CN113344897B - Lung image caliber measuring method and device and image processing method and device - Google Patents

Lung image caliber measuring method and device and image processing method and device Download PDF

Info

Publication number
CN113344897B
CN113344897B CN202110707743.2A CN202110707743A CN113344897B CN 113344897 B CN113344897 B CN 113344897B CN 202110707743 A CN202110707743 A CN 202110707743A CN 113344897 B CN113344897 B CN 113344897B
Authority
CN
China
Prior art keywords
pulmonary artery
caliber
point
midline
line
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
Application number
CN202110707743.2A
Other languages
Chinese (zh)
Other versions
CN113344897A (en
Inventor
孙岩峰
韦人
邹彤
于荣震
张欢
王瑜
王少康
陈宽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Infervision Medical Technology Co Ltd
Original Assignee
Infervision Medical Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Infervision Medical Technology Co Ltd filed Critical Infervision Medical Technology Co Ltd
Priority to CN202110707743.2A priority Critical patent/CN113344897B/en
Publication of CN113344897A publication Critical patent/CN113344897A/en
Application granted granted Critical
Publication of CN113344897B publication Critical patent/CN113344897B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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
    • G06T2207/10081—Computed x-ray tomography [CT]
    • 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
    • G06T2207/30061—Lung

Abstract

The application provides a method and a device for measuring the caliber of a lung image and a method and a device for processing the image, wherein the method for measuring the caliber comprises the following steps: acquiring a main pulmonary artery central line effective section and a main pulmonary artery boundary based on an optimal segmentation level in a segmentation result of a lung image; a plurality of pixel points on the central line effective section of the main pulmonary artery are used as the drop feet, and a plurality of vertical line sections are determined; and acquiring a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary. The technical scheme of this application is through on the best segmentation aspect, confirms main pulmonary artery central line valid segment and many perpendicular line segments to in the measuring point of acquireing pulmonary artery pipe diameter, promote the measurement accuracy of pulmonary artery pipe diameter.

Description

Lung image caliber measuring method and device and image processing method and device
Technical Field
The application relates to the technical field of deep learning, in particular to a method and a device for measuring the caliber of a lung image and an image processing method and device.
Background
Currently, the determination of pulmonary hypertension is mainly determined by the length or length ratio of the diameter of the pulmonary trunk (i.e. the diameter of the main pulmonary artery) and the diameter of the aortic trunk (i.e. the diameter of the aortic artery) in medical images (e.g. lung CT images). Therefore, the accuracy of determining the diameter of the pulmonary artery trunk and the diameter of the aorta trunk determines the accuracy of determining the pulmonary artery hypertension.
In view of this, how to accurately determine the pulmonary artery trunk diameter and the aortic artery trunk diameter becomes a technical problem to be solved urgently.
Disclosure of Invention
In view of this, embodiments of the present application provide a method and an apparatus for measuring a pulmonary artery caliber, and an image processing method and an apparatus, which can improve the measurement accuracy of a pulmonary artery caliber.
In a first aspect, an embodiment of the present application provides a method for measuring a caliber of a lung image, including: acquiring a main pulmonary artery central line effective section and a main pulmonary artery boundary based on an optimal segmentation level in a segmentation result of a lung image; a plurality of pixel points on the central line effective section of the main pulmonary artery are used as the drop feet, and a plurality of vertical line sections are determined; and acquiring a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary.
In some embodiments of the present application, obtaining a measurement point of a pulmonary artery caliber based on a plurality of vertical segments and a main pulmonary artery boundary comprises: and taking the intersection point of the vertical line segment which is not intersected with the left pulmonary artery inlet and the right pulmonary artery inlet and has the maximum line segment length and the main pulmonary artery boundary as the measuring point of the pulmonary artery caliber.
In some embodiments of the present application, the obtaining the main pulmonary artery centerline valid segment and the main pulmonary artery boundary based on the optimal segmentation level in the segmentation result of the lung image comprises: determining an optimal segmentation level based on gray values of pixel points in a bifurcation point segmentation result included by the segmentation result, wherein the optimal segmentation level comprises a pulmonary artery region and a bifurcation point region; determining a pulmonary artery central line of the pulmonary artery region based on a central line extraction algorithm; determining a branch point of the pulmonary artery midline based on the pulmonary artery midline; based on the branching point of the pulmonary artery midline and the pulmonary artery midline, the main pulmonary artery midline effective segment and the main pulmonary artery boundary are determined.
