CN110033442B - Vascular calcification area detection method and system based on analysis line extraction - Google Patents
Vascular calcification area detection method and system based on analysis line extraction Download PDFInfo
- Publication number
- CN110033442B CN110033442B CN201910256885.4A CN201910256885A CN110033442B CN 110033442 B CN110033442 B CN 110033442B CN 201910256885 A CN201910256885 A CN 201910256885A CN 110033442 B CN110033442 B CN 110033442B
- Authority
- CN
- China
- Prior art keywords
- curve
- gray value
- area
- blood vessel
- dimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a vascular calcification area detection method based on analysis line extraction, which comprises the following steps: obtaining a blood vessel straightening image and carrying out segmentation processing to obtain a blood vessel region image; counting the mean value of the gray values in the direction vertical to the blood vessels and generating a one-dimensional gray value curve; counting the mean value of the gray values along the blood vessel direction to generate a threshold curve; based on the threshold curve, dividing the area on the one-dimensional gray value curve into a dark area and a bright area, and respectively performing minimum value selection and maximum value selection on the dark area and the bright area to generate a new one-dimensional gray value curve; and performing large-window smoothing on the new one-dimensional gray value curve to detect a mutation region as a calcification candidate region. The invention also provides a vascular calcification area detection system based on analysis line extraction. The method can effectively detect the long-section calcified area on the blood vessel image, and effectively avoids the condition of missing detection.
Description
Technical Field
The invention relates to the technical field of coronary artery medical image processing, in particular to a vascular calcification area detection method based on analysis line extraction.
Background
The automatic coronary artery medical image detection has important clinical value and practical significance for doctors, and can feed back visual detection results for the doctors, so that the automatic coronary artery medical image detection can be used as reference for the doctors to diagnose the state of an illness, and the doctors are released from the tedious work of reading medical images, so that the diagnosis time of the doctors is shortened, the diagnosis efficiency is improved, and the problem of difficulty in medical treatment at present is solved.
The identification of calcified areas is an important part of automated coronary medical image detection, and calcifications are generally represented on medical images in a form that the brightness value of the calcifications is higher than that of peripheral blood vessels, so that most of the existing algorithms use dynamic thresholds for distinguishing and further identifying calcified areas. For the block calcified area, the detection effect is good, but for the case that the calcifications have a long period, the dynamic threshold method is difficult to obtain an accurate detection result.
Disclosure of Invention
In order to solve the problems, the invention provides a vascular calcification area detection method based on analysis line extraction.
The invention adopts the following technical scheme:
a vascular calcification area detection method based on analysis line extraction comprises the following steps:
s1, obtaining a blood vessel straightening image, and performing segmentation processing to obtain a blood vessel region image;
s2, counting the mean value of the gray values in the direction vertical to the blood vessels aiming at the blood vessel region image, and generating a one-dimensional gray value curve;
s3, counting the mean value of the gray values of the one-dimensional gray value curve along the blood vessel direction to generate a threshold value curve;
s4, dividing the area on the one-dimensional gray value curve into a dark area and a bright area based on a threshold curve, and respectively performing minimum value selection and maximum value selection on the dark area and the bright area to generate a new one-dimensional gray value curve;
and S5, performing large-window smoothing on the new one-dimensional gray value curve, and detecting a sudden change region as a calcification candidate region.
Preferably, the step S3 is specifically realized by the following method:
and dividing the one-dimensional gray value curve into a front section and a rear section along the blood vessel direction, respectively counting the gray value mean values of the front section and the rear section, and then generating the threshold curve through fitting.
Preferably, the step S4 is implemented by the following method:
and modifying the one-dimensional gray value curve, recording the value of a certain position of the one-dimensional gray value curve as a, recording the value of a corresponding position on a threshold curve as b, if a + a preset threshold > b, judging that the position belongs to the position on the bright area, replacing a with the maximum value of the position in the blood vessel area image in the direction vertical to the blood vessel, and if a < b, judging that the position belongs to the position on the dark area, replacing a with the minimum value of the position in the blood vessel area image in the direction vertical to the blood vessel, and finally generating a new one-dimensional gray value curve.
Preferably, the step S5 is implemented by the following sub-steps:
s51, performing large-window smoothing on the new one-dimensional gray value curve to generate a smooth curve;
s52, comparing the new one-dimensional gray value curve with the smooth curve, and detecting the mutation region as a calcification position;
and S53, outputting the calcification position, and taking the corresponding position on the blood vessel region image as a calcification candidate region.
