CN112509095A - Oct image dislocation correction method - Google Patents
Oct image dislocation correction method Download PDFInfo
- Publication number
- CN112509095A CN112509095A CN202110165934.0A CN202110165934A CN112509095A CN 112509095 A CN112509095 A CN 112509095A CN 202110165934 A CN202110165934 A CN 202110165934A CN 112509095 A CN112509095 A CN 112509095A
- Authority
- CN
- China
- Prior art keywords
- dislocation
- oct image
- point
- angle
- correction method
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 24
- 238000006243 chemical reaction Methods 0.000 claims abstract description 4
- 230000008439 repair process Effects 0.000 claims description 7
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 abstract description 11
- 238000006073 displacement reaction Methods 0.000 abstract description 3
- 238000012014 optical coherence tomography Methods 0.000 description 9
- 230000003287 optical effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 210000003743 erythrocyte Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 208000007536 Thrombosis Diseases 0.000 description 1
- 238000000149 argon plasma sintering Methods 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 125000003473 lipid group Chemical group 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/008—Specific post-processing after tomographic reconstruction, e.g. voxelisation, metal artifact correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Endoscopes (AREA)
Abstract
The invention discloses an oct image dislocation correction method. Reading an oct image in a blood vessel, and acquiring lumen contour information of the blood vessel from the oct image; the oct image and the lumen contour information are taken as the center (x) of the oct image0,y0) Performing polar coordinate conversion on the original point, and obtaining the distance from the lumen contour to the central point at each angle theta within the range of 0-360 degrees according to the lumen contour information; subtracting the distances at intervals of n degrees to obtain a gradient at the maximum angle of the gradientJudging the position to be dislocation, wherein the corresponding gradient is dislocation amplitude, if the dislocation amplitude is smaller than a threshold value T, carrying out rough judgment, otherwise, carrying out rough judgmentAnd performing fine judgment. According to the invention, the fine dislocation and the fine dislocation amplitude are calculated, and then the fine dislocation is repaired according to the fine dislocation amplitude, so that the dislocation generated due to the displacement of the relative position of the catheter and the blood vessel wall during oct imaging can be accurately corrected and repaired.
Description
Technical Field
The invention relates to the technical field of oct image processing, in particular to an oct image dislocation correction method.
Background
Optical Coherence Tomography (OCT) is a non-invasive probing technique. OCT technology has been widely used for imaging the structure of a living body cross section of a biological tissue. By measuring the scattered light as a function of depth, OCT can provide high resolution, high sensitivity tissue structures.
When the OCT is applied to blood vessel imaging, near infrared light is emitted to the inner surface of a blood vessel by using a rotatable optical lens and an optical fiber, and reflected light waves are received by using an optical interferometer and imaged. Because the optical wave imaging is utilized, the OCT imaging resolution is high, the axial resolution can reach 10-20um, and the components and the microstructure on the plaque surface can be imaged. However, the near infrared light wave is not very permeable (about 1.0-2.5 mm), and blood cells, red thrombus, and plaque lipid core or plaque necrosis all affect OCT observation of vessel wall structure and estimation of plaque burden. Because of red light scattering by red blood cells, past OCT requires constant injection of contrast agent to wash blood away during imaging. Modern OCT systems partially reduce the interference of red blood cells and the like on imaging by techniques such as rapid rotational withdrawal, and complete imaging of a length of blood vessel in a few seconds.
The dislocation cause of OCT blood vessel imaging: in the process of imaging by emitting near infrared light to the inner surface of a blood vessel through the rapid rotation of the optical lens and the optical fiber on the catheter, the relative position of the catheter and the blood vessel wall is displaced due to the movement of the catheter, the contraction and the relaxation of the blood vessel and the like, and the displacement is compared with the initial position and is accumulated to generate obvious dislocation. The resulting misalignment, shown at the top left in fig. 1, affects the observation and judgment.
