CN116152253A - Cardiac magnetic resonance mapping quantification method, system and storage medium - Google Patents
Cardiac magnetic resonance mapping quantification method, system and storage medium Download PDFInfo
- Publication number
- CN116152253A CN116152253A CN202310428761.6A CN202310428761A CN116152253A CN 116152253 A CN116152253 A CN 116152253A CN 202310428761 A CN202310428761 A CN 202310428761A CN 116152253 A CN116152253 A CN 116152253A
- Authority
- CN
- China
- Prior art keywords
- magnetic resonance
- image
- layer
- mapping
- cardiac
- 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
- 238000013507 mapping Methods 0.000 title claims abstract description 47
- 230000000747 cardiac effect Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000011002 quantification Methods 0.000 title claims description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 31
- 230000002861 ventricular Effects 0.000 claims abstract description 16
- 210000005240 left ventricle Anatomy 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 210000004165 myocardium Anatomy 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims description 27
- 238000003780 insertion Methods 0.000 claims description 11
- 230000037431 insertion Effects 0.000 claims description 11
- 230000005484 gravity Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 210000005241 right ventricle Anatomy 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 6
- 230000008439 repair process Effects 0.000 claims description 6
- 238000004040 coloring Methods 0.000 claims description 4
- 210000001174 endocardium Anatomy 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 210000001519 tissue Anatomy 0.000 description 6
- 230000002107 myocardial effect Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 230000003902 lesion Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012805 post-processing Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 206010000060 Abdominal distension Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 208000024330 bloating Diseases 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000009141 biological interaction Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010399 physical interaction Effects 0.000 description 1
- 230000001766 physiological effect Effects 0.000 description 1
- 238000011045 prefiltration Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 210000000596 ventricular septum Anatomy 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000011179 visual inspection 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
- G06T7/0002—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
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/30048—Heart; Cardiac
-
- 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
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Image Processing (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention belongs to the technical field of medical image processing, and particularly relates to a method, a system and a storage medium for quantifying cardiac magnetic resonance mapping. The method comprises the following steps: step 1, inputting original data of a heart magnetic resonance mapping image, respectively acquiring original images of a left ventricular basal layer, a middle layer and a cardiac apex layer, and executing subsequent steps on at least one layer of the original images of the basal layer, the middle layer and the cardiac apex layer; step 2, preprocessing the original image, and determining a general target area of left ventricle cardiac muscle based on contour recognition; step 3, obtaining an accurate target area of the segmentation target through connected domain analysis; step 4, segmenting left ventricular myocardium based on the accurate target region; and 5, calculating the average value of the original image pixels of each segmented region. The invention further provides a system for realizing the method. The method has high accuracy and repeatability of the quantized result and good application prospect.
Description
Technical Field
The invention belongs to the technical field of medical image processing, and particularly relates to a method, a system and a storage medium for quantifying cardiac magnetic resonance mapping.
Background
In recent years, the application of cardiac magnetic resonance mapping techniques in clinical environments has steadily increased, mapping being the quantification of one or more magnetic resonance contrast driving factors (i.e. relaxation times) in each pixel of an image. These relaxation times or relaxation parameters are quantifiable properties of the tissue in a magnetic field and are strongly dependent on the physiological properties of the tissue. Because mapping images are no longer dependent on some specific scan parameters (e.g., radio frequency coil proximity, receiver chain efficiency, or magnetic field inhomogeneity), this makes mapping imaging a great advantage over qualitative imaging. The quantified relaxation time also reduces inter-observer variability, allows for dynamic tracking of tissue parameters of patients, and allows for comparison of tissue parameters between individual patients. These mapping images rely solely on physical and biological interactions and are therefore highly reproducible in theory.
