CN112215839B - Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram - Google Patents
Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram Download PDFInfo
- Publication number
- CN112215839B CN112215839B CN202011166893.9A CN202011166893A CN112215839B CN 112215839 B CN112215839 B CN 112215839B CN 202011166893 A CN202011166893 A CN 202011166893A CN 112215839 B CN112215839 B CN 112215839B
- Authority
- CN
- China
- Prior art keywords
- point
- edge
- wall
- left ventricular
- points
- 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
- 230000002861 ventricular Effects 0.000 title claims abstract description 115
- 230000011218 segmentation Effects 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 38
- 210000005240 left ventricle Anatomy 0.000 claims abstract description 47
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 210000000596 ventricular septum Anatomy 0.000 claims abstract description 22
- 238000003709 image segmentation Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004040 coloring Methods 0.000 claims description 7
- PXXLQQDIFVPNMP-UHFFFAOYSA-N 3-(diethylcarbamoyl)benzoic acid Chemical compound CCN(CC)C(=O)C1=CC=CC(C(O)=O)=C1 PXXLQQDIFVPNMP-UHFFFAOYSA-N 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000002592 echocardiography Methods 0.000 abstract description 13
- 238000012545 processing Methods 0.000 abstract description 3
- 238000003759 clinical diagnosis Methods 0.000 abstract 1
- 230000002107 myocardial effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000012938 design process Methods 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06T7/12—Edge-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
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (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)
- Ultra Sonic Daignosis Equipment (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an echocardiography left ventricular wall six-segment segmentation method, an echocardiography left ventricular wall six-segment segmentation system and a storage medium, and relates to the technical field of medical image processing, wherein the method comprises the following steps: acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map; detecting left ventricular wall corner points of the left ventricular wall segmentation map to obtain four corner points at the bottom of a ventricular septum and the bottom of the outer wall of the left ventricle; performing edge extraction on the left ventricle wall segmentation graph, and combining four corner points to obtain an edge point set; determining a parting line of the inter-ventricular wall region and the left ventricular outer wall region based on the set of edge points for the left ventricular wall region; six sub-regions are calculated and obtained based on the set of edge points for the ventricular septum region and the left ventricular outer wall region, respectively. The invention successfully realizes the automation of six-segment segmentation of the left ventricle wall, has credibility of segmentation results and can play an auxiliary role in clinical diagnosis.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to an echocardiography left ventricular wall six-segment segmentation method, an echocardiography left ventricular wall six-segment segmentation system and a storage medium.
Background
The four-chamber section of the apex of the heart is an important standard section of the echocardiogram, which can clearly reflect the morphological structure of the left ventricle wall. Under this tangent plane, the left ventricular 16-segment segmentation proposed by the american society of echocardiography suggests dividing the left ventricular wall into six myocardial sub-segments (as shown in fig. 1) in order for the physician to clearly describe the location of the heart lesion.
Wherein, from the anatomical definition, the left ventricular wall is composed of two parts, a ventricular septum and a left ventricular outer wall. The parting line of the two is from the apex of the heart, and the direction is along the tangential direction of the myocardial trend. For the ventricular septum region, three myocardial sub-blocks (regions numbered 1, 2, 3 in FIG. 1) may be trisected. For the left ventricular outer wall, three additional sub-blocks (regions numbered 4, 5, 6 in fig. 1) may also be trisected.
In actual echocardiography analysis, the clinician needs to manually mark each myocardial sub-block in each image as per standard. This process is time consuming and the marking results are subjectively affected by the physician. If the marking process can be automated, the workload of the clinician can be greatly reduced, and the marking result quality can be ensured to be more stable. There is currently no automated method and system for six-segment segmentation of the echocardiographic left ventricular wall.
Disclosure of Invention
The invention provides an echocardiographic left ventricle six-segment segmentation method, an echocardiographic left ventricle six-segment segmentation system and a storage medium, which are used for realizing automatic six-segment segmentation of a left ventricle wall in a four-cavity section of an echocardiographic apex.