Disclosure of Invention
The invention aims to provide an oct image misalignment correction method aiming at the defects in the prior art.
In order to achieve the above object, the present invention provides an oct image misalignment correction method, which includes:
reading an oct image in a blood vessel, and acquiring lumen contour information of the blood vessel from the oct image;
using the oct image and the lumen contour information as the center (x) of the oct image0,y0) Polar coordinate conversion is carried out for the origin, and the distance from the lumen contour to the central point under each angle theta within the range of 0-360 DEG is obtained according to the lumen contour information;
At a distance of n DEG eachSubtracting to obtain a gradientAt maximum angle of gradientJudging the position of the dislocation, wherein,
corresponding gradientIf the dislocation amplitude is smaller than the threshold value T, carrying out rough judgment, otherwise, carrying out fine judgment;
the rough judgment comprises the following steps: the angles are traversed from 0 to 360 in steps of 1 pixel at each angle θ, ranging fromTraversing the distance r to the origin, calculating the spacing distance at each angle asGray scale difference of the pointsDistance from the point of maximum gradation gradient to the origin as gradation gradientNamely:
calculating the difference value of the distances from the point with the maximum gray gradient to the original point, and judging the angle with the maximum absolute value as the dislocation:
Wherein,is composed ofThe distance from the point with the maximum gray scale gradient of the adjacent angles to the original point is judged as the dislocationThen carrying out fine judgment;
the fine judgment comprises the following steps: the traversal range is2 DEG and/or2 °, step size 0.1 °, at each angleDistance r from the lower traverse to the center point in the range ofStep size of 0.5 pixels, per angleDistance from point with maximum lower gray gradient to center pointNamely:
calculating the difference value of the distances from the point with the maximum gray gradient to the origin, and judging the angle with the maximum absolute value as the fine dislocationComprises the following steps:
the corresponding fine misalignment magnitudes are:
and carrying out dislocation repair on the fine dislocation part, and specifically comprising the following steps: selecting direction by taking the angle of the fine dislocation as a starting point, traversing each pixel point (x, y) in a fan-shaped range which rotates by a certain angle p along the direction as an end point, and calculating to obtain the radius of the pointAngle of andwherein:
calculating the dislocation amplitude of the pointIf Δ r > 0, the angle isRadius ofAnd assigning a pixel value at the position to the point, not processing the catheter in the image within the range, if delta r is less than 0, indicating that the contour at the position needs to be expanded, and filling the area between the repaired lumen contour and the lumen contour before repair.
Further, the lumen contour information is obtained through manual segmentation of an interactive interface.
Further, the lumen contour information is obtained by automatic segmentation through a machine learning method.
Further, the direction selection comprises manually selecting a clockwise or counterclockwise direction by manually referring to the blood vessel image information of the upper and lower frames on the interactive interface.
Further, the direction selection includes calculating curvature along the lumen contour at each angle according to the lumen contour information, and dividing two types of angle sets according to the clustering information of the curvature, wherein the direction in which the set with the smaller number is located is the selected direction.
Further, the filling comprises calculating a pixel distribution histogram in a range between the outside of the catheter and the lumen contour, and randomly selecting one of a plurality of pixel values with the highest frequency for filling.
Further, the method further includes performing boundary smoothing processing on the image subjected to the dislocation restoration, and specifically includes: in a manner thatAnd (4) traversing pixel points in the boundary range by taking +/-1 degrees as the boundary range, and carrying out median filtering by taking 5-5 pixels around the boundary point and eliminating the pixel points in the boundary range as masks.
Further, the angle θ includes 2 °.
Further, the n ° includes 5 °.
Has the advantages that: according to the invention, the fine dislocation and the fine dislocation amplitude are calculated, and then the fine dislocation is repaired according to the fine dislocation amplitude, so that the dislocation generated due to the displacement of the relative position of the catheter and the blood vessel wall during oct imaging can be accurately corrected and repaired.
