CN112927212A - OCT cardiovascular plaque automatic identification and analysis method based on deep learning - Google Patents
OCT cardiovascular plaque automatic identification and analysis method based on deep learning Download PDFInfo
- Publication number
- CN112927212A CN112927212A CN202110263890.5A CN202110263890A CN112927212A CN 112927212 A CN112927212 A CN 112927212A CN 202110263890 A CN202110263890 A CN 202110263890A CN 112927212 A CN112927212 A CN 112927212A
- Authority
- CN
- China
- Prior art keywords
- image
- section
- result
- plaque
- oct
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 238000013135 deep learning Methods 0.000 title claims abstract description 22
- 230000002526 effect on cardiovascular system Effects 0.000 title claims abstract description 19
- 230000011218 segmentation Effects 0.000 claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 13
- 238000013461 design Methods 0.000 abstract description 2
- 238000012014 optical coherence tomography Methods 0.000 description 32
- 238000013527 convolutional neural network Methods 0.000 description 5
- 208000024172 Cardiovascular disease Diseases 0.000 description 2
- 208000029078 coronary artery disease Diseases 0.000 description 2
- 210000004351 coronary vessel Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 150000002632 lipids Chemical class 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 208000037260 Atherosclerotic Plaque Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides an OCT cardiovascular plaque automatic identification and analysis method based on deep learning, which comprises the following steps: and (3) deep section treatment: carrying out segmentation processing on the depth section of the OCT image to obtain a segmentation result A1; cross section treatment: performing segmentation processing on the cross section of the OCT image to obtain a segmentation result A2; comprehensive treatment of cross sections: integrating the depth section processing result A1 and the cross section processing result A2 and carrying out segmentation processing to obtain a segmentation result A; and (4) analyzing results: and calculating a plaque attenuation index IPA according to the segmentation result A to obtain the plaque category. The method is reasonable in design, integrates different image classification characteristics and OCT clinical characteristics, performs three-dimensional reconstruction and segmentation on the 3D OCT image, obtains the quantitative index IPA, finally classifies the plaque based on the IPA, and can effectively solve the problem of weak plaque identification capability in the prior art.
Description
Technical Field
The invention relates to the field of image analysis, in particular to an OCT cardiovascular plaque automatic identification and analysis method based on deep learning.
Background
Cardiovascular diseases have developed into the first killer of disease death of residents in China, and cause immeasurable harm to the health of the Chinese and the development of national economy. Unstable lipid plaques are a major cause of the first fatal cardiovascular disease, coronary heart disease.
The intravascular optical coherence tomography (IV-OCT) technology is rapidly developed as an effective means for diagnosing coronary heart disease due to its ultra-high imaging resolution (10-20 μm). The IV-OCT image can clearly display different types of atherosclerotic plaques and is known as a living tissue microscope.
In terms of plaque segmentation, N.Gessert et al pre-trains all models on ImageNet, then uses ResNet50-V2 and DenseNet121 models and polar and Cartesian coordinate system training images to realize segmentation and classification of several plaques of coronary OCT images, and tries several different transfer learning modes, and finally compares the series results of several methods. Zhang et al propose a mixture model of a faster-CNN network model, a fourth order partial differential equation and a global local active contour model, firstly use the faster-CNN network model to detect the area of calcified plaque, locate the position of the calcified plaque, set a bounding box for a characteristic region, set the bounding box as the initial contour of the active contour model, and then minimize the combined energy function of the fourth order partial differential equation and the global local active contour model part through a gradient descent and finite difference scheme, thereby segmenting the calcified plaque in the coronary OCT image. He et al uses OTSU automatic threshold algorithm to segment the tissue region in the image, then inputs it as an input source into a CNN-based classifier, divides the focal tissue in the coronary OCT image into 5 different tissue classes, and completes the plaque characterization of the coronary OCT image. The segmentation problem of coronary artery plaques by using deep learning needs a large data set, or the data volume is increased through a large amount of data expansion, and the computation amount and the requirement on hardware brought by a deep convolutional neural network are difficult points of applying the deep learning to the segmentation of the coronary artery OCT image plaques.
