CN112070778A - Multi-parameter extraction method based on intravascular OCT and ultrasound image fusion - Google Patents
Multi-parameter extraction method based on intravascular OCT and ultrasound image fusion Download PDFInfo
- Publication number
- CN112070778A CN112070778A CN202010861189.9A CN202010861189A CN112070778A CN 112070778 A CN112070778 A CN 112070778A CN 202010861189 A CN202010861189 A CN 202010861189A CN 112070778 A CN112070778 A CN 112070778A
- Authority
- CN
- China
- Prior art keywords
- oct
- picture
- plaque
- image fusion
- intravascular
- 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
- 230000004927 fusion Effects 0.000 title claims abstract description 12
- 238000002604 ultrasonography Methods 0.000 title claims abstract description 10
- 238000000605 extraction Methods 0.000 title claims abstract description 9
- 210000004231 tunica media Anatomy 0.000 claims abstract description 14
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 12
- 238000002608 intravascular ultrasound Methods 0.000 claims abstract description 10
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 8
- 238000013135 deep learning Methods 0.000 claims abstract description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000000034 method Methods 0.000 claims 1
- 230000035515 penetration Effects 0.000 abstract description 10
- 238000003384 imaging method Methods 0.000 abstract description 9
- 230000007547 defect Effects 0.000 abstract description 2
- 150000002632 lipids Chemical class 0.000 description 4
- 210000003716 mesoderm Anatomy 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000000004 hemodynamic effect Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000007499 fusion processing Methods 0.000 description 2
- 208000028867 ischemia Diseases 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 238000002601 radiography Methods 0.000 description 2
- 229920006302 stretch film Polymers 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000011176 pooling Methods 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
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
- Image Analysis (AREA)
Abstract
A multi-parameter extraction algorithm based on intravascular OCT and ultrasound image fusion is characterized in that an IVUS picture and an OCT picture of the same blood vessel are used for image fusion, the fused picture is used for deep learning to identify the tunica media of an OCT image, a satisfactory artificial intelligence algorithm is trained, the OCT picture is input into the artificial intelligence algorithm, the tunica media and a lumen boundary can be segmented, and therefore plaque load information can be obtained. The invention makes up the defect of insufficient penetration force of OCT imaging and can quickly obtain image load.
Description
Technical Field
The invention relates to an image processing technology, in particular to an OCT image processing technology, and specifically relates to a multi-parameter extraction algorithm based on intravascular OCT and ultrasound image fusion.
Background
At present, technical means such as X-ray, ultrasound and OCT have been widely used for diagnosis and treatment of various diseases. The X-ray has lower resolution, but can be used for large-range and integral imaging, is the basis of the current radiography imaging and is also the gold standard for coronary artery evaluation and treatment, but radiography can only provide two-dimensional imaging information and can not provide tissue composition information in a tube cavity; the resolution of the intravascular ultrasound is about 100-200 microns, and the penetration depth can reach 10 mm; the resolution of intravascular OCT is about 10-20 microns with a penetration depth of about 1-2 mm. Currently, these three imaging techniques are clinically complementary to each other and used in concert. Since the imaging mechanisms of intravascular ultrasound and intravascular OCT are similar, the main difference is resolution and penetration depth, and intravascular ultrasound has the main advantages over intravascular OCT in clinical application in that plaque burden can be evaluated, but the ultrasound signal cannot penetrate calcified plaque and the resolution of the ultrasound signal is low, and the lumen area is often overestimated when calculating the lumen area. Intravascular OCT has an ultrahigh resolution, can identify various plaques, limits the penetration depth, and cannot effectively identify the middle membrane position of the plaque position, thus failing to provide plaque load information and effectively imaging lipid plaques.
Disclosure of Invention
The invention aims to provide a multi-parameter extraction method based on intravascular OCT and ultrasonic image fusion, aiming at the problems that the middle membrane position of a plaque position cannot be effectively identified due to low penetrating power of an OCT imaging technology, plaque load information cannot be provided, and lipid plaques cannot be effectively imaged.