The invention provides the following technical scheme:
The invention provides an echocardiography left ventricular wall six-segment segmentation method, which comprises the following steps:
Acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map;
Detecting left ventricular wall corner points of the left ventricular wall segmentation map to obtain four corner points at the bottom of a ventricular septum and the bottom of the outer wall of the left ventricle;
performing edge extraction on the left ventricle wall segmentation map, and combining the four corner points to obtain an edge point set in the left ventricle wall segmentation map;
Determining, for the left ventricular wall region, a parting line of a ventricular septum region and a left ventricular outer wall region based on the set of edge points;
Six sub-regions are calculated and obtained based on the set of edge points for the inter-ventricular area and the left ventricular outer wall area, respectively.
Further, performing left ventricular wall angle point detection on the left ventricular wall segmentation map includes:
counting the number of non-zero pixels in the left ventricle wall segmentation map according to rows and columns, cutting off rows and columns with the number of non-zero pixels being zero, and only reserving a horseshoe-shaped left ventricle wall area;
Dividing the cut image into 2X 2 sub-blocks with equal size;
For the left lower sub-block, the center of the sub-block is taken as a rotation center, the sub-block rotates clockwise by a preset angle, and the leftmost point and the bottommost point are a left corner point A and a right corner point B of the bottom edge of the horseshoe-shaped left half area;
for the lower right sub-block, the center of the sub-block is taken as a rotation center, the sub-block rotates clockwise by a preset angle, and the leftmost point and the bottommost point are a left corner point C and a right corner point D of the bottom edge of the horseshoe-shaped right half area.
Further, performing edge extraction on the left ventricular wall segmentation map to obtain an edge point set, including:
extracting the edges of the left ventricle wall segmentation map by using an edge extraction operator to obtain a horseshoe-shaped edge map;
counting all non-zero pixel point coordinates in the horseshoe-shaped edge graph, and combining the four corner points to construct an edge point set;
Taking a non-zero pixel point in a first row in the edge point set as a starting point, deleting the point from the edge point set, recording the point in a sorting point set, searching a non-zero pixel point with the right side closest to the point deleted last time, deleting the non-zero pixel point from the edge point set, and recording the point in the sorting point set;
Sequentially removing nodes in the edge point set and recording the nodes in the sorting point set until the edge point set is empty;
Dividing the ordered point set into four sub-point sets { DC, CB, BA, AD } according to the order of DCBA; where { CB } is the set of inner edge points and { AD } is the set of outer edge points.
Further, determining a parting line of a ventricular septum region and a left ventricular outer wall region for the left ventricular wall region based on the set of edge points, comprising:
calculating coordinates of a midpoint E of a connecting line BC of the corner B and the corner C;
Sequentially calculating the distance between each inner edge point in the inner edge point set and the point E, and finding out a point F farthest from the point E;
obtaining an equation of a straight line EF between the point E and the point F;
and sequentially calculating the distance between the outer edge points in the outer edge point set and the straight line EF, and finding out the point G with the smallest distance as an intersection point of the EF and the outer edge, wherein the line segment FG is a dividing line of the ventricular septum region and the left ventricular outer wall region.
Further, for the ventricular septum region and the left ventricular outer wall region, respectively, six sub-regions are calculated and obtained based on the set of edge points, including:
Dividing the inner edge into two point sequences of { CF } { FB }, and respectively finding the trisection points of { CF } { FB };
dividing the outer edge into two point sequences of { AE } { ED }, and respectively finding the trisection points of { AE } { ED };
connecting the four pairs of trisection points into four line segments; ;
coloring the four line segments and the line segment FG into a background color in sequence;
and calculating a connected domain in the left ventricle wall segmentation map, and removing scattered areas with smaller areas to obtain six sub-areas.
Further, the edge extraction operator includes: sobel operator or Canny operator.
Further, the method further comprises the following steps:
calculating the center of gravity of each region and sequencing the regions according to the arc direction from the lower left corner to the lower right corner;
sequentially coloring and generating a translucent mask overlaying the echocardiogram.