These methods are mainly classified into methods focusing on deep learning, such as AlexNet, GoogleNet, VGG-Net, fasterR-CNN, DenseNet, ResNet, etc., in which patches are segmented at each depth section, and then deep features are extracted from the segmented regions and then classified. These methods have achieved better results on image classification, such as ImageNet. They mainly classify and identify different kinds of animals, plants, tools and other common life objects. However, for OCT 3D images, where the plaque is usually small and 3D images are generated by optical instrument interference, the ability to identify different plaques is usually weak and has certain drawbacks.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide an OCT cardiovascular plaque automatic identification and analysis method based on deep learning, which performs three-dimensional reconstruction and segmentation on a 3D OCT image to obtain a quantitative index IPA, and finally classifies plaques based on IPA.
In order to achieve the purpose, the invention adopts the following technical scheme:
an OCT cardiovascular plaque automatic identification and analysis method based on deep learning comprises the following steps:
s100, depth section processing: carrying out segmentation processing on the depth section of the OCT image to obtain a segmentation result A1;
s200, cross section processing: performing segmentation processing on the cross section of the OCT image to obtain a segmentation result A2;
s300, comprehensive cross section treatment: integrating the depth section processing result A1 and the cross section processing result A2 and carrying out segmentation processing to obtain a segmentation result A;
s400, result analysis: and calculating a plaque attenuation index IPA according to the segmentation result A to obtain the plaque category.
In a preferred embodiment of the present invention, in step S100, the depth section processing specifically includes:
s101, inputting a 2D Image { Image (i, j, k) of a depth section; k is 1, 2, 3, …, M } { Image (i, j, 1), Image (i, j, 2), Image (i, j, 3), …, Image (i, j, M) }, wherein Image (i, j, k) represents the coordinates of each point in the 2D Image;
s102 outputs the divided 2D images, and obtains 2D images of all depth sections with the size of the 2D images being equal to that of the input image, the useful region pixels being 1, and the useless region pixels being 0, and then combines them to obtain a 3D image a 1.
In a preferred embodiment of the present invention, the specific processing method of step S102 is: the 2D images of the depth sections are subjected to convolution operation, and combined to obtain a 3D image a 1.
In a preferred embodiment of the present invention, in step S200, the cross-section processing specifically includes:
s201, inputting a 2D Image { Image (i, j, k) of a cross section; 1, 2, 3, …, N } { Image (1, j, k), Image (2, j, k), Image (3, j, k), …, Image (N, j, k) }, wherein Image (i, j, k) represents the coordinates of each point in the 2D Image;
s202, the divided 2D images are output, and the size of the 2D images is the same as that of the input image, the pixels of the useful region are 1, and the pixels of the useless region are 0, and 2D images of all cross sections are obtained and combined to obtain a 3D image a 2.
In a preferred embodiment of the present invention, the convolution operation is performed on each 2D image of the cross-section, and the 3D image a2 is obtained in combination.
In a preferred embodiment of the present invention, in step S300, the cross-section integration processing specifically includes:
s301, inputting all the depth section segmentation results A1 and the cross section segmentation results A2;
s302, the integrated depth interface segmentation result a1 and the cross-section segmentation result a2 calculate the segmentation result a, where a is a1 and a 2.
In a preferred embodiment of the present invention, in step S400, the specific steps of result analysis include:
s401, calculating and inputting a segmentation result A according to a calculation formula of the segmentation result A;
s402, outputting the category of the plaque;
s403, calculating the value of the plaque attenuation coefficient IPA:
where x is the plaque attenuation coefficient threshold, μtAs attenuation coefficient, N (. mu.)tX) means the number of pixels with attenuation coefficient greater than x, NtotalThe effective area of the segmentation result a is shown.
Through the technical scheme, the invention has the following beneficial effects:
the method is reasonable in design, integrates different image classification characteristics and OCT clinical characteristics, performs three-dimensional reconstruction and segmentation on the 3D OCT image, obtains the quantitative index IPA, finally classifies the plaque based on the IPA, and can effectively solve the problem of weak plaque identification capability in the prior art.