According to the standard post-processing guidelines for cardiac magnetic resonance images published by the international cardiac magnetic resonance society (Society for Cardiovascular Magnetic Resonance, SCMR) in 2020, the existing post-processing analysis methods of mapping images include visual analysis and manual quantitative analysis, no specific recommended or preferred post-processing software package exists at present, and an analyst should receive training of local standard or selected post-processing software package. Visual analysis, i.e. visual inspection of the general image, aims at detecting image artifacts and verifying the diagnostic image quality, but does not allow to obtain quantitative data from the mapping image. In manual quantitative analysis, guidelines recommend a conservative delineation of a region of interest at the ventricular septum of the mid-layer short axis layer at the time of measuring global or diffuse myocardial lesions to reduce the effects of magnetically sensitive artifacts from adjacent tissues. To accurately assess diffuse disease, focal lesions should be excluded from the region of interest of the mapping image. For focal lesions, it is recommended to delineate additional regions of interest outside the abnormal region found by visual analysis, while the region of interest range <20 pixels should be avoided. In actual clinical applications and studies, doctors (researchers) often divide the left ventricular myocardium into 16 segments according to the american heart association (American Heart Association, AHA) -16 segment division method, and measure the average of the whole or segment myocardium in mapping images.
The above-mentioned post-processing method of the existing cardiac magnetic resonance image mainly has the following problems: the mapping image needs to be imported into a special commercial software package for cardiac imaging, then the inner/outer membrane of the left ventricle and/or the region of interest are manually sketched, the measurement method is long in time consumption, certain difference among observers exists, and the measured data also needs to be manually output, so that the clinical application and popularization of the technology are greatly limited. These problems are effectively solved if the above-described segmentation and quantization processes can be automatically implemented in computer software. However, due to the specificity of cardiac anatomy and interference of image background noise (especially myotrabeculae, pericardial tissue in close proximity to the endocardium/epicardium), automatic identification of the contours of the target region in the cardiac magnetic resonance mapping image (e.g., left ventricular endocardial/epicardium, right ventricular insertion) is still not accurate enough, and there is currently a lack of related research on how to implement accurate full-automatic processing of cardiac magnetic resonance mapping images, there is still a need in the art to develop a method and system capable of automatically segmenting and quantifying cardiac magnetic resonance mapping images using a computer.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method, a system and a storage medium for quantifying a cardiac magnetic resonance mapping image, which realize the purpose of automatically segmenting and quantifying the cardiac magnetic resonance mapping image by using a computer.
A method for quantifying cardiac magnetic resonance, comprising the steps of:
step 1, inputting original data of a heart magnetic resonance mapping image, respectively acquiring original images of a basal layer, a middle layer and a cardiac apex layer, and executing subsequent steps on at least one of the original images of the basal layer, the middle layer and the cardiac apex layer;
step 2, preprocessing the original image, and determining a general target area of left ventricle cardiac muscle based on contour recognition;
step 3, obtaining an accurate target area of the segmentation target through connected domain analysis;
step 4, segmenting based on the accurate target area;
and 5, calculating the average value of the original image pixels of each segmented region.
Preferably, the format of the original data is a DICOM file.
Preferably, step 2 specifically includes:
step 2.1, converting the original image into a gray scale image;
step 2.2, filtering background noise and foreground noise;
step 2.3, drawing a reference circle with the radius of 1/4 width by using the center point of the image;
step 2.4, detecting the outline of the whole image, traversing the detected outline, and determining that the outline with the center of gravity in the reference circle is an alternative outline;
step 2.5, obtaining an alternative contour with the largest area as a target contour;
step 2.6, drawing extreme points of the target contour;
and 2.7, acquiring the approximate target area according to the extreme point.
Preferably, step 2.2 specifically includes:
step 2.2.1, filtering background noise through threshold analysis and median filtering;
step 2.2.2, filtering background noise through connected domain analysis;
step 2.2.3, inverting the image, analyzing and filtering the image through a connected domain to Jing Zaoyin;
step 2.2.4, performing image inversion again;
the approximate target area is rectangular in shape; step 2.7 specifically includes:
step 2.7.1, taking the extreme left point as the center point c (x 0 , y 0 )；
And 2.7.2, calculating an upper left point and a lower right point of the approximate target area by taking half of the vertical distance between the upper point and the lower point as a reference value d, wherein the calculation formula is as follows:
upper left dot coordinates: lt (x) 1 , y 1 ) = (x 0 - 0.5*d, y 0 - 0.8*d)；
Lower right dot coordinates: rb (x) 2 , y 2 ) = (x 0 + r, y 0 + 0.8*d)；
Step 2.7.3, the approximate target area is rendered.