The invention also provides an echocardiography left ventricular wall six-segment segmentation system, which comprises:
The left ventricular wall segmentation map acquisition module is used for acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map;
The left ventricular wall angle point detection module is used for detecting left ventricular wall angle points of the left ventricular wall segmentation map acquired by the left ventricular wall segmentation map acquisition module to acquire four angle points of the bottom of the ventricular septum and the bottom of the left ventricular outer wall;
the left ventricular wall edge point extraction module is used for carrying out edge extraction on the left ventricular wall segmentation map acquired by the left ventricular wall segmentation map acquisition module, and combining the four corner points acquired by the left ventricular wall corner point detection module to acquire a left ventricular wall edge point set;
An automatic six-segment segmentation module of the left ventricle wall is used for determining a segmentation line of a ventricular interval region and a left ventricle outer wall region aiming at the left ventricle wall region based on the edge point set extracted by the left ventricle wall edge point extraction module; six sub-regions are calculated and obtained based on the set of edge points for the inter-ventricular area and the left ventricular outer wall area, respectively.
The invention also provides a computer readable storage medium, wherein a computer instruction set is stored in the computer readable storage medium, and when the computer instruction set is executed by a processor, the method for segmenting the left ventricular wall six segments of the echocardiogram is realized.
The invention has the advantages and positive effects that:
The invention realizes automatic six-segment segmentation of the left ventricular wall in the echocardiography. The anatomical features of the left ventricular wall are fully considered in the design process, the anatomical features are in one-to-one correspondence with the geometric features of the left ventricular wall region in the echocardiogram, so that the calculated key points, the dividing lines and the six-segment dividing results are matched with the proposal of the American echocardiogram society, and the reliability is realized. Further, based on the six-segment segmentation result of the invention, the local motion pattern feature of the echocardiogram can be extracted for predicting whether the myocardial motion pattern is abnormal.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic view of a standard apical four-chamber heart section and an echocardiogram;
FIG. 2 is a flow chart of a six-segment segmentation method for the left ventricular wall of an echocardiography in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of all key points in a six-segment segmentation method according to an embodiment of the present invention;
FIG. 4 shows six sub-regions and their numbers obtained by dividing the sub-regions by a six-segment dividing method according to an embodiment of the present invention;
fig. 5 is a visual result of six segments of the left ventricular wall of the echocardiography in an embodiment of the invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 2, a flowchart of a six-segment segmentation method for an echocardiographic left ventricle wall is shown in an embodiment of the invention, wherein the coordinates of the points involved are shown in fig. 3. The method comprises the following steps:
s101, acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map.
The image segmentation method may be a deep learning-based image segmentation model (e.g., FCN, UNet, etc.) or a conventional image segmentation algorithm (e.g., a particle swarm image segmentation algorithm, etc.).
S102, detecting left ventricular wall corner points of the left ventricular wall segmentation map to obtain four corner points at the bottom of a ventricular septum and the bottom of the outer wall of the left ventricle;
The corner detection may be performed as follows:
2.1, counting the number of non-zero pixels in the left ventricle wall segmentation graph according to rows and columns, cutting off rows and columns with the number of non-zero pixels being zero, and only keeping a horseshoe-shaped left ventricle wall area;
2.2 dividing the cut image into 2X 2 sub-blocks with equal size;
2.3 for the lower left sub-block, the center of the sub-block is taken as a rotation center, the sub-block rotates clockwise by theta degrees (typical value is 45 degrees), and the leftmost point and the bottommost point are a left corner point A and a right corner point B of the bottom edge of the horseshoe-shaped left half area; the space corresponds to the intersection of the ventricular septum and the root of the right ventricular valve and the left ventricular valve respectively;
2.4, carrying out the same operation as in the step 2.3 on the right lower sub-block, and detecting left and right corner points C, D at the bottom edge of the horseshoe-shaped right half area; the intersection of the outer wall inner membrane and the outer membrane of the left ventricle and the root of the left ventricle respectively corresponds to the space.
S103, carrying out edge extraction on the left ventricle wall segmentation map, and combining the four corner points to obtain an edge point set in the left ventricle wall segmentation map.
The set of edge points can be obtained as follows:
3.1, extracting edges of the segmentation map by using edge extraction operators (such as Sobel operator and Canny operator) to obtain a horseshoe-shaped edge map;
and 3.2, counting all non-zero pixel point coordinates in the edge map, and constructing an edge point set P (wherein the P comprises ABCD points in the step 1).