Drawings
FIG. 1 is a schematic diagram of the conventional misalignment of oct images;
FIG. 2 is a flow chart of an oct image misalignment correction method according to an embodiment of the present invention;
FIG. 3 is a schematic illustration of the oct image after the restoration of the misalignment;
fig. 4 is a schematic diagram of the oct image after the boundary smoothing process.
Detailed Description
The present invention will be further illustrated with reference to the accompanying drawings and specific examples, which are carried out on the premise of the technical solution of the present invention, and it should be understood that these examples are only for illustrating the present invention and are not intended to limit the scope of the present invention.
As shown in fig. 2, an embodiment of the present invention provides a method for correcting an oct image misalignment, including:
and reading an oct image in the blood vessel, and segmenting the oct image to obtain lumen contour information of the blood vessel. The lumen contour information of the obtained blood vessel can be obtained by a certain blood vessel segmentation method. Specifically, an interactive interface can be created, and manual lumen segmentation is performed on the oct image in the blood vessel manually to acquire lumen contour information of the blood vessel. Or automatically segmenting the oct image based on a machine learning method to acquire lumen contour information of the blood vessel.
The oct image and the lumen contour information are taken as the center (x) of the oct image0,y0) Polar coordinate conversion is carried out for the origin, and the distance from the lumen contour to the central point under each angle theta within the range of 0-360 DEG is obtained according to the lumen contour information. Among them, the angle θ is preferably 2 °.
At a distance of n DEG eachSubtracting to obtain a gradientN ° is preferably 5 °, at the maximum angle of the gradientJudging the position of the dislocation, wherein,
corresponding gradientIf the dislocation amplitude is smaller than the threshold value T, rough judgment is carried out, and otherwise, fine judgment is carried out. The threshold T is typically 10 to 15 unit pixels and can be adjusted as desired.
The rough judgment of the embodiment of the invention comprises the following steps: the angles are traversed from 0 to 360 in steps of 1 pixel at each angle θ, ranging fromTraversing the distance r to the origin, calculating the spacing distance at each angle asGray scale difference of the pointsAs a result of the gradient of the gray scale,preferably 9 pixels, the distance from the point of maximum gray gradient to the originNamely:
calculating the difference value of the distances from the point with the maximum gray gradient to the original point, and preliminarily judging the angle with the maximum absolute value of the difference value as a dislocation:
Wherein,is composed ofThe distance from the point with the maximum gray gradient of the adjacent angles to the original point is judged as the dislocationAnd then carrying out fine judgment.
The fine judgment of the embodiment of the invention comprises the following steps: the traversal range is2 DEG and/or2 °, step size 0.1 °, at each angleDistance r from the lower traverse to the center point in the range ofStep size of 0.5 pixels, per angleDistance from point with maximum lower gray gradient to center pointNamely:
calculating the difference value of the distances from the point with the maximum gray gradient to the origin, and judging the angle with the maximum absolute value as the fine dislocationComprises the following steps:
the corresponding fine misalignment magnitudes are:
carry out dislocation restoration to meticulous dislocation department, specifically include: the direction selection is carried out by taking the angle of the fine dislocation as a starting point, and has two modes, specifically, the clockwise or anticlockwise direction can be manually selected by manually referring to the blood vessel image information of the upper frame and the lower frame on an interactive interface, or the clockwise or anticlockwise direction can be manually selected according to the lumen contourAnd calculating the curvature of the lumen contour under each angle by the information, dividing two types of angle sets according to the clustering information of the curvature, and taking the direction of the set with the smaller number as the selected direction. Traversing each pixel point (x, y) in a fan-shaped range which rotates for a certain angle p along the direction to be an end point, and calculating to obtain the radius of the pointAngle of andwherein:
Calculating the dislocation amplitude of the pointIf Δ r > 0, the angle isRadius ofAnd assigning a pixel value at the position to the point, not processing the catheter in the image within the range, if delta r is less than 0, indicating that the contour at the position needs to be expanded, and filling the area between the repaired lumen contour and the lumen contour before repair.