Preferably, step 3 specifically includes:
step 3.1, preprocessing through threshold analysis;
step 3.2, removing the connected domain with small area through connected domain analysis, and leaving at least 3 connected domains as candidate regions;
step 3.3, positioning the left ventricle through contour detection;
step 3.4, positioning the front insertion part of the right ventricle by adopting a convex hull algorithm;
step 3.5, performing image inversion;
step 3.6, filtering background noise through at least one method of threshold analysis, median filtering, corrosion and expansion;
and 3.7, obtaining a connected domain with the largest area as the accurate target area through connected domain analysis.
Preferably, step 4 specifically includes:
step 4.1, performing contour repair on the endocardium and epicardium of the left ventricle, wherein the contour repair method comprises the following steps: filling faults through morphological operation, and deleting bloated;
step 4.2, drawing an epicardial contour ring;
step 4.3, drawing a star-shaped scattered ray uniform segmentation contour ring based on the center of gravity of the left ventricular chamber and the front insertion part of the right ventricle;
step 4.4, performing corrosion operation on each segmented region;
step 4.5, starting from the right ventricular anterior insertion, numbering the center of gravity of each segment of the region in a clockwise direction.
Preferably, in step 4, the original image of the basal layer or the middle layer is divided into 6 segments, and the original image of the apical layer is divided into 4 segments.
Preferably, step 5 specifically includes:
step 5.1, obtaining all pixel points of each section of area after segmentation, and coloring each section of area by using different colors;
step 5.2, mapping the coordinate position of each pixel point to the original image to obtain a pixel value;
and 5.3, calculating the pixel average value of each section of area according to the pixel value of the original image of each section of area.
The invention also provides a heart magnetic resonance mapping image quantification system, which comprises:
the input module is used for inputting the original data of the heart magnetic resonance mapping image;
the calculation module is used for processing the original data according to the heart magnetic resonance mapping image quantification method;
and the output module is used for outputting the processing result of the calculation module.
The present invention also provides a computer-readable storage medium having stored thereon: a computer program for implementing the above-mentioned cardiac magnetic resonance mapping quantification method.
The invention designs the flow of the automatic quantification method of the heart magnetic resonance mapping image for the first time, and can realize the purpose of automatically processing the heart magnetic resonance mapping image by using a computer. The problem of long time consumption caused by the fact that the current myocardial mapping image quantitative measurement needs to manually delineate the endocardial/epicardial of the left ventricle and manually position an inter-ventricular inserting part is solved, and full automation of measurement is realized; the operation is simple and quick, the reliability and the repeatability of the obtained result are high, and the problem of large difference of manual measurement data caused by different proficiency of analysts is solved. Therefore, the invention has good application prospect.
It should be apparent that, in light of the foregoing, various modifications, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
The above-described aspects of the present invention will be described in further detail below with reference to specific embodiments in the form of examples. It should not be understood that the scope of the above subject matter of the present invention is limited to the following examples only. All techniques implemented based on the above description of the invention are within the scope of the invention.
Drawings
Fig. 1 is a schematic flow chart of acquiring a rough target area in embodiment 1 of the present invention.
Fig. 2 is a flow chart of acquiring a precise target area in embodiment 1 of the present invention.
Fig. 3 is a flow chart of contour segmentation and data extraction in embodiment 1 of the present invention.
Fig. 4 is a preprocessing step of an original image. A. DICOM image gray scale; B. filtering background noise through threshold analysis and median filtering; C. filtering background noise through connected domain analysis; D. and after the image is inverted, the foreground noise is filtered through connected domain analysis. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 5 is a view of acquiring a rough target area according to an extreme point. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 6 is an illustration of acquisition of candidate regions based on connected domain analysis. A. Inverting the image; B. removing the small-area connected domain; C. an alternative region is acquired. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 7 is a diagram of the positioning of the anterior insertion portion of the right ventricle using a convex hull algorithm. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 8 is a diagram of filtering background noise. A. Filtering the background noise by median filtering; C. filtering background noise by corrosion; D. the background noise is filtered by dilation. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 9 is a view of acquiring a maximum area connected domain as a precise target area. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 10 illustrates contour patching of a target area. A. Filling faults; B. removing bloating; C. the left ventricular myocardium contour ring is drawn. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 11 is a segmented left ventricular myocardial contour ring. A. Drawing star-shaped scattered rays; B. dividing the contour ring; C. and acquiring the gravity center of each section of region. In the figure, the units of the abscissa and the ordinate are pixels.
Fig. 12 is a view of capturing and coloring pixel points of each segment of region. In the figure, the units of the abscissa and the ordinate are pixels.
Detailed Description
It should be noted that, in the embodiments, algorithms of steps such as data acquisition, transmission, storage, and processing, which are not specifically described, and hardware structures, circuit connections, and the like, which are not specifically described may be implemented through the disclosure of the prior art.
Example 1 cardiac magnetic resonance mapping image quantification method and System
The present embodiment provides a system for automatically segmenting and quantifying cardiac magnetic resonance mapping images, the system comprising:
the input module is used for inputting the original data of the heart magnetic resonance mapping image;
the computing module is used for processing the original data by a heart magnetic resonance mapping image quantification method;
and the output module is used for outputting the processing result of the calculation module.
The workflow of the algorithm in the computing module is shown in fig. 1-3, and fig. 4-12 illustrate an exemplary operation with a DICOM file for a set of myocardium T1 mapping, and specifically includes the following steps:
step 1, inputting original data of a heart magnetic resonance mapping image, respectively acquiring original images of a basal layer, a middle layer and a cardiac apex layer, and respectively executing subsequent steps on the original images of the basal layer, the middle layer and the cardiac apex layer; in the subsequent step, the original image of the basal layer or the middle layer is divided into 6 segments, and the original image of the apical layer is divided into 4 segments;
specific:
step 1.1, the raw data of a set of cardiac magnetic resonance mapping images to be measured (in this embodiment, a set of cardiac muscle T1 mapping images) are exported in DICOM form and classified into a folder, which includes three DICOM files of basal layer, middle layer and apex layer.
Step 1.2, reading the Slice Location of each DICOM file by using the pydicom library, and sorting each DICOM file in reverse order by the Slice Location, so as to determine the position (i.e. basal layer, middle layer and apex layer) of each DICOM.
Step 2, preprocessing the original image, and determining a general target area of left ventricle cardiac muscle based on contour recognition; the approximate target area is rectangular in shape;
specific:
step 2.1, converting the original image into a gray scale image;
step 2.2, filtering background noise and foreground noise;
step 2.2 specifically comprises:
step 2.2.1, filtering background noise through threshold analysis and median filtering (figure 4);
step 2.2.2, filtering background noise by connected domain analysis (fig. 4);
step 2.2.3, image inversion, pre-filtration Jing Zaoyin by connected domain analysis (fig. 4);
step 2.2.4, performing image inversion again;
step 2.3, drawing a reference circle with the radius of 1/4 width by using the center point of the image;
step 2.4, detecting the outline of the whole image, traversing the detected outline, and determining that the outline with the center of gravity in the reference circle is an alternative outline;
step 2.5, obtaining an alternative contour with the largest area as a target contour;
step 2.6, drawing extreme points of the target contour;
step 2.7, obtaining the approximate target area according to the extreme points (fig. 5);
step 2.7 specifically includes:
step 2.7.1, taking the extreme left point as the center point c (x 0 , y 0 )；
And 2.7.2, calculating an upper left point and a lower right point of the approximate target area by taking half of the vertical distance between the upper point and the lower point as a reference value d, wherein the calculation formula is as follows:
upper left dot coordinates: lt (x) 1 , y 1 ) = (x 0 - 0.5*d, y 0 - 0.8*d)；
Lower right dot coordinates: rb (x) 2 , y 2 ) = (x 0 + r, y 0 + 0.8*d)；
Step 2.7.3, the approximate target area is rendered.