3.3, Taking the non-zero pixel point in the first row in P as a starting point Pi, deleting the point in P, recording the point in P to the ordered point set Q, and searching the non-zero pixel point Pj closest to the right side;
3.4 deleting the Pj node in P, recording to Q, and finding a non-zero pixel Pk closest to the P node by calculating the pixel distance;
3.5, sequentially removing the nodes in P according to the step 3.4 and recording the nodes in Q until P is empty;
3.6 dividing Q into four sub-point sets { DC, CB, BA, AD } in the order of DCBA; where { CB } is the set of inner edge points and { AD } is the set of outer edge points.
S104, determining a parting line of the inter-chamber area and the left ventricular outer wall area based on the edge point set aiming at the left ventricular wall area.
The parting line may be determined as follows:
4.1, calculating the coordinates of a midpoint E of a connecting line BC of the corner B and the corner C;
4.2, sequentially calculating the distance between the inner edge point and the point E, and finding out the point F with the farthest distance;
4.3 calculating the equation y=kx+b for the straight line EF between point E and point F;
4.4, sequentially calculating the distance between the outer edge point and the straight line EF, finding out the point G with the minimum distance as the intersection point of the EF and the outer edge, wherein the line segment FG is a dividing line of the chamber interval and the outer wall of the left ventricle; spatially, the point G is the anatomically defined apex, and the line segment FG is a parting line along the tangential direction of the myocardial progression.
S105, calculating and obtaining six sub-areas based on the edge point set aiming at the inter-chamber area and the left ventricular outer wall area respectively.
Six sub-regions can be obtained as follows:
5.1 dividing the inner edge into two point sequences of { CF } { FB }, and respectively finding the trisection points of { CF } { FB };
5.2 dividing the outer edge into two point sequences of { AE } { ED }, and respectively finding the trisection points of { AE } { ED };
5.3 four pairs of trisection points of the inner and outer edges may be connected into four line segments, as shown in fig. 3, numbered 1,2, 3, 4. The split line resulting from the arc trisection point connection enables trisection recommended by the american echocardiography society.
5.4 Coloring segments 1, 2, 3, 4 and GF in order to background color;
5.5, removing scattered areas with smaller areas from connected areas in the calculation graph, wherein six sub-areas (shown in fig. 4) can be obtained at the moment;
5.6, finding the center of gravity of each region and sequencing the regions according to the arc direction from the lower left corner to the lower right corner;
5.7 coloring and generating a translucent mask in sequence, overlaying the echocardiogram (as shown in fig. 5).
The embodiment of the invention realizes automatic six-segment segmentation of the left ventricular wall in the echocardiography. The anatomical features of the left ventricular wall are fully considered in the design process, the anatomical features are in one-to-one correspondence with the geometric features of the left ventricular wall region in the echocardiogram, so that the calculated key points, the dividing lines and the six-segment dividing results are matched with the proposal of the American echocardiogram society, and the reliability is realized. Further, based on the six-segment segmentation result of the invention, the local motion pattern feature of the echocardiogram can be extracted for predicting whether the myocardial motion pattern is abnormal.
Corresponding to the six-segment segmentation method of the left ventricular wall of the echocardiogram in the above embodiment of the present invention, the present invention also provides an six-segment segmentation system of the left ventricular wall of the echocardiogram, comprising:
The left ventricular wall segmentation map acquisition module is used for acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map;
The left ventricular wall angle point detection module is used for detecting left ventricular wall angle points of the left ventricular wall segmentation map acquired by the left ventricular wall segmentation map acquisition module to acquire four angle points of the bottom of the ventricular septum and the bottom of the left ventricular outer wall;
the left ventricular wall edge point extraction module is used for carrying out edge extraction on the left ventricular wall segmentation map acquired by the left ventricular wall segmentation map acquisition module, and combining the four corner points acquired by the left ventricular wall corner point detection module to acquire a left ventricular wall edge point set;
An automatic six-segment segmentation module of the left ventricle wall is used for determining a segmentation line of a ventricular interval region and a left ventricle outer wall region aiming at the left ventricle wall region based on the edge point set extracted by the left ventricle wall edge point extraction module; six sub-regions are calculated and obtained based on the set of edge points for the inter-ventricular area and the left ventricular outer wall area, respectively.
For the echocardiographic left ventricular wall six-segment segmentation system of the embodiment of the present invention, since it corresponds to the echocardiographic left ventricular wall six-segment segmentation method in the above embodiment, the description is relatively simple, and the relevant similarities will be referred to the description of the above embodiment, and will not be described in detail herein.