Drawings
FIG. 1 is a flow chart of an OCT cardiovascular plaque automatic identification and analysis method based on deep learning according to the present invention;
FIG. 2 is a diagram of a calculation process of a segmentation result A1 of an OCT cardiovascular plaque automatic identification and analysis method based on deep learning according to the present invention;
FIG. 3 is a diagram of a calculation process of a segmentation result A2 of an OCT cardiovascular plaque automatic identification and analysis method based on deep learning according to the present invention;
FIG. 4 is a depth sectional view of an OCT image of an OCT cardiovascular plaque automatic identification and analysis method based on deep learning of the present invention;
fig. 5 is a cross-sectional view of an OCT image of an OCT cardiovascular plaque automatic identification and analysis method based on deep learning according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
Fig. 1 shows an embodiment of an OCT cardiovascular plaque automatic identification and analysis method based on deep learning according to the present invention. In this embodiment, the method for automatically identifying and analyzing a plaque includes the following steps:
referring to fig. 1 and 2, step S100 is described in detail:
s100, depth section processing: the depth section of the OCT image is subjected to segmentation processing, and a segmentation result a1 is obtained. The processing method of the segmentation result A1 comprises the following steps:
i. inputting a 2D Image { Image (i, j, k) of a depth section; k is 1, 2, 3, …, M } { Image (i, j, 1), Image (i, j, 2), Image (i, j, 3), …, Image (i, j, M) }, wherein Image (i, j, k) represents the coordinates of each point in the 2D Image;
and ii, outputting the divided 2D images, wherein the size of the divided 2D images is consistent with that of the input image, the pixel of the useful area is 1, the pixel of the useless area is 0, obtaining 2D images of all the depth sections, and combining to obtain a 3D image A1. In which convolution operation is performed on each 2D image of the depth section, and a 3D image a1 is obtained by combination.
The specific treatment method is as follows:
Block1：
for the 2D Image (i, j, k) of the kth depth section, k is 1, 2, 3, …, M, result in result of convolution operation by filter _ k1 of 3 × 3, result _ k1, result _ k1 result in result of convolution operation by filter _ k2 of 3 × 5, result _ k2 result in result _ k3 by convolution operation by filter _ k3 of 5 × 3, result _ k3 result in result _ k4 by convolution operation by filter _ k4 of 5 × 5, a1 result _ k1+ a2 result _ k2+ a3 result _ 3+ a4 result _ k 4.
Block _ k _2, Block _ k _3, Block _ k _ 4: the structure is the same as Block _ k _ 1.
Result _ k _ B1 goes through block2 ═ Result _ k _ B2,
result _ k _ B2 goes through block3 ═ Result _ k _ B3,
result _ k _ B3 goes through block4 ═ Result _ k _ B4,
c1*Result_k_B1+c2*Result_k_B2+c3*Result_k_B3+c4*Result_k_B4＝A1。
referring to fig. 1 and 3, step S200 is described in detail:
s200, cross section processing: the cross section of the OCT image is subjected to segmentation processing, resulting in a segmentation result a 2. The processing method of the segmentation result A2 comprises the following steps:
i. inputting a 2D Image { Image (i, j, k) of the cross-section; 1, 2, 3, …, N } { Image (1, j, k), Image (2, j, k), Image (3, j, k), …, Image (N, j, k) }, wherein Image (i, j, k) represents the coordinates of each point in the 2D Image;
and ii, outputting the segmented 2D images, wherein the size of the segmented 2D images is consistent with that of the input image, the pixel of a useful area is 1, the pixel of a useless area is 0, and obtaining 2D images of all cross sections, and combining the 2D images to obtain a 3D image A2. In which convolution operations are performed on respective 2D images of the cross-sections, and a 3D image a2 is obtained in combination.
The specific method is as follows:
Block1:
for the 2D Image { Image (i, j, k), i ═ 1, 2, 3, …, N } of the i-th depth section, filter _ i1 of 3 × 3 is subjected to convolution operation to obtain result _ i1, result _ i1 is subjected to convolution operation through filter _ i2 of 3 × 5 to obtain result _ i2, result _ i2 is subjected to convolution operation through filter _ i3 of 5 × 3 to obtain result _ i3, result _ i3 is subjected to convolution operation through filter _ i4 of 5 × 5 to obtain result _ i4, B1 is caused _ i1+ B2 result _ i2+ B3 is caused by result _ i3+ B4 + B4.
Block2, Block3, Block 4: the structure is the same as Block 1.