Step 3, obtaining an accurate target area of the segmentation target through connected domain analysis;
specific:
step 3.1, preprocessing through threshold analysis;
step 3.2, removing the connected domain with small area through connected domain analysis, and leaving at least 3 connected domains as candidate regions (fig. 6);
step 3.3, positioning the left ventricle through contour detection; specific: acquiring the profiles of the first 3 connected domains with the largest area in the alternative area, and then positioning the left ventricle through the extreme lower point and the extreme left point of the connected domains;
step 3.4, positioning the right ventricle front insertion part by adopting a convex hull algorithm (fig. 7);
step 3.5, performing image inversion;
step 3.6, filtering background noise through threshold analysis, median filtering, erosion and dilation (fig. 8);
and step 3.7, acquiring a connected domain with the largest area as the precise target area through connected domain analysis (figure 9).
Step 4, segmenting based on the accurate target area;
specific:
step 4.1, performing contour repair on the endocardium and epicardium of the left ventricle, wherein the contour repair method comprises the following steps: filling the fault by morphological operations, deleting the bloating (fig. 10);
step 4.2, drawing a left ventricular myocardial contour ring (figure 10);
step 4.3, drawing a star-shaped scattered ray uniform segmentation contour ring based on the center of gravity of the left ventricular chamber and the front insertion part of the right ventricle (figure 11);
step 4.4, performing corrosion operation on each segmented region;
step 4.5, starting from the right ventricular anterior insertion, numbering the center of gravity of each segment of the region in a clockwise direction.
And 5, calculating the average value of the original image pixels of each segmented region.
Specific:
step 5.1, obtaining all pixel points of each segmented area after segmentation, and coloring each segmented area with different colors (fig. 12);
step 5.2, mapping the coordinate position of each pixel point to the original image to obtain a pixel value;
and 5.3, calculating the pixel average value of each section of area according to the pixel value of the original image of each section of area.
Taking 50 healthy people (150 DICOM original images in total) as an example for verification, the success rate of accurately identifying the target area reaches 91.3%.
The method can realize the purpose of automatically processing the heart magnetic resonance mapping image by using a computer, has the advantages of extremely high accuracy and high repeatability and reduces the workload of doctors, and has good application prospect.
Claims (10)
1. The heart magnetic resonance mapping quantification method is characterized by comprising the following steps of:
step 1, inputting original data of a heart magnetic resonance mapping image, respectively acquiring original images of a left ventricular basal layer, a middle layer and a cardiac apex layer, and executing subsequent steps on at least one layer of the original images of the basal layer, the middle layer and the cardiac apex layer;
step 2, preprocessing the original image, and determining a general target area of left ventricle cardiac muscle based on contour recognition;
step 3, obtaining an accurate target area of the segmentation target through connected domain analysis;
step 4, segmenting based on the accurate target area;
and 5, calculating the average value of the original image pixels of each segmented region.
2. The method for quantifying cardiac magnetic resonance according to claim 1, wherein the raw data is in the form of a DICOM file.
3. The method for quantifying cardiac magnetic resonance according to claim 1, wherein step 2 specifically comprises:
step 2.1, converting the original image into a gray scale image;
step 2.2, filtering background noise and foreground noise;
step 2.3, drawing a reference circle with the radius of 1/4 width by using the center point of the image;
step 2.4, detecting the outline of the whole image, traversing the detected outline, and determining that the outline with the center of gravity in the reference circle is an alternative outline;
step 2.5, obtaining an alternative contour with the largest area as a target contour;
step 2.6, drawing extreme points of the target contour;
and 2.7, acquiring the approximate target area according to the extreme point.
4. A method of quantifying cardiac magnetic resonance as claimed in claim 3, wherein step 2.2 comprises:
step 2.2.1, filtering background noise through threshold analysis and median filtering;
step 2.2.2, filtering background noise through connected domain analysis;
step 2.2.3, inverting the image, analyzing and filtering the image through a connected domain to Jing Zaoyin;
step 2.2.4, performing image inversion again;
the approximate target area is rectangular in shape; step 2.7 specifically includes:
step 2.7.1, taking the extreme left point as the center point c (x 0 , y 0 )；
And 2.7.2, calculating an upper left point and a lower right point of the approximate target area by taking half of the vertical distance between the upper point and the lower point as a reference value d, wherein the calculation formula is as follows:
upper left dot coordinates: lt (x) 1 , y 1 ) = (x 0 - 0.5*d, y 0 - 0.8*d)；
Lower right dot coordinates: rb (x) 2 , y 2 ) = (x 0 + r, y 0 + 0.8*d)；
Step 2.7.3, the approximate target area is rendered.
5. The method for quantifying cardiac magnetic resonance according to claim 1, wherein step 3 specifically comprises:
step 3.1, preprocessing through threshold analysis;
step 3.2, removing the connected domain with small area through connected domain analysis, and leaving at least 3 connected domains as candidate regions;
step 3.3, positioning the left ventricle through contour detection;
step 3.4, positioning the front insertion part of the right ventricle by adopting a convex hull algorithm;
step 3.5, performing image inversion;
step 3.6, filtering background noise by at least one method of threshold analysis, median filtering and corrosion expansion;
and 3.7, obtaining a connected domain with the largest area as the accurate target area through connected domain analysis.
6. The method for quantifying cardiac magnetic resonance according to claim 1, wherein step 4 specifically comprises:
step 4.1, performing contour repair on endocardium and epicardium of the left ventricle, wherein the contour repair method comprises the following steps: filling faults through morphological operation, and deleting bloated;
step 4.2, drawing a contour ring of the left ventricular myocardium;
step 4.3, drawing a star-shaped scattered ray uniform segmentation contour ring based on the center of gravity of the left ventricular chamber and the front insertion part of the right ventricle;
step 4.4, performing corrosion operation on each segmented region;
step 4.5, starting from the right ventricular anterior insertion, numbering the center of gravity of each segment of the region in a clockwise direction.
7. The method for quantifying cardiac magnetic resonance mapping according to claim 1, wherein: in step 4, the original image of the basal layer or the middle layer is subjected to 6-segment division, and the original image of the apical layer is subjected to 4-segment division.
8. The method for quantifying cardiac magnetic resonance according to claim 1, wherein step 5 specifically comprises:
step 5.1, obtaining all pixel points of each section of area after segmentation, and coloring each section of area by using different colors;
step 5.2, mapping the coordinate position of each pixel point to the original image to obtain a pixel value;
and 5.3, calculating the pixel average value of each section of area according to the pixel value of the original image of each section of area.
9. A cardiac magnetic resonance mapping quantification system, comprising:
the input module is used for inputting the original data of the heart magnetic resonance mapping image;
a calculation module for processing the raw data according to the cardiac magnetic resonance mapping quantification method of any of claims 1-8;
and the output module is used for outputting the processing result of the calculation module.