Filling the region between the lumen contour after repair and the lumen contour before repair comprises calculating a pixel distribution histogram in a range between the outside of the catheter and the lumen contour, and randomly selecting one of a plurality of pixel values with the highest frequency for filling. Can be expressed as:
wherein H is a pixel distribution histogram in a range between the outside of the catheter and the lumen contour,for a certain pixel in the pixel distribution histogram H,is the probability of the occurrence of the pixel,for the b-th highest probability of occurrence, b is generally equal to 9, that is, one of the first 9 names with the highest probability of occurrence is randomly selected for filling.
As shown in fig. 3 and 4, a boundary after repairing may have an obvious boundary line, and boundary smoothing is required, so the embodiment of the present invention further includes performing boundary smoothing processing on the image after dislocation repairing, specifically including: in a manner thatAnd (3) traversing pixel points in the boundary range by taking +/-1 degrees as the boundary range, taking 5-5 pixels around the boundary point and eliminating the pixel points in the boundary range as masks, carrying out median filtering, and then obtaining a finally repaired image.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that other parts not specifically described are within the prior art or common general knowledge to those of ordinary skill in the art. Without departing from the principle of the invention, several improvements and modifications can be made, and these improvements and modifications should also be construed as the scope of the invention.
Claims (10)
1. An oct image misalignment correction method, comprising:
reading an oct image in a blood vessel, and acquiring lumen contour information of the blood vessel from the oct image;
using the oct image and the lumen contour information as the center (x) of the oct image0,y0) Polar coordinate conversion is carried out for the origin, and the distance from the lumen contour to the central point under each angle theta within the range of 0-360 DEG is obtained according to the lumen contour information;
At a distance of n DEG eachSubtracting to obtain a gradientAt maximum angle of gradientJudging the position of the dislocation, wherein,
corresponding gradientIf the dislocation amplitude is smaller than the threshold value T, carrying out rough judgment, otherwise, carrying out fine judgment;
the rough judgment comprises the following steps: the angles are traversed from 0 to 360 in steps of 1 pixel at each angle θ, ranging fromTraversing the distance r to the origin, calculating the spacing distance at each angle asGray scale difference of the pointsDistance from the point of maximum gradation gradient to the origin as gradation gradientNamely:
calculating the difference value of the distances from the point with the maximum gray gradient to the original point, and judging the angle with the maximum absolute value as the dislocation:
Wherein,is composed ofThe distance from the point with the maximum gray scale gradient of the adjacent angles to the original point is judged as the dislocationThen carrying out fine judgment;
the fine judgment comprises the following steps: the traversal range is2 DEG and/or2 °, step size 0.1 °, at each angleDistance r from the lower traverse to the center point in the range ofStep size of 0.5 pixels, per angleDistance from point with maximum lower gray gradient to center pointNamely:
calculating the difference value of the distances from the point with the maximum gray gradient to the origin, and judging the angle with the maximum absolute value as the fine dislocationComprises the following steps:
the corresponding fine misalignment magnitudes are:
and carrying out dislocation repair on the fine dislocation part, and specifically comprising the following steps: selecting direction by taking the angle of the fine dislocation as a starting point, traversing each pixel point (x, y) in a fan-shaped range which rotates by a certain angle p along the direction as an end point, and calculating to obtainRadius of the pointAngle of andwherein:
calculating the dislocation amplitude of the pointIf Δ r > 0, the angle isRadius ofAnd assigning a pixel value at the position to the point, not processing the catheter in the image within the range, if delta r is less than 0, indicating that the contour at the position needs to be expanded, and filling the area between the repaired lumen contour and the lumen contour before repair.
2. The oct image-misalignment correction method according to claim 1, wherein the lumen contour information is obtained by manual segmentation via an interactive interface.
3. The oct image misalignment correction method according to claim 1, wherein the lumen contour information is obtained by automatic segmentation using a machine learning method.