Result _ i _ B1 goes through Block2 ═ Result _ i _ B2,
result _ i _ B2 goes through Block3 ═ Result _ i _ B3,
result _ i _ B3 goes through Block4 ═ Result _ i _ B4,
d1*Result_i_B1+d2*Result_i_B2+d3*Result_i_B3+d4*Result_i_B4＝A2。
referring to fig. 1, step S300 is described in detail:
s300, comprehensive cross section treatment: the depth section processing result a1 and the cross section processing result a2 are integrated and subjected to segmentation processing, and a segmentation result a is obtained. The processing method of the segmentation result A comprises the following steps:
i. inputting all the depth section segmentation results A1 and the cross section segmentation results A2;
the segmentation result a is calculated by integrating the depth interface segmentation result a1 and the cross-section segmentation result a2, wherein a is a1 and a 2.
The specific algorithm is:
referring to fig. 1, step S400 is described in detail:
s400, result analysis: and calculating a plaque attenuation index IPA according to the segmentation result A to obtain the plaque category. The specific method for analyzing the result comprises the following steps:
i. calculating and inputting the segmentation result A according to a calculation formula of the segmentation result A;
outputting the plaque categories;
calculating the value of the plaque attenuation coefficient IPA:
where x is the plaque attenuation coefficient threshold, μtAs attenuation coefficient, N (. mu.)tX) means the number of pixels with attenuation coefficient greater than x, NtotalEffective area representing segmentation result A. IPA denotes the plaque attenuation index (indexoplaqueattention) used to quantify the degree of vascular plaque attenuation. The calculation method is to multiply by 1000 when the pixel fractions of different types of plaques in the attenuation map are larger than the attenuation coefficient threshold value x. The study represented fibrous plaques with calculated values IPA6, IPA11 indicating lipid plaques. Wherein the larger the IPA, the less stable the plaque.
The invention not only considers the characteristics of common image classification, but also combines the clinical characteristics of OCT, and simultaneously analyzes two sections of the OCT image: depth section and cross section. Fig. 4 and 5 are depth section 2D images and cross section 2D images of OCT, respectively. In the depth section: each 2D section of the OCT image presents a circular or circular-like interference aperture; in cross section, OCT image can be viewed from cross section after three-dimensional reconstruction, each cross section is 2D image, and is characterized in that a certain middle area has a transverse bent interval stripe. By carrying out three-dimensional reconstruction and segmentation on the 3D OCT image, obtaining a quantitative index IPA and finally classifying the plaque based on the IPA, the problem of weak plaque identification capability in the prior art can be effectively solved.
While the invention has been described with respect to a preferred embodiment, it will be understood by those skilled in the art that the foregoing and other changes, omissions and deviations in the form and detail thereof may be made without departing from the scope of this invention. Those skilled in the art can make various changes, modifications and equivalent arrangements, which are equivalent to the embodiments of the present invention, without departing from the spirit and scope of the present invention, and which may be made by utilizing the techniques disclosed above; meanwhile, any changes, modifications and variations of the above-described embodiments, which are equivalent to those of the technical spirit of the present invention, are within the scope of the technical solution of the present invention.
Claims (7)
1. An OCT cardiovascular plaque automatic identification and analysis method based on deep learning is characterized by comprising the following steps:
s100, depth section processing: carrying out segmentation processing on the depth section of the OCT image to obtain a segmentation result A1;
s200, cross section processing: performing segmentation processing on the cross section of the OCT image to obtain a segmentation result A2;
s300, comprehensive cross section treatment: integrating the depth section processing result A1 and the cross section processing result A2 and carrying out segmentation processing to obtain a segmentation result A;
s400, result analysis: and calculating a plaque attenuation index IPA according to the segmentation result A to obtain the plaque category.
2. The deep learning-based automatic OCT cardiovascular plaque identification and analysis method according to claim 1, wherein in step S100, the depth section processing comprises:
s101, inputting a 2D Image { Image (i, j, k) of a depth section; k is 1, 2, 3, …, M } { Image (i, j, 1), Image (i, j, 2), Image (i, j, 3), …, Image (i, j, M) }, wherein Image (i, j, k) represents the coordinates of each point in the 2D Image;
s102 outputs the divided 2D images, and obtains 2D images of all depth sections with the size of the 2D images being equal to that of the input image, the useful region pixels being 1, and the useless region pixels being 0, and then combines them to obtain a 3D image a 1.