The technical scheme of the invention is as follows:
a multi-parameter extraction method based on intravascular OCT and ultrasound image fusion is characterized in that an IVUS picture and an OCT picture of the same section of blood vessel are used for image fusion, deep learning is carried out on the fused picture to identify the tunica media of an OCT image, a satisfactory artificial intelligence algorithm is trained, the OCT picture is input into the artificial intelligence algorithm, the tunica media and a lumen boundary can be segmented, and therefore plaque load information can be obtained.
The plaque load evaluation is the occupation effect of plaque on the original blood vessel lumen, and the calculation formula is
The cross-sectional area of the outer stretch film is typically characterized using the cross-sectional area of the middle film. Because intravascular ultrasound has a large penetration depth, the tunica media can be imaged at the plaque-rich part, so that the plaque area and the tunica media area can be measured, and the plaque load condition can be further evaluated. The penetration depth of the intravascular OCT to tissues is only 1-2 mm, and when the plaque depth is more than 1mm or a special plaque is encountered (a lipid pool), the intima cannot be effectively imaged, so that the conventional OCT image cannot evaluate the plaque load condition.
The invention has the beneficial effects that:
the invention makes up the defect of insufficient penetration force of OCT imaging and can quickly obtain image load.
Drawings
FIG. 1 is a schematic flow chart of the algorithm of the present invention.
FIG. 2 is a schematic diagram of the image fusion process of the present invention.
Fig. 3 is a schematic diagram of the segmentation of the tunica media (green) and the lumen (blue) and the plaque load information by inputting the OCT image into the model.
Fig. 4 shows a section of a blood vessel identified, and the lumen and media locations (arrows) at the plaque are obtained, and a hemodynamic analysis can be performed to further evaluate the ischemia condition of the blood vessel and the local eddy current and stress distribution.
Fig. 5 is a schematic diagram of a U-net network structure.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
As shown in fig. 1-5.
A multi-parameter extraction method based on intravascular OCT and ultrasound image fusion is characterized in that an IVUS picture and an OCT picture of the same blood vessel are used for image fusion, the fused picture is used for deep learning to identify the mesoderm of an OCT image, a satisfactory artificial intelligence algorithm is trained, the OCT picture is input into the artificial intelligence algorithm, the mesoderm and a lumen boundary can be segmented, and therefore plaque load information can be obtained. The plaque load evaluation is the occupation effect of plaque on the original blood vessel lumen, and the calculation formula is
The cross-sectional area of the outer stretch film is typically characterized using the cross-sectional area of the middle film. Because intravascular ultrasound has a large penetration depth, the tunica media can be imaged at the plaque-rich part, so that the plaque area and the tunica media area can be measured, and the plaque load condition can be further evaluated. The penetration depth of the intravascular OCT to tissues is only 1-2 mm, and when the plaque depth is more than 1mm or a special plaque is encountered (a lipid pool), the intima cannot be effectively imaged, so that the conventional OCT image cannot evaluate the plaque load condition.
The specific algorithm flow is shown in FIG. 1
The image fusion process is shown in fig. 2: and inputting an IVUS image, identifying the tunica media, and accurately marking the identified tunica media on the OCT image.
Then the OCT image is input into the model, the tunica media (green) and the lumen (blue) can be segmented, and the plaque load information can be obtained. As shown in fig. 3.
The algorithm can not only obtain plaque load information, but also identify a section of blood vessel to obtain the mesoderm and lumen information of the section of blood vessel, so that the hemodynamics calculation (figure 4) is carried out, the section of blood vessel is identified to obtain the lumen and the mesoderm position (arrow position) of the plaque, the hemodynamics analysis can be carried out, and the ischemia condition of the blood vessel and the local eddy current and stress distribution can be further evaluated.
And (3) network model: u-net
The U-net network model is one of models which are applied more in the semantic segmentation field, particularly in the medical field. Considering the limited data set of medical images, we have adopted the U-net network model. The greatest advantage of the model is that learning is carried out through a small training set, and good effect can be obtained.