4. The oct image-misalignment-correction method according to claim 1, wherein the direction selection includes manually selecting a clockwise or counterclockwise direction with reference to the vessel image information of the upper and lower frames on the interactive interface.
5. The oct image-misalignment correction method according to claim 1, wherein the direction selection includes calculating a curvature along the lumen contour at each angle according to the lumen contour information, and dividing two types of angle sets according to the curvature clustering information, wherein a direction in which a smaller number of types of sets are located is the selected direction.
6. The oct image-misalignment correction method according to claim 1, wherein the filling comprises calculating a pixel distribution histogram in a range between the outside of the catheter and the lumen contour, and randomly selecting one of a plurality of pixel values having the highest frequency for filling.
7. The oct image misalignment correction method according to claim 1, further comprising performing boundary smoothing on the image after misalignment restoration, specifically comprising: in a manner thatAnd (4) traversing pixel points in the boundary range by taking +/-1 degrees as the boundary range, and carrying out median filtering by taking 5-5 pixels around the boundary point and eliminating the pixel points in the boundary range as masks.
8. The oct image misalignment correction method of claim 1, wherein the angle θ comprises 2 °.
9. The oct image misalignment correction method of claim 1, wherein the n ° includes 5 °.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110165934.0A CN112509095B (en) | 2021-02-07 | 2021-02-07 | Oct image dislocation correction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110165934.0A CN112509095B (en) | 2021-02-07 | 2021-02-07 | Oct image dislocation correction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112509095A true CN112509095A (en) | 2021-03-16 |
CN112509095B CN112509095B (en) | 2021-05-07 |
Family
ID=74953191
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110165934.0A Active CN112509095B (en) | 2021-02-07 | 2021-02-07 | Oct image dislocation correction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112509095B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113349737A (en) * | 2021-06-30 | 2021-09-07 | 深圳英美达医疗技术有限公司 | Method for calibrating OCT image of intravascular dual-mode imaging system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398935A (en) * | 2007-09-29 | 2009-04-01 | 上海西门子医疗器械有限公司 | Method for judging image dislocation |
CN104237167A (en) * | 2013-09-09 | 2014-12-24 | 深圳市斯尔顿科技有限公司 | Correction method and system for distortion of scanning device during OCT sectional image scanning |
US20150150447A1 (en) * | 2012-06-15 | 2015-06-04 | Oregon Health & Science University | Non-invasive 3d imaging and measuring of anterior chamber angle of the eye |
US20160360962A1 (en) * | 2015-06-11 | 2016-12-15 | Tomey Corporation | Anterior Ocular Segment Optical Coherence Tomographic Imaging Device and Anterior Ocular Segment Optical Coherence Tomographic Imaging Method |
CN110033496A (en) * | 2019-03-27 | 2019-07-19 | 江苏理工学院 | The motion artifact bearing calibration of time series three-dimensional retina SD-OCT image |
CN111461961A (en) * | 2020-03-27 | 2020-07-28 | 佛山科学技术学院 | OCT blood vessel image dislocation correction method |
-
2021
- 2021-02-07 CN CN202110165934.0A patent/CN112509095B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101398935A (en) * | 2007-09-29 | 2009-04-01 | 上海西门子医疗器械有限公司 | Method for judging image dislocation |
US20150150447A1 (en) * | 2012-06-15 | 2015-06-04 | Oregon Health & Science University | Non-invasive 3d imaging and measuring of anterior chamber angle of the eye |
CN104237167A (en) * | 2013-09-09 | 2014-12-24 | 深圳市斯尔顿科技有限公司 | Correction method and system for distortion of scanning device during OCT sectional image scanning |