10. A computer-readable storage medium having stored thereon: computer program for implementing a cardiac magnetic resonance mapping quantification method according to any of the claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310428761.6A CN116152253B (en) | 2023-04-20 | 2023-04-20 | Cardiac magnetic resonance mapping quantification method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310428761.6A CN116152253B (en) | 2023-04-20 | 2023-04-20 | Cardiac magnetic resonance mapping quantification method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116152253A true CN116152253A (en) | 2023-05-23 |
| CN116152253B CN116152253B (en) | 2023-06-16 |
Family
ID=86360398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310428761.6A Active CN116152253B (en) | 2023-04-20 | 2023-04-20 | Cardiac magnetic resonance mapping quantification method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116152253B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236062A (en) * | 2013-05-03 | 2013-08-07 | 北京国铁华晨通信信息技术有限公司 | Magnetic resonance imaging blood vessel segmentation method and system based on human brain tumor nuclear magnetic library |
| CN104680127A (en) * | 2014-12-18 | 2015-06-03 | 闻泰通讯股份有限公司 | Gesture identification method and gesture identification system |
| US20160110879A1 (en) * | 2014-10-18 | 2016-04-21 | International Business Machines Corporation | Automatic Visualization of Regional Functional Parameters of Left Ventricle from Cardiac Imaging |
| CN105956587A (en) * | 2016-04-20 | 2016-09-21 | 哈尔滨工业大学 | Method for automatically extracting meniscus from knee-joint magnetic resonance image sequence based on shape constraint |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
| US20170178285A1 (en) * | 2015-12-22 | 2017-06-22 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for cardiac image segmentation |
| CN106997594A (en) * | 2016-01-26 | 2017-08-01 | 上海联影医疗科技有限公司 | The localization method and device of a kind of part tissue of eye |
| CN108185984A (en) * | 2017-12-28 | 2018-06-22 | 中山大学 | The method that eyeground color picture carries out eyeground lesion identification |
| CN108257214A (en) * | 2018-02-12 | 2018-07-06 | 成都信息工程大学 | Heart left ventricle flow field domain method for numerical simulation, computer, computer program |
| CN110895817A (en) * | 2019-11-01 | 2020-03-20 | 复旦大学 | MRI image hepatic fibrosis automatic grading method based on image omics analysis |
| CN111815586A (en) * | 2020-06-29 | 2020-10-23 | 苏州润心医疗器械有限公司 | Method and system for acquiring connected domain of left atrium and left ventricle based on CT image |
| CN112017198A (en) * | 2020-10-16 | 2020-12-01 | 湖南师范大学 | Right ventricle segmentation method and device based on self-attention mechanism multi-scale features |
| CN112435272A (en) * | 2020-12-07 | 2021-03-02 | 南京派光高速载运智慧感知研究院有限公司 | High-voltage transmission line connected domain removing method based on image contour analysis |
| US20210125037A1 (en) * | 2019-10-28 | 2021-04-29 | Ai4Medimaging - Medical Solutions, S.A. | Artificial intelligence based cardiac motion classification |
| US20210125333A1 (en) * | 2019-10-28 | 2021-04-29 | Centro Clinico Académico - Braga | Artificial-Intelligence-Based Global Cardiac Motion Classification |
| CN113344991A (en) * | 2021-05-17 | 2021-09-03 | 山东师范大学 | Unsupervised medical image registration method and system based on deep learning |
| EP3985605A1 (en) * | 2020-10-15 | 2022-04-20 | Koninklijke Philips N.V. | Image segmentation methods and systems |
-
2023
- 2023-04-20 CN CN202310428761.6A patent/CN116152253B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236062A (en) * | 2013-05-03 | 2013-08-07 | 北京国铁华晨通信信息技术有限公司 | Magnetic resonance imaging blood vessel segmentation method and system based on human brain tumor nuclear magnetic library |
| US20160110879A1 (en) * | 2014-10-18 | 2016-04-21 | International Business Machines Corporation | Automatic Visualization of Regional Functional Parameters of Left Ventricle from Cardiac Imaging |
| CN104680127A (en) * | 2014-12-18 | 2015-06-03 | 闻泰通讯股份有限公司 | Gesture identification method and gesture identification system |
| US20170178285A1 (en) * | 2015-12-22 | 2017-06-22 | Shanghai United Imaging Healthcare Co., Ltd. | Method and system for cardiac image segmentation |
| CN106997594A (en) * | 2016-01-26 | 2017-08-01 | 上海联影医疗科技有限公司 | The localization method and device of a kind of part tissue of eye |
| CN105956587A (en) * | 2016-04-20 | 2016-09-21 | 哈尔滨工业大学 | Method for automatically extracting meniscus from knee-joint magnetic resonance image sequence based on shape constraint |
| CN106780460A (en) * | 2016-12-13 | 2017-05-31 | 杭州健培科技有限公司 | A kind of Lung neoplasm automatic checkout system for chest CT image |
| CN108185984A (en) * | 2017-12-28 | 2018-06-22 | 中山大学 | The method that eyeground color picture carries out eyeground lesion identification |
| CN108257214A (en) * | 2018-02-12 | 2018-07-06 | 成都信息工程大学 | Heart left ventricle flow field domain method for numerical simulation, computer, computer program |
| US20210125037A1 (en) * | 2019-10-28 | 2021-04-29 | Ai4Medimaging - Medical Solutions, S.A. | Artificial intelligence based cardiac motion classification |
| US20210125333A1 (en) * | 2019-10-28 | 2021-04-29 | Centro Clinico Académico - Braga | Artificial-Intelligence-Based Global Cardiac Motion Classification |
| CN110895817A (en) * | 2019-11-01 | 2020-03-20 | 复旦大学 | MRI image hepatic fibrosis automatic grading method based on image omics analysis |
| CN111815586A (en) * | 2020-06-29 | 2020-10-23 | 苏州润心医疗器械有限公司 | Method and system for acquiring connected domain of left atrium and left ventricle based on CT image |
| EP3985605A1 (en) * | 2020-10-15 | 2022-04-20 | Koninklijke Philips N.V. | Image segmentation methods and systems |
| CN112017198A (en) * | 2020-10-16 | 2020-12-01 | 湖南师范大学 | Right ventricle segmentation method and device based on self-attention mechanism multi-scale features |
| CN112435272A (en) * | 2020-12-07 | 2021-03-02 | 南京派光高速载运智慧感知研究院有限公司 | High-voltage transmission line connected domain removing method based on image contour analysis |
| CN113344991A (en) * | 2021-05-17 | 2021-09-03 | 山东师范大学 | Unsupervised medical image registration method and system based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 邓巧等: ""多发性肌炎或皮肌炎患者亚临床心脏受累的磁共振心肌分层应变特征 及诊断价值"", 《中国医学影像学杂志》, vol. 30, no. 7, pages 648 - 654 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116152253B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Loizou et al. | Snakes based segmentation of the common carotid artery intima media | |
| CN107798679B (en) | Breast region segmentation and calcification detection method for mammary gland molybdenum target image | |
| CN110197713B (en) | Medical image processing method, device, equipment and medium | |
| EP1851720B1 (en) | Method of automatic extraction of the pulmonary artery tree from 3d medical images | |
| JP6422198B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| US7711167B2 (en) | Fissure detection methods for lung lobe segmentation | |
| Datta et al. | Gray matter segmentation of the spinal cord with active contours in MR images | |
| CN108615239B (en) | Tongue image segmentation method based on threshold technology and gray level projection | |
| KR20150063995A (en) | Apparatus and method processing image | |
| Abdulraqeb et al. | An automated method for segmenting brain tumors on MRI images | |
| Lawrence et al. | Computer assisted detection of polycystic ovary morphology in ultrasound images | |
| US9947094B2 (en) | Medical image processing device, operation method therefor, and medical image processing program | |
| Purnama et al. | Follicle detection on the usg images to support determination of polycystic ovary syndrome | |
| CN113012127A (en) | Cardiothoracic ratio measuring method based on chest medical image | |
| US20190333212A1 (en) | Visual cardiomyocyte analysis | |
| CN116152253B (en) | Cardiac magnetic resonance mapping quantification method, system and storage medium | |
| Zhang et al. | Atlas-driven lung lobe segmentation in volumetric X-ray CT images | |
| RU2656761C1 (en) | Method and system of segmentation of lung foci images | |
| CN113112473B (en) | Automatic diagnosis system for human body dilated cardiomyopathy | |
| KR102384083B1 (en) | Apparatus and Method for Diagnosing Sacroiliac Arthritis and Evaluating the Degree of Inflammation using Magnetic Resonance Imaging | |
| Morais et al. | Fully automatic left ventricular myocardial strain estimation in 2D short-axis tagged magnetic resonance imaging | |
| Shaziya et al. | Comprehensive review of automatic lung segmentation techniques on pulmonary CT images | |
| EP3114646B1 (en) | Apparatus and method for detecting myocardial iron content using black-blood magnetic resonance data | |
| KR20190138105A (en) | Qualification method of lung vessel based on lobe | |
| Suji et al. | Comparision of Some Image Thresholding Techniques with Morphological Operations and Quantitative Evaluation for Lung Segmentation |
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 |