A vascular calcification area detection system based on analysis line extraction comprises an acquisition module, a one-dimensional curve generation module, a threshold curve generation module, a one-dimensional curve adjustment module and a mutation area detection module, the acquisition module is used for acquiring a blood vessel straightening image and performing segmentation processing to obtain a blood vessel region image, the one-dimensional curve generation module is used for counting the mean value of the gray values in the direction vertical to the blood vessels and generating a one-dimensional gray value curve, the threshold curve generation module is used for counting the mean value of the gray values along the blood vessel direction and generating a threshold curve, the one-dimensional curve adjusting module is used for dividing the area on the one-dimensional gray value curve into a dark area and a bright area, respectively selecting and replacing the dark area and the bright area with a minimum value and a maximum value to generate a new one-dimensional gray value curve, and the abrupt change region detection module smoothly detects an abrupt change region on a new one-dimensional gray value curve through a large window to serve as a calcification candidate region.
Preferably, the abrupt change region detection module includes a large window smoothing submodule, a comparison submodule and a conversion submodule, the large window smoothing submodule is configured to perform large window smoothing on a new one-dimensional gray value curve and generate a smooth curve, the comparison submodule is configured to compare the new one-dimensional gray value curve with the smooth curve and detect an abrupt change region as a calcification position, and the conversion submodule is configured to output the calcification position and use a corresponding position on the blood vessel region image as a calcification candidate region.
After adopting the technical scheme, compared with the background technology, the invention has the following advantages:
the invention converts the blood vessel image into a one-dimensional gray value curve for analysis, divides a dark area and a bright area by using a threshold value curve, selects a minimum value and a maximum value, smoothes through a large window, and detects a mutation area on the curve as a calcification candidate area. The method can effectively detect the long-section calcified area on the blood vessel image, and effectively avoids the condition of missing detection.
Drawings
FIG. 1 is a schematic flow chart of 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. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example one
Referring to fig. 1, the invention discloses a vascular calcification area detection method based on analysis line extraction, comprising the following steps:
and S1, acquiring a blood vessel straightening image, and performing segmentation processing to obtain a blood vessel region image.
And S2, counting the mean value of the gray values in the direction vertical to the blood vessels aiming at the blood vessel region image, and generating a one-dimensional gray value curve.
And S3, counting the gray value mean value of the one-dimensional gray value curve along the blood vessel direction to generate a threshold value curve. In this embodiment, the generation manner of the threshold curve is specifically as follows: dividing the one-dimensional gray value curve into a front section and a rear section along the blood vessel direction, respectively counting the gray value mean values of the front section and the rear section, and then generating a threshold value curve through fitting.
And S4, dividing the area on the one-dimensional gray value curve into a dark area and a bright area based on the threshold curve, and respectively performing minimum value selection and maximum value selection on the dark area and the bright area to generate a new one-dimensional gray value curve. The steps are realized by the following method: and modifying the one-dimensional gray value curve, recording the value of a certain position of the one-dimensional gray value curve as a, recording the value of a corresponding position on the threshold curve as b, if a + a preset threshold > b, judging that the position belongs to the position on a bright area, replacing a with the maximum value of the position in the blood vessel direction on the blood vessel area image, and if a < b, judging that the position belongs to the position on the dark area, replacing a with the minimum value of the position in the blood vessel direction on the blood vessel area image, and finally generating a new one-dimensional gray value curve.
And S5, performing large-window smoothing on the new one-dimensional gray value curve, and detecting a sudden change region as a calcification candidate region. The method comprises the following steps:
and S51, performing large-window smoothing on the new one-dimensional gray value curve to generate a smooth curve.
And S52, comparing the new one-dimensional gray value curve with the smooth curve, and detecting the mutation region as the calcification position. Specifically, if there is a large difference between the new one-dimensional gray scale value curve and the smooth curve at a certain position, and the value a of the new one-dimensional gray scale value curve at the certain position is greater than the sum of the value b on the threshold curve and the preset threshold, the certain position is a calcified position.
And S53, outputting the calcification position, and taking the corresponding position on the blood vessel region image as a calcification candidate region.
Example two
The utility model provides a vascular calcification regional detecting system based on analysis line draws, includes and acquires module, one-dimensional curve generation module, threshold value curve generation module, one-dimensional curve adjustment module and sudden change regional detection module, wherein:
the acquisition module is used for acquiring the blood vessel straightening image and performing segmentation processing to obtain a blood vessel region image.
The one-dimensional curve generation module is used for counting the mean value of the gray values in the direction perpendicular to the blood vessels and generating a one-dimensional gray value curve.
The threshold curve generation module is used for counting the mean value of the gray values along the blood vessel direction and generating a threshold curve.
The one-dimensional curve adjusting module is used for dividing the area on the one-dimensional gray value curve into a dark area and a bright area, and respectively selecting and replacing a minimum value and a maximum value for the dark area and the bright area to generate a new one-dimensional gray value curve.
And the abrupt change region detection module is used for smoothly detecting an abrupt change region on the new one-dimensional gray value curve through a large window to serve as a calcification candidate region. The abrupt change region detection module comprises a large window smoothing submodule, a comparison submodule and a conversion submodule, wherein the large window smoothing submodule is used for performing large window smoothing on a new one-dimensional gray value curve to generate a smooth curve, the comparison submodule is used for comparing the new one-dimensional gray value curve with the smooth curve to detect that an abrupt change region is a calcification position, and the conversion submodule is used for outputting the calcification position and taking a corresponding position on a blood vessel region image as a calcification candidate region.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. A vascular calcification area detection method based on analysis line extraction is characterized by comprising the following steps:
s1, obtaining a blood vessel straightening image, and performing segmentation processing to obtain a blood vessel region image;
s2, counting the mean value of the gray values in the direction vertical to the blood vessels aiming at the blood vessel region image, and generating a one-dimensional gray value curve;
s3, counting the mean value of the gray values of the one-dimensional gray value curve along the blood vessel direction to generate a threshold value curve;
s4, dividing the area on the one-dimensional gray value curve into a dark area and a bright area based on a threshold curve, and respectively performing minimum value selection and maximum value selection on the dark area and the bright area to generate a new one-dimensional gray value curve;
and S5, performing large-window smoothing on the new one-dimensional gray value curve, and detecting a sudden change region as a calcification candidate region.
2. The method for detecting calcified vascular regions based on analysis line extraction as claimed in claim 1, wherein the step S3 is specifically realized by the following steps:
and dividing the one-dimensional gray value curve into a front section and a rear section along the blood vessel direction, respectively counting the gray value mean values of the front section and the rear section, and then generating the threshold curve through fitting.
3. The method for detecting calcified vascular regions based on analysis line extraction as claimed in claim 1, wherein said step S5 is implemented by the following sub-steps:
s51, performing large-window smoothing on the new one-dimensional gray value curve to generate a smooth curve;
s52, comparing the new one-dimensional gray value curve with the smooth curve, and detecting the mutation region as a calcification position;
and S53, outputting the calcification position, and taking the corresponding position on the blood vessel region image as a calcification candidate region.
4. A vascular calcification area detection system based on analysis line extraction is characterized in that; comprises an acquisition module, a one-dimensional curve generation module, a threshold curve generation module, a one-dimensional curve adjustment module and a mutation region detection module, the acquisition module is used for acquiring a blood vessel straightening image and performing segmentation processing to obtain a blood vessel region image, the one-dimensional curve generation module is used for counting the mean value of the gray values in the direction vertical to the blood vessels and generating a one-dimensional gray value curve, the threshold curve generating module is used for counting the gray value mean value of the one-dimensional gray value curve along the blood vessel direction and generating a threshold curve, the one-dimensional curve adjusting module is used for dividing the area on the one-dimensional gray value curve into a dark area and a bright area, respectively selecting and replacing the dark area and the bright area with a minimum value and a maximum value to generate a new one-dimensional gray value curve, and the abrupt change region detection module smoothly detects an abrupt change region on a new one-dimensional gray value curve through a large window to serve as a calcification candidate region.
5. The vascular calcification area detecting system as recited in claim 4, wherein: the abrupt change region detection module comprises a large window smoothing submodule, a comparison submodule and a conversion submodule, wherein the large window smoothing submodule is used for performing large window smoothing on a new one-dimensional gray value curve and generating a smooth curve, the comparison submodule is used for comparing the new one-dimensional gray value curve with the smooth curve and detecting an abrupt change region as a calcification position, and the conversion submodule is used for outputting the calcification position and taking a corresponding position on the blood vessel region image as a calcification candidate region.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910256885.4A CN110033442B (en) | 2019-04-01 | 2019-04-01 | Vascular calcification area detection method and system based on analysis line extraction |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910256885.4A CN110033442B (en) | 2019-04-01 | 2019-04-01 | Vascular calcification area detection method and system based on analysis line extraction |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110033442A CN110033442A (en) | 2019-07-19 |
CN110033442B true CN110033442B (en) | 2020-12-25 |
Family
ID=67237179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910256885.4A Active CN110033442B (en) | 2019-04-01 | 2019-04-01 | Vascular calcification area detection method and system based on analysis line extraction |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110033442B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105380682A (en) * | 2015-12-24 | 2016-03-09 | 飞依诺科技(苏州)有限公司 | Bilateral intima-media membrane measuring method and system based on ultrasonic images |
CN106372654A (en) * | 2016-08-29 | 2017-02-01 | 滕忠照 | Method for assessing cerebral infarction risk caused by head and neck atherosclerosis plaques |
CN108765363A (en) * | 2018-03-24 | 2018-11-06 | 语坤(北京)网络科技有限公司 | A kind of automatic after-treatment systems of coronary artery CTA based on artificial intelligence |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7993274B2 (en) * | 2006-11-22 | 2011-08-09 | General Electric Company | Method, system, and computer product for automatically extracting and tracking cardiac calcifications and determining a tracking centerline |
US8750615B2 (en) * | 2010-08-02 | 2014-06-10 | Case Western Reserve University | Segmentation and quantification for intravascular optical coherence tomography images |
CN108257196A (en) * | 2018-01-11 | 2018-07-06 | 苏州润心医疗器械有限公司 | A kind of blood vessel based on cardiac CT image stretches method for reconstructing |
CN108171698B (en) * | 2018-02-12 | 2020-06-09 | 数坤(北京)网络科技有限公司 | Method for automatically detecting human heart coronary calcified plaque |
CN108805815B (en) * | 2018-06-14 | 2023-02-17 | 苏州润迈德医疗科技有限公司 | Blood vessel straightening reconstruction method based on X-ray angiography image |
-
2019
- 2019-04-01 CN CN201910256885.4A patent/CN110033442B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105380682A (en) * | 2015-12-24 | 2016-03-09 | 飞依诺科技(苏州)有限公司 | Bilateral intima-media membrane measuring method and system based on ultrasonic images |
CN106372654A (en) * | 2016-08-29 | 2017-02-01 | 滕忠照 | Method for assessing cerebral infarction risk caused by head and neck atherosclerosis plaques |
CN108765363A (en) * | 2018-03-24 | 2018-11-06 | 语坤(北京)网络科技有限公司 | A kind of automatic after-treatment systems of coronary artery CTA based on artificial intelligence |
Also Published As
Publication number | Publication date |
---|---|
CN110033442A (en) | 2019-07-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Scales et al. | Automated image segmentation for breast analysis using infrared images | |
EP2658439B1 (en) | Automatic left ventricular function evaluation | |
CN108932714B (en) | Plaque classification method of coronary artery CT image | |
CN111667456B (en) | Method and device for detecting vascular stenosis in coronary artery X-ray sequence radiography | |
US20110103674A1 (en) | Marker detection in x-ray images | |
AU2015284524A1 (en) | Detecting tooth wear using intra-oral 3D scans | |
CN103260526A (en) | Ultrasound imaging system and method with peak intensity detection | |
CN110047086B (en) | Automatic carotid intimal thickness measuring method and system | |
CN106659480B (en) | Ultrasonic diagnosis video generation device and method | |
WO2011008906A1 (en) | Computer-aided detection (cad) of intracranial aneurysms | |
WO2011066689A1 (en) | Method and device for detecting bright brain regions from computed tomography images | |
CN106875387B (en) | Automatic detection method and device of biodegradable stent based on OCT image | |
KR101111055B1 (en) | Method for Automatic Breast Density Measurement on Digital Mammogram | |
CN110517264B (en) | Nidus extraction method and device based on blood vessel segmentation | |
CN101425140A (en) | Encephalic angioma image recognizing and detecting method based on framework characteristic | |
CN115546232A (en) | Liver ultrasonic image working area extraction method and system and electronic equipment | |
CN109948622B (en) | Method and device for detecting head and neck body aneurysm and computer readable storage medium | |
CN110033442B (en) | Vascular calcification area detection method and system based on analysis line extraction | |
US8204289B2 (en) | System for identifying medical images having a particular medical characteristic | |
CN109846465B (en) | Vascular calcification false alarm detection method based on brightness analysis | |
Medhi et al. | Automatic detection of fovea using property of vessel free region | |
CN112785580B (en) | Method and device for determining vascular flow velocity | |
CN110021016B (en) | Calcification detection method | |
CN114663443A (en) | 12-lead paper electrocardiogram digitization method and device | |
CN110009616B (en) | Punctate calcification detection method |
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 | ||
CP03 | Change of name, title or address |
Address after: 100120 rooms 303, 304, 305, 321 and 322, building 3, No. 11, Chuangxin Road, science and Technology Park, Changping District, Beijing Patentee after: Shukun (Beijing) Network Technology Co.,Ltd. Address before: Unit 547, unit 1, building 1, yard 1, Longyu middle street, Huilongguan town, Changping District, Beijing Patentee before: SHUKUN (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |
|
CP03 | Change of name, title or address |