The embodiment of the invention also discloses a computer readable storage medium, wherein a computer instruction set is stored in the computer readable storage medium, and when the computer instruction set is executed by a processor, the method for segmenting the six segments of the left ventricle of the echocardiogram provided by any embodiment is realized.
In the several embodiments provided in the present invention, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of the units, for example, may be a logic function division, and may be implemented in another manner, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a read-only memory (ROM), a random access memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. An echocardiographic left ventricular wall six-segment segmentation method, comprising:
Acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map;
Detecting left ventricular wall corner points of the left ventricular wall segmentation map to obtain four corner points at the bottom of a ventricular septum and the bottom of the outer wall of the left ventricle;
performing edge extraction on the left ventricle wall segmentation map, and combining the four corner points to obtain an edge point set in the left ventricle wall segmentation map;
Determining, for the left ventricular wall region, a parting line of a ventricular septum region and a left ventricular outer wall region based on the set of edge points;
calculating and obtaining six sub-areas based on the edge point set for the inter-ventricular area and the left ventricular outer wall area respectively;
The edge extraction is performed on the left ventricle wall segmentation graph to obtain an edge point set, which comprises the following steps:
extracting the edges of the left ventricle wall segmentation map by using an edge extraction operator to obtain a horseshoe-shaped edge map;
counting all non-zero pixel point coordinates in the horseshoe-shaped edge graph, and combining the four corner points to construct an edge point set;
Taking a non-zero pixel point in a first row in the edge point set as a starting point, deleting the point from the edge point set, recording the point in a sorting point set, searching a non-zero pixel point with the right side closest to the point deleted last time, deleting the non-zero pixel point from the edge point set, and recording the point in the sorting point set;
Sequentially removing nodes in the edge point set and recording the nodes in the sorting point set until the edge point set is empty;
Dividing the ordered point set into four sub-point sets { DC, CB, BA, AD } according to the order of DCBA; wherein { CB } is an inner edge point set and { AD } is an outer edge point set;
Wherein determining a parting line of a ventricular septum region and a left ventricular outer wall region for the left ventricular wall region based on the set of edge points comprises:
calculating coordinates of a midpoint E of a connecting line BC of the corner B and the corner C;
Sequentially calculating the distance between each inner edge point in the inner edge point set and the point E, and finding out a point F farthest from the point E;
obtaining an equation of a straight line EF between the point E and the point F;
Sequentially calculating the distance between the outer edge points in the outer edge point set and a straight line EF, and finding out a point G with the smallest distance as an intersection point of the EF and the outer edge, wherein the line segment FG is a dividing line of a ventricular septum region and a left ventricular outer wall region;
wherein, for the ventricular septum region and left ventricular outer wall region, respectively, six sub-regions are calculated and obtained based on the set of edge points, including:
Dividing the inner edge into two point sequences of { CF } { FB }, and respectively finding the trisection points of { CF } { FB };
dividing the outer edge into two point sequences of { AE } { ED }, and respectively finding the trisection points of { AE } { ED };
Connecting the four pairs of trisection points into four line segments;
coloring the four line segments and the line segment FG into a background color in sequence;
and calculating a connected domain in the left ventricle wall segmentation map, and removing scattered areas with smaller areas to obtain six sub-areas.
2. The method of claim 1, wherein detecting left ventricular wall angle points for the left ventricular wall segmentation map comprises:
counting the number of non-zero pixels in the left ventricle wall segmentation map according to rows and columns, cutting off rows and columns with the number of non-zero pixels being zero, and only reserving a horseshoe-shaped left ventricle wall area;
Dividing the cut image into 2X 2 sub-blocks with equal size;
For the left lower sub-block, the center of the sub-block is taken as a rotation center, the sub-block rotates clockwise by a preset angle, and the leftmost point and the bottommost point are a left corner point A and a right corner point B of the bottom edge of the horseshoe-shaped left half area;
for the lower right sub-block, the center of the sub-block is taken as a rotation center, the sub-block rotates clockwise by a preset angle, and the leftmost point and the bottommost point are a left corner point C and a right corner point D of the bottom edge of the horseshoe-shaped right half area.