The U-net network is very simple, the first half is used for feature extraction and the second half is upsampled, and this structure can also be called an encoder-decoder. The whole structure of the network is similar to the capital letter U, so the network is called U-net. As shown in FIG. 5, FIG. 5 is a U-net network semantic segmentation model, the left side represents down-sampling and the right side represents up-sampling. The first layer is the input layer (input), the input picture size is 572 × 572, and the maximum pooled (max × pool) result continues the convolution as input for one layer by two-layer convolution (number of volumes (conv) is 64, convolution size is 3 × 3, activation function is ReLU). After four times of large convolution pooling, downsampling is completed. For the fourth result, deconvolution up-sampling (up-conv) is adopted, and the step size is 2, so that the feature is combined with the corresponding down-sampling layer. After four times of downsampling, the output layer (output) uses a convolution layer of 1 × 1, and outputs the classification prediction result by using a softmax activation function. In the case of limited data sets, the data may be enhanced by copying, cutting, rotating (copy, crop) pictures.
The present invention is not concerned with parts that are the same as the prior art or that can be implemented using the prior art.
Claims (2)
1. A multi-parameter extraction method based on intravascular OCT and ultrasound image fusion is characterized in that an IVUS picture and an OCT picture of the same section of blood vessel are used for image fusion, deep learning is carried out on the fused picture to identify the tunica media of an OCT image, a satisfactory artificial intelligence algorithm is trained, the OCT picture is input into the artificial intelligence algorithm, the tunica media and a lumen boundary can be segmented, and therefore plaque load information can be obtained.
2. The method of claim 1, wherein the plaque burden assessment is a plaque occupancy effect on the lumen of the native vessel, and is calculated by the formula:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010861189.9A CN112070778A (en) | 2020-08-25 | 2020-08-25 | Multi-parameter extraction method based on intravascular OCT and ultrasound image fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010861189.9A CN112070778A (en) | 2020-08-25 | 2020-08-25 | Multi-parameter extraction method based on intravascular OCT and ultrasound image fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112070778A true CN112070778A (en) | 2020-12-11 |
Family
ID=73659284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010861189.9A Pending CN112070778A (en) | 2020-08-25 | 2020-08-25 | Multi-parameter extraction method based on intravascular OCT and ultrasound image fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112070778A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112587170A (en) * | 2020-12-29 | 2021-04-02 | 全景恒升（北京）科学技术有限公司 | Intravascular plaque load detection method, system and terminal based on dual-mode imaging |
| CN115644989A (en) * | 2022-12-29 | 2023-01-31 | 南京沃福曼医疗科技有限公司 | Multi-channel pulse high-voltage parameter controllable shock wave lithotripsy balloon imaging system and catheter thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070043292A1 (en) * | 2005-08-08 | 2007-02-22 | Siemens Aktiengesellschaft | Method for acquiring and evaluating vascular examination data |
| CN107730540A (en) * | 2017-10-09 | 2018-02-23 | 全景恒升（北京）科学技术有限公司 | The computational methods of coronary artery parameter based on high-precision Matching Model |
| CN109091167A (en) * | 2018-06-29 | 2018-12-28 | 东南大学 | The prediction technique that Coronary Atherosclerotic Plaque increases |
| CN110070529A (en) * | 2019-04-19 | 2019-07-30 | 深圳睿心智能医疗科技有限公司 | A kind of Endovascular image division method, system and electronic equipment |
| CN111291736A (en) * | 2020-05-07 | 2020-06-16 | 南京景三医疗科技有限公司 | Image correction method and device and medical equipment |
| CN111523538A (en) * | 2020-04-14 | 2020-08-11 | 博动医学影像科技（上海）有限公司 | Blood vessel image processing method and system, computing device and storage medium |
-
2020
- 2020-08-25 CN CN202010861189.9A patent/CN112070778A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070043292A1 (en) * | 2005-08-08 | 2007-02-22 | Siemens Aktiengesellschaft | Method for acquiring and evaluating vascular examination data |