3. The deep learning-based OCT cardiovascular plaque automatic identification and analysis method as claimed in claim 2, wherein the specific processing method of step S102 is: the 2D images of the depth sections are subjected to convolution operation, and combined to obtain a 3D image a 1.
4. The deep learning-based OCT cardiovascular plaque automatic identification and analysis method of claim 1, wherein in step S200, the cross-section processing specific steps comprise:
s201, inputting a 2D Image { Image (i, j, k) of a cross section; 1, 2, 3, …, N } { Image (1, j, k), Image (2, j, k), Image (3, j, k), …, Image (N, j, k) }, wherein Image (i, j, k) represents the coordinates of each point in the 2D Image;
s202, the divided 2D images are output, and the size of the 2D images is the same as that of the input image, the pixels of the useful region are 1, and the pixels of the useless region are 0, and 2D images of all cross sections are obtained and combined to obtain a 3D image a 2.
5. The deep learning-based automatic OCT cardiovascular plaque identification and analysis method according to claim 1, wherein the convolution operation is performed on each 2D image of the cross section, and a 3D image A2 is obtained in combination.
6. The deep learning-based OCT cardiovascular plaque automatic identification and analysis method as claimed in claim 1, wherein in step S300, the cross-section integration processing specific steps comprise:
s301, inputting all the depth section segmentation results A1 and the cross section segmentation results A2;
s302, the integrated depth interface segmentation result a1 and the cross-section segmentation result a2 calculate the segmentation result a, where a is a1 and a 2.
7. The deep learning-based OCT cardiovascular plaque automatic identification and analysis method as claimed in claim 1, wherein in step S400, the specific steps of result analysis comprise:
s401, calculating and inputting a segmentation result A according to a calculation formula of the segmentation result A;
s402, outputting the category of the plaque;
s403, calculating the value of the plaque attenuation coefficient IPA:
where x is the plaque attenuation coefficient threshold, μtAs attenuation coefficient, N (. mu.)tX) means the number of pixels with attenuation coefficient greater than x, NtotalThe effective area of the segmentation result a is shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110263890.5A CN112927212B (en) | 2021-03-11 | 2021-03-11 | OCT cardiovascular plaque automatic identification and analysis method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110263890.5A CN112927212B (en) | 2021-03-11 | 2021-03-11 | OCT cardiovascular plaque automatic identification and analysis method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112927212A true CN112927212A (en) | 2021-06-08 |
| CN112927212B CN112927212B (en) | 2023-10-27 |
Family
ID=76172610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110263890.5A Active CN112927212B (en) | 2021-03-11 | 2021-03-11 | OCT cardiovascular plaque automatic identification and analysis method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112927212B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538471A (en) * | 2021-06-30 | 2021-10-22 | 上海联影医疗科技股份有限公司 | Method and device for dividing patch, computer equipment and storage medium |
| CN114469337A (en) * | 2021-07-05 | 2022-05-13 | 深圳市中科微光医疗器械技术有限公司 | Ablation catheter assembly, laser ablation system and method |
| WO2023284055A1 (en) * | 2021-07-13 | 2023-01-19 | 深圳市中科微光医疗器械技术有限公司 | Method and device for calculating ipa of intraluminal oct image |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101011260A (en) * | 2006-02-01 | 2007-08-08 | 西门子公司 | Method and CT system for detecting and differentiating plaque in vessel structures of a patient |
| US20110071404A1 (en) * | 2009-09-23 | 2011-03-24 | Lightlab Imaging, Inc. | Lumen Morphology and Vascular Resistance Measurements Data Collection Systems, Apparatus and Methods |
| US20140303499A1 (en) * | 2013-04-09 | 2014-10-09 | Konica Minolta, Inc. | Ultrasound diagnostic apparatus and method for controlling the same |
| US20140371593A1 (en) * | 2012-01-19 | 2014-12-18 | Konica Minolta, Inc. | Ultrasound diagnostic device and method for controlling ultrasound diagnostic device |
| CN104398271A (en) * | 2014-11-14 | 2015-03-11 | 西安交通大学 | Method using three-dimensional mechanics and tissue specific imaging of blood vessels and plaques for detection |
| CN104794708A (en) * | 2015-04-10 | 2015-07-22 | 浙江工业大学 | Atherosclerosis plaque composition dividing method based on multi-feature learning |
| CN109697459A (en) * | 2018-12-04 | 2019-04-30 | 云南大学 | One kind is towards optical coherence tomography image patch Morphology observation method |
| CN110136157A (en) * | 2019-04-09 | 2019-08-16 | 华中科技大学 | A kind of three-dimensional carotid ultrasound image vascular wall dividing method based on deep learning |
| CN110223781A (en) * | 2019-06-03 | 2019-09-10 | 中国医科大学附属第一医院 | A kind of various dimensions plaque rupture Warning System |
| CN111161216A (en) * | 2019-12-09 | 2020-05-15 | 杭州脉流科技有限公司 | Intravascular ultrasound image processing method, device, equipment and storage medium based on deep learning |
| CN111445473A (en) * | 2020-03-31 | 2020-07-24 | 复旦大学 | Vascular membrane accurate segmentation method and system based on intravascular ultrasound image sequence multi-angle reconstruction |
| US20200288971A1 (en) * | 2019-03-14 | 2020-09-17 | Oregon Health & Science University | Visual field simulation using optical coherence tomography and optical coherence tomographic angiography |
| CN111768403A (en) * | 2020-07-09 | 2020-10-13 | 成都全景恒升科技有限公司 | Calcified plaque detection decision-making system and device based on artificial intelligence algorithm |
-
2021
- 2021-03-11 CN CN202110263890.5A patent/CN112927212B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101011260A (en) * | 2006-02-01 | 2007-08-08 | 西门子公司 | Method and CT system for detecting and differentiating plaque in vessel structures of a patient |
| US20110071404A1 (en) * | 2009-09-23 | 2011-03-24 | Lightlab Imaging, Inc. | Lumen Morphology and Vascular Resistance Measurements Data Collection Systems, Apparatus and Methods |
| US20140371593A1 (en) * | 2012-01-19 | 2014-12-18 | Konica Minolta, Inc. | Ultrasound diagnostic device and method for controlling ultrasound diagnostic device |
| US20140303499A1 (en) * | 2013-04-09 | 2014-10-09 | Konica Minolta, Inc. | Ultrasound diagnostic apparatus and method for controlling the same |
| CN104398271A (en) * | 2014-11-14 | 2015-03-11 | 西安交通大学 | Method using three-dimensional mechanics and tissue specific imaging of blood vessels and plaques for detection |
| CN104794708A (en) * | 2015-04-10 | 2015-07-22 | 浙江工业大学 | Atherosclerosis plaque composition dividing method based on multi-feature learning |
| CN109697459A (en) * | 2018-12-04 | 2019-04-30 | 云南大学 | One kind is towards optical coherence tomography image patch Morphology observation method |
| US20200288971A1 (en) * | 2019-03-14 | 2020-09-17 | Oregon Health & Science University | Visual field simulation using optical coherence tomography and optical coherence tomographic angiography |
| CN110136157A (en) * | 2019-04-09 | 2019-08-16 | 华中科技大学 | A kind of three-dimensional carotid ultrasound image vascular wall dividing method based on deep learning |
| CN110223781A (en) * | 2019-06-03 | 2019-09-10 | 中国医科大学附属第一医院 | A kind of various dimensions plaque rupture Warning System |
| CN111161216A (en) * | 2019-12-09 | 2020-05-15 | 杭州脉流科技有限公司 | Intravascular ultrasound image processing method, device, equipment and storage medium based on deep learning |
| CN111445473A (en) * | 2020-03-31 | 2020-07-24 | 复旦大学 | Vascular membrane accurate segmentation method and system based on intravascular ultrasound image sequence multi-angle reconstruction |
| CN111768403A (en) * | 2020-07-09 | 2020-10-13 | 成都全景恒升科技有限公司 | Calcified plaque detection decision-making system and device based on artificial intelligence algorithm |
Non-Patent Citations (5)
| Title |
|---|
| HELIN CEREN K?SE;OYA TEKELI;: "Optical coherence tomography angiography of the peripapillary region and macula in normal, primary open angle glaucoma, pseudoexfoliation glaucoma and ocular hypertension eyes", INTERNATIONAL JOURNAL OF OPHTHALMOLOGY, no. 05 * |