3. The method of claim 2, wherein the edge extraction operator comprises: sobel operator or Canny operator.
4. A method according to claim 3, further comprising:
calculating the center of gravity of each region and sequencing the regions according to the arc direction from the lower left corner to the lower right corner;
sequentially coloring and generating a translucent mask overlaying the echocardiogram.
5. An echocardiographic left ventricular wall six segment segmentation system, comprising:
The left ventricular wall segmentation map acquisition module is used for acquiring an echocardiogram, and performing image segmentation on the echocardiogram by using an image segmentation method to obtain a left ventricular wall segmentation map;
The left ventricular wall angle point detection module is used for detecting left ventricular wall angle points of the left ventricular wall segmentation map acquired by the left ventricular wall segmentation map acquisition module to acquire four angle points of the bottom of the ventricular septum and the bottom of the left ventricular outer wall;
the left ventricular wall edge point extraction module is used for carrying out edge extraction on the left ventricular wall segmentation map acquired by the left ventricular wall segmentation map acquisition module, and combining the four corner points acquired by the left ventricular wall corner point detection module to acquire a left ventricular wall edge point set;
An automatic six-segment segmentation module of the left ventricle wall is used for determining a segmentation line of a ventricular interval region and a left ventricle outer wall region aiming at the left ventricle wall region based on the edge point set extracted by the left ventricle wall edge point extraction module; calculating and obtaining six sub-areas based on the edge point set for the inter-ventricular area and the left ventricular outer wall area respectively;
The edge extraction is performed on the left ventricle wall segmentation graph to obtain an edge point set, which comprises the following steps:
extracting the edges of the left ventricle wall segmentation map by using an edge extraction operator to obtain a horseshoe-shaped edge map;
counting all non-zero pixel point coordinates in the horseshoe-shaped edge graph, and combining the four corner points to construct an edge point set;
Taking a non-zero pixel point in a first row in the edge point set as a starting point, deleting the point from the edge point set, recording the point in a sorting point set, searching a non-zero pixel point with the right side closest to the point deleted last time, deleting the non-zero pixel point from the edge point set, and recording the point in the sorting point set;
Sequentially removing nodes in the edge point set and recording the nodes in the sorting point set until the edge point set is empty;
Dividing the ordered point set into four sub-point sets { DC, CB, BA, AD } according to the order of DCBA; wherein { CB } is an inner edge point set and { AD } is an outer edge point set;
Wherein determining a parting line of a ventricular septum region and a left ventricular outer wall region for the left ventricular wall region based on the set of edge points comprises:
calculating coordinates of a midpoint E of a connecting line BC of the corner B and the corner C;
Sequentially calculating the distance between each inner edge point in the inner edge point set and the point E, and finding out a point F farthest from the point E;
obtaining an equation of a straight line EF between the point E and the point F;
Sequentially calculating the distance between the outer edge points in the outer edge point set and a straight line EF, and finding out a point G with the smallest distance as an intersection point of the EF and the outer edge, wherein the line segment FG is a dividing line of a ventricular septum region and a left ventricular outer wall region;
wherein, for the ventricular septum region and left ventricular outer wall region, respectively, six sub-regions are calculated and obtained based on the set of edge points, including:
Dividing the inner edge into two point sequences of { CF } { FB }, and respectively finding the trisection points of { CF } { FB };
dividing the outer edge into two point sequences of { AE } { ED }, and respectively finding the trisection points of { AE } { ED };
Connecting the four pairs of trisection points into four line segments;
coloring the four line segments and the line segment FG into a background color in sequence;
and calculating a connected domain in the left ventricle wall segmentation map, and removing scattered areas with smaller areas to obtain six sub-areas.