US20160360962A1 (en) * | 2015-06-11 | 2016-12-15 | Tomey Corporation | Anterior Ocular Segment Optical Coherence Tomographic Imaging Device and Anterior Ocular Segment Optical Coherence Tomographic Imaging Method |
CN110033496A (en) * | 2019-03-27 | 2019-07-19 | 江苏理工学院 | The motion artifact bearing calibration of time series three-dimensional retina SD-OCT image |
CN111461961A (en) * | 2020-03-27 | 2020-07-28 | 佛山科学技术学院 | OCT blood vessel image dislocation correction method |
Non-Patent Citations (4)
Title |
---|
DAMIAN SIEDLECKI等: "Distortion Correction of OCT Images of the Crystalline Lens Gradient Index Approach", 《OPTOMETRY AND VISION SCIENCE》 * |
VASILY MATKIVSKY等: "Determination and correction of aberrations in full field OCT using phase gradient autofocus by maximizing the likelihood function", 《JOURNAL OF BIOPHOTONICS》 * |
张明蓉等: "OCT图像运动伪差校正算法的研究", 《中国医疗器械杂志》 * |
高振玉等: "基于C扫描的视盘OCT图像运动伪差校正算法的研究", 《中国医疗器械杂志》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113349737A (en) * | 2021-06-30 | 2021-09-07 | 深圳英美达医疗技术有限公司 | Method for calibrating OCT image of intravascular dual-mode imaging system |
CN113349737B (en) * | 2021-06-30 | 2023-05-26 | 深圳英美达医疗技术有限公司 | Calibration method of OCT (optical coherence tomography) image of intravascular dual-mode imaging system |
Also Published As
Publication number | Publication date |
---|---|
CN112509095B (en) | 2021-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9955951B2 (en) | Sensor coordinate calibration in an ultrasound system | |
CN102068281B (en) | Processing method for space-occupying lesion ultrasonic images | |
US7787673B2 (en) | Method and apparatus for airway detection and segmentation using 3D morphological operators | |
CN108537838B (en) | Detection method for hip joint bony acetabulum angle | |
CN108765388B (en) | Automatic segmentation method and system for esophageal endoscopic OCT (optical coherence tomography) image hierarchical structure | |
CN105488796A (en) | Lung segmentation method | |
CN109829942A (en) | A kind of automatic quantization method of eye fundus image retinal blood vessels caliber | |
Xu et al. | Alignment of 3-D optical coherence tomography scans to correct eye movement using a particle filtering | |
US20210272291A1 (en) | Method and computer program for segmentation of optical coherence tomography images of the retina | |
CN108257126A (en) | The blood vessel detection and method for registering, equipment and application of three-dimensional retina OCT image | |
CN112509095B (en) | Oct image dislocation correction method | |
US6748257B2 (en) | Detection of ribcage boundary from digital chest image | |
Artaechevarria et al. | Airway segmentation and analysis for the study of mouse models of lung disease using micro-CT | |
CN113012127A (en) | Cardiothoracic ratio measuring method based on chest medical image | |
JP4091318B2 (en) | X-ray CT system | |
CN111260673B (en) | Visceral organ parenchyma segmentation method and device suitable for edge-breaking visceral organ radiography | |
CN110033496B (en) | Motion artifact correction method for time sequence three-dimensional retina SD-OCT image | |
CN117274216A (en) | Ultrasonic carotid plaque detection method and system based on level set segmentation | |
CN116277978A (en) | Multimode bone joint digital 3D printing method | |
CN113012151B (en) | OCT (optical coherence tomography) image correction method and system for SS-OCT operation navigation system | |
Nakamura et al. | Automated segmentation and morphometric analysis of the human airway tree from multidetector CT images | |
Roy et al. | MDL-IWS: multi-view deep learning with iterative watershed for pulmonary fissure segmentation | |
CN114494177A (en) | IVOCT (in-vivo visual optical coherence tomography) branch blood vessel identification method by utilizing longitudinal section and withdrawal property | |
CN108269258B (en) | Method and system for segmenting corneal structures from OCT corneal images | |
CN112085711A (en) | Method for automatically tracking muscle pinnate angle by combining convolutional neural network and Kalman filtering |
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 |