| UNDURTI N DAS;: "Molecular pathobiology of scleritis and its therapeutic implications", INTERNATIONAL JOURNAL OF OPHTHALMOLOGY, no. 01 * |
| 曾绍群，骆清铭，刘贤德，徐海峰，李再光: "OCT纵向图像形成分析", 电子学报, no. 10 * |
| 蔡梦媛;周然;程新耀;丁明跃;: "基于深度学习的颈动脉超声图像斑块分割算法", 生命科学仪器, no. 03 * |
| 陆冬筱;房文汇;李玉瑶;李金华;王笑军;: "光学相干层析成像技术原理及研究进展", 中国光学, no. 05 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538471A (en) * | 2021-06-30 | 2021-10-22 | 上海联影医疗科技股份有限公司 | Method and device for dividing patch, computer equipment and storage medium |
| CN113538471B (en) * | 2021-06-30 | 2023-09-22 | 上海联影医疗科技股份有限公司 | Plaque segmentation method, plaque segmentation device, computer equipment and storage medium |
| CN114469337A (en) * | 2021-07-05 | 2022-05-13 | 深圳市中科微光医疗器械技术有限公司 | Ablation catheter assembly, laser ablation system and method |
| WO2023284055A1 (en) * | 2021-07-13 | 2023-01-19 | 深圳市中科微光医疗器械技术有限公司 | Method and device for calculating ipa of intraluminal oct image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112927212B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112927212A (en) | OCT cardiovascular plaque automatic identification and analysis method based on deep learning | |
| CN109325942B (en) | Fundus image structure segmentation method based on full convolution neural network | |
| Bjornsson et al. | Associative image analysis: a method for automated quantification of 3D multi-parameter images of brain tissue | |
| CN113420826B (en) | Liver focus image processing system and image processing method | |
| Qian et al. | An integrated method for atherosclerotic carotid plaque segmentation in ultrasound image | |
| CN113610808B (en) | Group brain map individuation method, system and equipment based on individual brain connection diagram | |
| CN110503635B (en) | Hand bone X-ray film bone age assessment method based on heterogeneous data fusion network | |
| JP2009531117A (en) | Method and system for automatically recognizing precancerous abnormalities in anatomical structures and corresponding computer program | |
| CN111583385B (en) | Personalized deformation method and system for deformable digital human anatomy model | |
| Włodarczyk et al. | Spontaneous preterm birth prediction using convolutional neural networks | |
| Zhu et al. | Automatic measurement of fetal femur length in ultrasound images: a comparison of random forest regression model and SegNet | |
| CN113782184A (en) | Cerebral apoplexy auxiliary evaluation system based on facial key point and feature pre-learning | |
| CN113223005A (en) | Thyroid nodule automatic segmentation and grading intelligent system | |
| Ilanchezian et al. | Interpretable gender classification from retinal fundus images using BagNets | |
| Xu et al. | Weakly supervised detection of central serous chorioretinopathy based on local binary patterns and discrete wavelet transform | |
| Nayan et al. | A deep learning approach for brain tumor detection using magnetic resonance imaging | |
| CN114332910A (en) | Human body part segmentation method for similar feature calculation of far infrared image | |
| Singh et al. | Good view frames from ultrasonography (USG) video containing ONS diameter using state-of-the-art deep learning architectures | |
| CN116725563B (en) | Eyeball salience measuring device | |
| Saad et al. | Segmentation and classification analysis techniques for stroke based on diffusion weighted images | |
| Li et al. | Classify and explain: An interpretable convolutional neural network for lung cancer diagnosis | |
| CN115969400A (en) | Apparatus for measuring area of eyeball protrusion | |
| Supriyanti et al. | Coronal slices segmentation of mri images using active contour method on initial identification of alzheimer severity level based on clinical dementia rating (CDR) | |
| Hu et al. | Slice grouping and aggregation network for auxiliary diagnosis of rib fractures | |
| CN111768845B (en) | Pulmonary nodule auxiliary detection method based on optimal multi-scale perception |
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 |