| CN107730540A (en) * | 2017-10-09 | 2018-02-23 | 全景恒升（北京）科学技术有限公司 | The computational methods of coronary artery parameter based on high-precision Matching Model |
| CN109091167A (en) * | 2018-06-29 | 2018-12-28 | 东南大学 | The prediction technique that Coronary Atherosclerotic Plaque increases |
| CN110070529A (en) * | 2019-04-19 | 2019-07-30 | 深圳睿心智能医疗科技有限公司 | A kind of Endovascular image division method, system and electronic equipment |
| CN111523538A (en) * | 2020-04-14 | 2020-08-11 | 博动医学影像科技（上海）有限公司 | Blood vessel image processing method and system, computing device and storage medium |
| CN111291736A (en) * | 2020-05-07 | 2020-06-16 | 南京景三医疗科技有限公司 | Image correction method and device and medical equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112587170A (en) * | 2020-12-29 | 2021-04-02 | 全景恒升（北京）科学技术有限公司 | Intravascular plaque load detection method, system and terminal based on dual-mode imaging |
| CN112587170B (en) * | 2020-12-29 | 2022-06-21 | 全景恒升（北京）科学技术有限公司 | Intravascular plaque load detection method, system and terminal based on dual-mode imaging |
| CN115644989A (en) * | 2022-12-29 | 2023-01-31 | 南京沃福曼医疗科技有限公司 | Multi-channel pulse high-voltage parameter controllable shock wave lithotripsy balloon imaging system and catheter thereof |
| CN115644989B (en) * | 2022-12-29 | 2023-09-15 | 南京沃福曼医疗科技有限公司 | Multi-channel impulse high-pressure parameter controllable shock wave lithotriptic balloon imaging system and catheter thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7341874B2 (en) | Image processing device, image processing method, and program | |
| US7359554B2 (en) | System and method for identifying a vascular border | |
| Saba et al. | Ultrasound-based carotid stenosis measurement and risk stratification in diabetic cohort: a deep learning paradigm | |
| CN110599499B (en) | MRI image heart structure segmentation method based on multipath convolutional neural network | |
| JP4481824B2 (en) | System and method for identifying vascular borders | |
| CN111667478A (en) | Method and system for identifying carotid plaque through CTA-MRA cross-modal prediction | |
| CN112070778A (en) | Multi-parameter extraction method based on intravascular OCT and ultrasound image fusion | |
| Xie et al. | Vessel lumen segmentation in internal carotid artery ultrasounds with deep convolutional neural networks | |
| CN113420826A (en) | Liver focus image processing system and image processing method | |
| CN109003280A (en) | Inner membrance dividing method in a kind of blood vessel of binary channels intravascular ultrasound image | |
| CN116051826A (en) | Coronary vessel segmentation method based on DSA image continuous frame sequence, computer equipment and readable storage medium | |
| US20220138936A1 (en) | Systems and methods for calcium-free computed tomography angiography | |
| Pociask et al. | Fully automated lumen segmentation method for intracoronary optical coherence tomography | |
| CN113470060B (en) | Coronary artery multi-angle curved surface reconstruction visualization method based on CT image | |
| CN112562058B (en) | Method for quickly establishing intracranial vascular simulation three-dimensional model based on transfer learning | |
| CN115861612A (en) | Method for automatically segmenting coronary vessels based on DSA (digital Signal amplification) images | |
| CN113744215B (en) | Extraction method and device for central line of tree-shaped lumen structure in three-dimensional tomographic image | |
| CN111798438B (en) | Intravascular ultrasound image intelligent segmentation method and system | |
| Xia et al. | AwCPM-Net: a collaborative constraint GAN for 3D coronary artery reconstruction in intravascular ultrasound sequences | |
| CN112529906B (en) | Software-level intravascular oct three-dimensional image lumen segmentation method and device | |
| CN114022405A (en) | Intravascular ultrasound image processing method based on deep learning | |
| CN112967295A (en) | Image processing method and system based on residual error network and attention mechanism | |
| Mi et al. | Detecting carotid intima-media from small-sample ultrasound images | |
| Zhan et al. | Recognition of angiographic atherosclerotic plaque development based on deep learning | |
| Wang et al. | Vision Transformer-based Classification Study of Intracranial Hemorrhage |
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 |