6. A computer readable storage medium, wherein a set of computer instructions is stored in the computer readable storage medium, which when executed by a processor, implements the echocardiographic left ventricular wall six-segment segmentation method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011166893.9A CN112215839B (en) | 2020-10-27 | 2020-10-27 | Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011166893.9A CN112215839B (en) | 2020-10-27 | 2020-10-27 | Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112215839A CN112215839A (en) | 2021-01-12 |
| CN112215839B true CN112215839B (en) | 2024-04-19 |
Family
ID=74057127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011166893.9A Active CN112215839B (en) | 2020-10-27 | 2020-10-27 | Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112215839B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794706A (en) * | 2015-04-03 | 2015-07-22 | 哈尔滨医科大学 | Method for examining cardiac muscles and measuring features by aid of ultrasonic images |
| CN105741310A (en) * | 2016-03-21 | 2016-07-06 | 东北大学 | Heart's left ventricle image segmentation system and method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2026280B1 (en) * | 2007-07-23 | 2013-10-23 | Esaote S.p.A. | Method and corresponding apparatus for quantitative measurements on sequences of images, particularly ultrasonic images |
| US8983160B2 (en) * | 2009-03-31 | 2015-03-17 | Hitachi Medical Corporation | Medical image diagnostic apparatus and volume calculating method |
| US20110262018A1 (en) * | 2010-04-27 | 2011-10-27 | MindTree Limited | Automatic Cardiac Functional Assessment Using Ultrasonic Cardiac Images |
| US9147258B2 (en) * | 2013-02-19 | 2015-09-29 | General Electric Company | Methods and systems for segmentation in echocardiography |
-
2020
- 2020-10-27 CN CN202011166893.9A patent/CN112215839B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794706A (en) * | 2015-04-03 | 2015-07-22 | 哈尔滨医科大学 | Method for examining cardiac muscles and measuring features by aid of ultrasonic images |
| CN105741310A (en) * | 2016-03-21 | 2016-07-06 | 东北大学 | Heart's left ventricle image segmentation system and method |
Non-Patent Citations (2)
| Title |
|---|
| Samaneh Mazaheri,et al..Segmentation Methods of Echocardiography Images for Left Ventricle Boundary Detection.Journal of Computer Science.2015,全文. * |
| 超声心动图的分割方法研究;魏洪成;中国优秀硕士学位论文全文数据库 基础科学辑;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112215839A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956635B (en) | Lung segment segmentation method, device, equipment and storage medium | |
| US8199985B2 (en) | Automatic interpretation of 3-D medicine images of the brain and methods for producing intermediate results | |
| AU2015284524B2 (en) | Detecting tooth wear using intra-oral 3D scans | |
| US8761493B2 (en) | Method and system for tooth segmentation in dental images | |
| US8929635B2 (en) | Method and system for tooth segmentation in dental images | |
| US9349184B2 (en) | Method and apparatus for identifying regions of interest in a medical image | |
| CN110570445B (en) | Image segmentation method, device, terminal and readable medium | |
| WO2021082434A1 (en) | Abnormal cell screening method and apparatus, electronic device, and storage medium | |
| CN114359277B (en) | Brain image processing method and system for stroke patient | |
| CN107622245A (en) | Papery Wave shape extracting method and device | |
| CN112215839B (en) | Six-segment segmentation method, system and storage medium for left ventricular wall of echocardiogram | |
| CN108597589B (en) | Model generation method, target detection method and medical imaging system | |
| CN110910348A (en) | Method, device, equipment and storage medium for classifying positions of pulmonary nodules | |
| Ben-Hamadou et al. | 3DTeethSeg'22: 3D Teeth Scan Segmentation and Labeling Challenge | |
| JP5669977B1 (en) | Myocardial contour extraction technology | |
| CN115937466B (en) | GIS-fused three-dimensional model generation method, system and storage medium | |
| CN112308845A (en) | Left ventricle segmentation method and device and electronic equipment | |
| CN113222051A (en) | Image labeling method based on small intestine focus characteristics | |
| CN107392976A (en) | Data processing method, device and equipment | |
| JP2010167067A (en) | Medical image processing apparatus and program | |
| JP5755276B2 (en) | Myocardial contour extraction technology and its application | |
| CN113112475A (en) | Traditional Chinese medicine ear five-organ region segmentation method and device based on machine learning | |
| CN100592335C (en) | Using corner pixels as seeds for detection of convex objects | |
| CN112258476B (en) | Method, system and storage medium for analyzing abnormal motion pattern of heart muscle of echocardiography | |
| JP7480997B2 (en) | Image processing device, image processing method, and program |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 116000 room 206, no.8-9, software garden road, Ganjingzi District, Dalian City, Liaoning Province Applicant after: Neusoft Education Technology Group Co.,Ltd. Address before: 116000 room 206, no.8-9, software garden road, Ganjingzi District, Dalian City, Liaoning Province Applicant before: Dalian Neusoft Education Technology Group Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |