is the heart
Dirty CT coronary angiography image, Fig. 2 (b) are heart nucleic images, and the size of heart CT coronary angiography image is 512 × 512, the number of plies
423 or so, pixel resolution is 0.51 × 0.51mm2, the size of nucleic image is 168 × 168, the number of plies 111 or so, as
Plain resolution ratio is 2.03 × 2.03mm2；
Nucleic image is adjusted using frequency domain interpolation method, keeps it consistent with CT coronary angiography image pixel resolution sizes；
Step 2. obtains the heart area in PET/CT image and CTA image using multichannel chromatogram split plot design, obtains heart area
Domain mark figure；
3a step: spectrum grayscale image Ai(x) and map associated therewith label schemes Li(x) N number of altogether；
3b step: by grayscale image A in each group of mapi(x) it is registrated to segmented image P (x) respectively, registration result can generate
N group Deformation Field information T(1,...,N)；
3c step: by N group Deformation Field information T(1,...,N)Travel to the map label figure L in corresponding mapi(x) it on, propagates
Map label figure L after generating the deformation of N group afterwardsi(Ti(x))。
3d step: the map label after N group deformation is schemed into L according to most ballot criterioni(Ti(x)) image co-registration is carried out, it is raw
At final segmentation result tag image LF。
Enable Li'=Li(Ti(x)), then most ballots areWherein m, n are pixel
Coordinate.Majority ballot criterion traverses whole picture three-dimensional figure.
Step 3. cardiac muscle segmentation.Successively manually divide in CTA picture centre flesh region；PET image is obtained left using threshold method
Myocardium of ventricle region, threshold value T=50% × maximal oxygen value.Point greater than threshold value is 1, and the point less than threshold value is 0；
Step 4. image registration.The heart area mark figure of both modalities which is merged respectively with myocardial region mark figure, is melted
The area marking for belonging to cardiac muscle after conjunction is 2, and the area marking for belonging to heart but non-cardiac muscle is 1, and non-cardiac area marking is 0.Melt
CTA mark figure is registrated on nucleic mark figure by the mark figure after conjunction as registration with objects, while seeking registration inverse transformation.
Step 5. cardiac muscle classification.The each data point for participating in training is defined asWherein Ck
For the three-dimensional coordinate of 9 points of image block.The value on mark image, PET are merged in CTA cardiac myocytes for image blockkFor figure
As the tracer uptake value of block corresponding position；
Step 6. infarct ratio calculates: the registration inverse transformation sought in step 4 is used in what random forest classification obtained
In infarcted region, infarcted region is obtained in the volume in the space original CT AWhereinFor pth layer infarct size
Size, ZIFor there are the numbers of plies of infarcted region.Then myocardium of left ventricle layer volume is calculatedWhereinIt indicates
The area of myocardium of left ventricle on each slice, k are slice number, and z is the 3-D image number of plies.Infarct ratio:
Simulated effect
Heart infarction model is established with embolization in miniature pig body, by this patent to miniature pig myocardium of left ventricle layer infarct size
Carry out quantitative analysis.Small pig heart is taken out again and carries out histotomy TTC dyeing, measures infarct ratio, as quantitative analysis gold
Standard.It is as shown in the table for the two comparing result.This patent method therefor and TTC dyeing gained infarct ratio are consistent, minimum absolutely to miss
Difference is up to 0.39%.The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in the present invention
Spirit and principle within made any modifications, equivalent replacements, and improvements etc., should be included in protection scope of the present invention it
It is interior.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811377527.0A CN109498046A (en) | 2018-11-19 | 2018-11-19 | The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811377527.0A CN109498046A (en) | 2018-11-19 | 2018-11-19 | The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109498046A true CN109498046A (en) | 2019-03-22 |
Family
ID=65749037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811377527.0A Pending CN109498046A (en) | 2018-11-19 | 2018-11-19 | The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109498046A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363755A (en) * | 2019-07-16 | 2019-10-22 | 中山大学 | Method, device, equipment and medium for detecting myocardial infarction size without contrast agent |
| CN111312373A (en) * | 2020-01-19 | 2020-06-19 | 浙江树人学院（浙江树人大学） | An automatic labeling method for PET/CT image fusion |
| CN111652954A (en) * | 2020-07-01 | 2020-09-11 | 杭州脉流科技有限公司 | Left ventricle volume automatic calculation method and device based on left ventricle segmentation picture, computer equipment and storage medium |
| CN111798498A (en) * | 2020-07-16 | 2020-10-20 | 上海商汤智能科技有限公司 | Image processing method and device, electronic device and storage medium |
| CN111887858A (en) * | 2020-08-04 | 2020-11-06 | 西安电子科技大学 | A Heart Rate Estimation Method Based on Cross-modal Mapping for Pulse Cardiogram Signals |
| CN111904450A (en) * | 2020-09-07 | 2020-11-10 | 北京永新医疗设备有限公司 | Method, device and system for extracting center and region of interest of left ventricle |
| CN114420260A (en) * | 2021-12-17 | 2022-04-29 | 宁波市科技园区明天医网科技有限公司 | Ultrasonic cardiogram acoustic radiography bull's eye graph structured automatic auxiliary analysis method |
| CN115205294A (en) * | 2022-09-16 | 2022-10-18 | 杭州脉流科技有限公司 | Ischemic stroke infarction assessment device and method based on multi-model fusion |
| CN115699079A (en) * | 2020-07-07 | 2023-02-03 | 中加健康工程研究院(合肥)有限公司 | Image processing method, device, computing device and medium |
| WO2024230714A1 (en) * | 2023-05-08 | 2024-11-14 | 中山大学附属第五医院 | Myocardial focal scar detection method, risk prediction method and related apparatus |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9972069B2 (en) * | 2014-10-06 | 2018-05-15 | Technion Research & Development Foundation Limited | System and method for measurement of myocardial mechanical function |
| WO2018089755A1 (en) * | 2016-11-10 | 2018-05-17 | Memorial Sloan Kettering Cancer Center | Methods and systems for synthetic computed tomography (ct) image creation |
| CN108292434A (en) * | 2015-09-10 | 2018-07-17 | 爱克发医疗保健公司 | Method, apparatus and system for segmentation of anatomical structures in medical images |
| CN108694994A (en) * | 2018-05-11 | 2018-10-23 | 浙江大学 | Noninvasive cardiac infarction disaggregated model construction method based on stack self-encoding encoder and support vector machines |
| CN108805913A (en) * | 2018-05-14 | 2018-11-13 | 首都医科大学附属北京安贞医院 | A kind of fusion method of coronary artery CT images and cardiac ultrasonic strain imaging |
-
2018
- 2018-11-19 CN CN201811377527.0A patent/CN109498046A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9972069B2 (en) * | 2014-10-06 | 2018-05-15 | Technion Research & Development Foundation Limited | System and method for measurement of myocardial mechanical function |
| CN108292434A (en) * | 2015-09-10 | 2018-07-17 | 爱克发医疗保健公司 | Method, apparatus and system for segmentation of anatomical structures in medical images |
| WO2018089755A1 (en) * | 2016-11-10 | 2018-05-17 | Memorial Sloan Kettering Cancer Center | Methods and systems for synthetic computed tomography (ct) image creation |
| CN108694994A (en) * | 2018-05-11 | 2018-10-23 | 浙江大学 | Noninvasive cardiac infarction disaggregated model construction method based on stack self-encoding encoder and support vector machines |
| CN108805913A (en) * | 2018-05-14 | 2018-11-13 | 首都医科大学附属北京安贞医院 | A kind of fusion method of coronary artery CT images and cardiac ultrasonic strain imaging |
Non-Patent Citations (2)
| Title |
|---|
| 郭晋纲: "《SPECT-CT和PET-CT计算机分析方法的探索研究》", 《2014年中国医疗设备民族工业发展大会征文集》 * |
| 高铭杰: "《多模态小型猪心脏图像的分割与配准》", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110363755A (en) * | 2019-07-16 | 2019-10-22 | 中山大学 | Method, device, equipment and medium for detecting myocardial infarction size without contrast agent |
| CN111312373A (en) * | 2020-01-19 | 2020-06-19 | 浙江树人学院（浙江树人大学） | An automatic labeling method for PET/CT image fusion |
| CN111312373B (en) * | 2020-01-19 | 2023-08-18 | 浙江树人学院（浙江树人大学） | Automatic labeling method for PET/CT image fusion |
| CN111652954A (en) * | 2020-07-01 | 2020-09-11 | 杭州脉流科技有限公司 | Left ventricle volume automatic calculation method and device based on left ventricle segmentation picture, computer equipment and storage medium |
| CN111652954B (en) * | 2020-07-01 | 2023-09-05 | 杭州脉流科技有限公司 | Left ventricle volume automatic calculation method, device, computer equipment and storage medium based on left ventricle segmentation picture |
| CN115699079A (en) * | 2020-07-07 | 2023-02-03 | 中加健康工程研究院(合肥)有限公司 | Image processing method, device, computing device and medium |
| CN111798498A (en) * | 2020-07-16 | 2020-10-20 | 上海商汤智能科技有限公司 | Image processing method and device, electronic device and storage medium |
| CN111887858B (en) * | 2020-08-04 | 2021-05-04 | 西安电子科技大学 | A Heart Rate Estimation Method Based on Cross-modal Mapping for Pulse Cardiogram Signals |
| CN111887858A (en) * | 2020-08-04 | 2020-11-06 | 西安电子科技大学 | A Heart Rate Estimation Method Based on Cross-modal Mapping for Pulse Cardiogram Signals |
| CN111904450A (en) * | 2020-09-07 | 2020-11-10 | 北京永新医疗设备有限公司 | Method, device and system for extracting center and region of interest of left ventricle |
| CN111904450B (en) * | 2020-09-07 | 2023-11-07 | 北京永新医疗设备有限公司 | Extraction method, device and system for center of left ventricle and region of interest |
| CN114420260A (en) * | 2021-12-17 | 2022-04-29 | 宁波市科技园区明天医网科技有限公司 | Ultrasonic cardiogram acoustic radiography bull's eye graph structured automatic auxiliary analysis method |
| CN115205294A (en) * | 2022-09-16 | 2022-10-18 | 杭州脉流科技有限公司 | Ischemic stroke infarction assessment device and method based on multi-model fusion |
| WO2024230714A1 (en) * | 2023-05-08 | 2024-11-14 | 中山大学附属第五医院 | Myocardial focal scar detection method, risk prediction method and related apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109498046A (en) | The myocardial infarction quantitative evaluating method merged based on nucleic image with CT coronary angiography | |
| Sun et al. | Multiparametric MRI and radiomics in prostate cancer: a review | |
| Slomka et al. | Cardiac imaging: working towards fully-automated machine analysis & interpretation | |
| Ulas et al. | Convolutional neural networks for direct inference of pharmacokinetic parameters: application to stroke dynamic contrast-enhanced MRI | |
| Schlosser et al. | Assessment of left ventricular parameters using 16-MDCT and new software for endocardial and epicardial border delineation | |
| JP5081390B2 (en) | Method and system for monitoring tumor burden | |
| US20080021301A1 (en) | Methods and Apparatus for Volume Computer Assisted Reading Management and Review | |
| Positano et al. | A fast and effective method to assess myocardial necrosis by means of contrast magnetic resonance imaging | |
| CN111047589A (en) | An attention-enhanced brain tumor-assisted intelligent detection and recognition method | |
| Heydarheydari et al. | Auto-segmentation of head and neck tumors in positron emission tomography images using non-local means and morphological frameworks | |
| Armato III et al. | Imaging in pleural mesothelioma: a review of the 11th International Conference of the International Mesothelioma Interest Group | |
| CN119048694A (en) | Multi-mode-based three-dimensional image post-processing method and system | |
| Niu et al. | Texture features and pharmacokinetic parameters in differentiating benign and malignant breast lesions by dynamic contrast enhanced magnetic resonance imaging | |
| Preim et al. | Survey of the visual exploration and analysis of perfusion data | |
| Zhou et al. | Deep CTS: a deep neural network for identification MRI of carpal tunnel syndrome | |
| US20250057472A1 (en) | System and Method for Monitoring Multiple Lesions | |
| Xu et al. | Deep learning-based automated detection of arterial vessel wall and plaque on magnetic resonance vessel wall images | |
| Alam et al. | Evaluation of medical image registration techniques based on nature and domain of the transformation | |
| Jayender et al. | Statistical learning algorithm for in situ and invasive breast carcinoma segmentation | |
| Memon et al. | Brain lesion segmentation using deep learning and its role in computer-aided differential diagnosis of multiple sclerosis and neuromyelitis optica | |
| CN118279327A (en) | Image segmentation method for medical image data | |
| Kim et al. | Deep learning for classification of late gadolinium enhancement lesions based on the 16-segment left ventricular model | |
| Li et al. | Clinical study of diffusion-weighted imaging in the diagnosis of liver focal lesion | |
| Sun et al. | [Retracted] Application of Artificial Intelligence Nuclear Medicine Automated Images Based on Deep Learning in Tumor Diagnosis | |
| Peng et al. | A windowing-based multi-view u-net for tumor segmentation in cone-beam breast CT |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190322 |