In some embodiments of the present application, determining the main pulmonary artery centerline valid segment and the main pulmonary artery boundary based on the branch point of the pulmonary artery centerline and the pulmonary artery centerline comprises: obtaining a main pulmonary artery midline, a left pulmonary artery midline and a right pulmonary artery midline based on a branch point of the pulmonary artery midline and the pulmonary artery midline; taking part of the central line of the main pulmonary artery with a preset distance from the central point of the bifurcation point area as an effective section of the central line of the main pulmonary artery; respectively making a vertical line from the central point of the bifurcation point region to the central line of the left pulmonary artery and the central line of the right pulmonary artery, and determining the entrance of the left pulmonary artery and the entrance of the right pulmonary artery; and obtaining a main pulmonary artery boundary based on the pulmonary artery segmentation result, the left branch pulmonary artery inlet and the right branch pulmonary artery inlet which are included in the segmentation result.
In a second aspect, an embodiment of the present application provides an image processing method, including: obtaining a measuring point of the pulmonary artery caliber based on the caliber measuring method of the first aspect; determining a measurement point of the aortic diameter based on the optimal segmentation level; and judging whether pulmonary artery high pressure exists or not based on a pulmonary artery caliber measuring line determined by the pulmonary artery caliber measuring point and an aorta caliber measuring line determined by the aorta caliber measuring point.
In some embodiments of the present application, determining the measurement point of the aortic diameter based on the optimal segmentation level comprises: determining a center point of the aorta region based on an optimal segmentation level, wherein the optimal segmentation level comprises the aorta region and an aorta boundary; determining a plurality of line segments passing through the center point of the aorta region and intersecting with the aorta boundary based on the center point of the aorta region; and taking two intersection points of the line segment with the minimum length in the plurality of line segments and the aorta boundary as measurement points of the aorta diameter.
In some embodiments of the present application, determining whether pulmonary hypertension exists based on a measurement line of pulmonary artery caliber determined by a measurement point of pulmonary artery caliber and a measurement line of aorta caliber determined by a measurement point of aorta caliber comprises: comparing the measuring line of the pulmonary artery caliber with a first preset threshold value to obtain a first comparison result; comparing the ratio of the measuring line of the pulmonary artery caliber to the measuring line of the aorta caliber with a second preset threshold value to obtain a second comparison result; based on the first comparison result and the second comparison result, it is determined whether pulmonary hypertension is present.
In a third aspect, an embodiment of the present application provides a caliber measuring device for a lung image, the device including: the first acquisition module is used for acquiring a main pulmonary artery central line effective section and a main pulmonary artery boundary based on an optimal segmentation level in a segmentation result of a lung image; the determining module is used for determining a plurality of vertical line segments by taking a plurality of pixel points on the effective segment of the central line of the main pulmonary artery as the vertical feet; and the second acquisition module is used for acquiring the measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary.
In a fourth aspect, an embodiment of the present application provides an image processing apparatus, including: an obtaining module, configured to obtain a measurement point of a pulmonary artery caliber based on the caliber measurement method according to the first aspect; the first determination module is used for determining a measurement point of the aortic diameter based on the optimal segmentation level; and the second determination module is used for determining whether pulmonary artery high pressure exists or not based on the measurement line of the pulmonary artery caliber determined by the measurement point of the pulmonary artery caliber and the measurement line of the aorta caliber determined by the measurement point of the aorta caliber.
In a fifth aspect, an embodiment of the present application provides an electronic device, including: a processor; a memory for storing processor executable instructions, wherein the processor is adapted to perform the lung image method according to the first aspect or to perform the image processing method according to the second aspect.
The embodiment of the application provides a method and a device for measuring the caliber of a lung image, and a method and a device for processing the image. Meanwhile, the measuring accuracy of the measuring line (or point) of the pulmonary artery caliber is also ensured by selecting one vertical line segment from the plurality of vertical line segments through the effective segment of the central line of the main pulmonary artery and the plurality of vertical line segments.
Drawings
Fig. 1 is a schematic flow chart of a method for measuring a caliber of a lung image according to an exemplary embodiment of the present application.
Fig. 2 is a schematic diagram of an optimal segmentation level of a lung image provided by an exemplary embodiment of the present application.
Fig. 3 is a flowchart illustrating a method for measuring a caliber of a lung image according to another exemplary embodiment of the present application.
Fig. 4 is a flowchart illustrating a method for measuring a caliber of a lung image according to another exemplary embodiment of the present application.
Fig. 5 is a flowchart illustrating an image processing method according to an exemplary embodiment of the present application.
Fig. 6 is a flowchart illustrating an image processing method according to another exemplary embodiment of the present application.
Fig. 7 is a flowchart illustrating an image processing method according to another exemplary embodiment of the present application.
Fig. 8 is a schematic structural diagram of a caliber measuring device for lung images provided by an exemplary embodiment of the present application.
Fig. 9 is a schematic structural diagram of an image processing apparatus according to an exemplary embodiment of the present application.
Fig. 10 is a block diagram of an electronic device for caliber measurement or image processing of lung images provided by an exemplary embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic flow chart of a method for measuring a caliber of a lung image according to an exemplary embodiment of the present application. The method of fig. 1 is performed by a computing device, e.g., a server. As shown in fig. 1, the pipe diameter measuring method includes the following steps.
110: and acquiring a central line effective section of the main pulmonary artery and a boundary of the main pulmonary artery based on the optimal segmentation level in the segmentation result of the lung image.
Specifically, the lung image data is input into a segmentation model trained in advance for image segmentation to obtain a segmentation result, wherein the segmentation result is a 3D image. The segmentation results include aorta segmentation results, pulmonary artery segmentation results, and bifurcation point segmentation results.
And then, intercepting the layer of the preset thickness in the segmentation result, wherein the preset range is not specifically limited in the embodiment of the application, and calculating the gray value of each pixel point included in the bifurcation segmentation result by a maximum density projection method in the intercepted preset thickness. The segmentation level containing the largest gray values is taken as the optimal segmentation level, wherein the optimal segmentation level is the 2D image, and the optimal segmentation level (see, e.g., fig. 2) includes a pulmonary artery region, an aorta region, and a bifurcation point region.
And determining the pulmonary artery midline based on the obtained optimal segmentation level. Specifically, obtaining the pulmonary artery centerline of the pulmonary artery region in the optimal segmentation level may first extract the first pulmonary artery centerline using a centerline extraction algorithm, such as a thinning algorithm, which performs simpletik. And then, performing a smoothing operation on the first pulmonary artery centerline obtained based on the centerline extraction algorithm to obtain a second pulmonary artery centerline (i.e. the pulmonary artery centerline), wherein the smoothing operation mode can be calculated by using a smoothing algorithm.
And thirdly, classifying each pixel point on the centerline of the pulmonary artery according to the degree. The pixel points with the degree of 1 are divided into end points, the pixel points with the degree of 3 and above are divided into branch points of the pulmonary artery central line, and the pixel points between the end points and the branch points of the pulmonary artery central line are divided into path points. Detecting each pixel point on the pulmonary artery midline, and checking whether a branch point of the pulmonary artery midline with the degree of 3 and a certain length satisfied from an end point exists. The certain length may be a proportional value, for example, the length of the branch point from the middle line of the pulmonary artery accounts for 20% of the total length of the middle line of the pulmonary artery, and the certain length may also be a fixed value, which is not specifically limited in this embodiment of the present application. Illustratively, the shape of the pulmonary artery midline resembles a shape of a "human", and the branching point of the pulmonary artery midline corresponds to the intersection of the left-falling and right-falling strokes of the "human".
It should be noted that, after detecting each pixel point on the pulmonary artery centerline, if no pixel point with a degree of 3 is detected, that is, no branch point of the pulmonary artery centerline is detected, the preset thickness of the segmentation result is replaced, and the above operations are repeatedly performed until the branch point of the pulmonary artery centerline is determined.
And then, based on the branch point of the pulmonary artery midline and the pulmonary artery midline, obtaining a main pulmonary artery midline, a left pulmonary artery midline and a right pulmonary artery midline. And taking the part of the central line of the main pulmonary artery with a preset distance from the central point of the bifurcation point area as an effective section of the central line of the main pulmonary artery. And respectively making a perpendicular line for the central point of the bifurcation point region to the central line of the left pulmonary artery and the central line of the right pulmonary artery, and determining the entrance of the left pulmonary artery and the entrance of the right pulmonary artery. And obtaining a main pulmonary artery boundary based on the pulmonary artery segmentation result, the left branch pulmonary artery inlet and the right branch pulmonary artery inlet which are included in the segmentation result. Please refer to the description of the embodiment in fig. 4 for details, which are not repeated herein to avoid redundancy.
It should be noted that, referring to fig. 2, the main pulmonary artery midline effective segment OA1 can also be referred to as main pulmonary artery midline proximal segment OA 1. The main pulmonary artery midline effective segment OA1 (or the main pulmonary artery midline proximal segment OA1) may be a partial segment of the main pulmonary artery midline (e.g., the dashed line in the shape of a herringbone in fig. 2). On the central line OA of the main pulmonary artery, point a1 is located at a predetermined distance (e.g., 3cm) from the central point P of the bifurcation area. That is, the main pulmonary artery central line effective section OA1 may be a line segment between the branching point O of the pulmonary artery central line and the position point a1 located at a predetermined distance from the center point P of the branching point region on the main pulmonary artery central line OA.
120: and determining a plurality of vertical line segments by taking a plurality of pixel points on the central line effective segment of the main pulmonary artery as the vertical feet.
Specifically, each pixel point on the central line effective segment of the main pulmonary artery is scanned according to a preset sequence, or the pixel points on the central line effective segment of the main pulmonary artery are scanned according to a preset rule, for example, the scanning is performed at intervals of one pixel. The preset sequence may be from top to bottom or from bottom to top, which is not specifically limited in the embodiments of the present application.
And then, determining a plurality of vertical lines which take each pixel point as a foot and are vertical to the central line direction of the pixel point according to each pixel point on the central line effective section of the main pulmonary artery and the central line direction of the pixel point. The central line direction of the pixel point can be calculated based on the current position of the pixel point and the adjacent position relationship with other pixel points, for example, the tangential direction of the current position and the adjacent position of the pixel point is taken as the central line direction of the pulmonary artery central line of the pixel point at the current position, so as to ensure that each pixel point on the central line effective segment of the main pulmonary artery is located at the central line position.
And determining a plurality of vertical line segments based on the main pulmonary artery boundary in the optimal segmentation level, wherein two end points of the vertical line segments are two intersection points of the vertical line and the main pulmonary artery boundary.
130: and acquiring a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary.
Specifically, two intersection points of the vertical line segment with the maximum segment length and the main pulmonary artery boundary, which are not intersected with the left pulmonary artery entrance and the right pulmonary artery entrance of the optimal segmentation level, in the multiple vertical line segments are used as the measuring points of the pulmonary artery caliber.
Or, the vertical line segment which is not intersected with the left pulmonary artery inlet and the right pulmonary artery inlet of the optimal segmentation level and has the largest segment length is taken as the measuring line of the pulmonary artery caliber.
It should be noted that, due to the limitation of the data transmission protocol of the port, the embodiment of the present application preferably selects the measurement point for obtaining the pulmonary artery caliber, so as to increase the speed of data transmission.
Therefore, the embodiment of the application selects the two-dimensional optimal segmentation level from the three-dimensional segmentation result, so that the calculation efficiency is improved, and the subsequent processing steps only depend on the segmentation result, so that the robustness is also improved. Meanwhile, the measurement precision of the pipe diameter measurement line (or point) is also ensured by selecting one vertical line segment from the plurality of vertical line segments through the effective segment of the central line of the main pulmonary artery and the plurality of vertical line segments.
In an embodiment of the present application, based on a plurality of vertical segments and a main pulmonary artery boundary, obtaining a measurement point of a pulmonary artery caliber includes: and taking the intersection point of the vertical line segment which is not intersected with the left pulmonary artery inlet and the right pulmonary artery inlet and has the maximum line segment length and the main pulmonary artery boundary as the measuring point of the pulmonary artery caliber.
Specifically, two intersection points of the vertical line segment with the maximum line segment length and the main pulmonary artery boundary, which do not intersect with the left pulmonary artery entrance (or the left pulmonary artery region) and the right pulmonary artery entrance (or the right pulmonary artery region) in the optimal segmentation level, are used as the measuring points of the pulmonary artery caliber. For example, referring to fig. 2, pulmonary artery caliber measurement points are P1 and P2.
Alternatively, the vertical line segment which does not intersect the left pulmonary artery entrance and the right pulmonary artery entrance in the optimal segmentation level and has the largest segment length is taken as the measurement line of the pulmonary artery caliber, for example, see the measurement line P1P2 of the pulmonary artery caliber in fig. 2.
Therefore, the longest vertical line segment is selected or the intersection point of the longest vertical line segment and the aorta boundary is selected to serve as the measuring line or the measuring point of the pulmonary artery caliber, and the condition that the measuring point of the pulmonary artery caliber is not accurately positioned due to the fact that the selected measuring line of the pulmonary artery caliber is too short is avoided.
Fig. 3 is a flowchart illustrating a method for measuring a caliber of a lung image according to another exemplary embodiment of the present application. The embodiment of fig. 3 is an example of the embodiment of fig. 1, and the same parts are not repeated herein, and the differences are mainly described here. As shown in fig. 3, the pipe diameter measuring method includes the following steps.
210: and determining the optimal segmentation level based on the gray values of the pixel points in the bifurcation segmentation result included in the segmentation result.
In an embodiment, the optimal segmentation level comprises a pulmonary artery region and a bifurcation point region.
Specifically, the lung image is input into a segmentation model trained in advance for image segmentation to obtain a segmentation result, wherein the segmentation result is a 3D image. The segmentation result comprises an aorta segmentation result, a pulmonary artery segmentation result and a bifurcation point segmentation result.
And then, intercepting the layer with the preset thickness from the obtained segmentation result, wherein the preset range is not specifically limited in the embodiment of the application. And in the intercepted preset thickness, calculating the gray value of each pixel point included in the bifurcation point segmentation result by a maximum density projection method. And taking the segmentation level containing the maximum gray value as an optimal segmentation level, wherein the optimal segmentation level is a 2D image and comprises a pulmonary artery area, an aorta area and a bifurcation point area.
220: a pulmonary artery centerline of the pulmonary artery region is determined based on a centerline extraction algorithm.
Specifically, first, a first pulmonary artery centerline of the pulmonary artery region may be determined based on a centerline extraction algorithm, for example, a thinning algorithm of simpletik is performed to extract the first pulmonary artery centerline. And then, performing smoothing operation on the extracted first pulmonary artery central line to obtain a second pulmonary artery central line of the smoothed pulmonary artery region, wherein the smoothing operation mode can be calculated by adopting a smoothing algorithm, and the smoothing operation mode is not specifically limited in the embodiment of the application. And, the second pulmonary artery centerline is defined as the pulmonary artery centerline described in this application, such as the dashed line of the herringbone in fig. 2.
230: based on the pulmonary artery centerline, a branch point of the pulmonary artery centerline is determined.
In particular, each pixel point on the scan-smoothed pulmonary artery centerline (i.e., the second pulmonary artery centerline) may be classified by degree to determine a branching point of the pulmonary artery centerline.
In one example, the pixels with the degree of 1 are divided into end points, the pixels with the degree of 3 and above are divided into branch points of the pulmonary artery central line, and the pixels between the end points and the branch points of the pulmonary artery central line are divided into path points. Detecting each pixel point on the pulmonary artery midline, and checking whether a branch point of the pulmonary artery midline with the degree of 3 and a certain length satisfied from an end point exists. The certain length may be a proportional value, for example, the length of the branch point from the middle line of the pulmonary artery accounts for 20% of the total length of the middle line of the pulmonary artery, and the certain length may also be a fixed value, which is not specifically limited in this embodiment of the present application. Illustratively, the shape of the pulmonary artery midline resembles a shape of a "human", and the branching point of the pulmonary artery midline corresponds to the intersection of the left-falling and right-falling strokes of the "human".
It should be noted that, after detecting each pixel point on the pulmonary artery centerline, if no pixel point with a degree of 3 is detected, that is, no branch point of the pulmonary artery centerline is detected, the preset thickness of the segmentation result may be replaced, and the operations in steps 210 to 240 are repeatedly performed until the branch point of the pulmonary artery centerline is determined.
240: based on the branching point of the pulmonary artery midline and the pulmonary artery midline, the main pulmonary artery midline effective segment and the main pulmonary artery boundary are determined. It should be noted that, please refer to the description of the embodiment in fig. 4 for details of the description of step 250, which is not repeated herein to avoid repetition.
250: and determining a plurality of vertical line segments by taking a plurality of pixel points on the central line effective segment of the main pulmonary artery as the vertical feet.
260: and acquiring a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary.
Therefore, the embodiment of the application selects the two-dimensional optimal segmentation level from the three-dimensional segmentation result, so that the calculation efficiency is improved, and the robustness is also improved because the processing steps only depend on the segmentation result.
Fig. 4 is a flowchart illustrating a method for measuring a caliber of a lung image according to another exemplary embodiment of the present application. The embodiment of fig. 4 is an example of the embodiment of fig. 1, and the same parts are not described again, and the differences are mainly described here. As shown in fig. 4, the pipe diameter measuring method includes the following steps.
310: based on the branching point of the pulmonary artery midline and the pulmonary artery midline, a main pulmonary artery midline, a left pulmonary artery midline and a right pulmonary artery midline are obtained.
Specifically, the pulmonary artery centerline is the centerline of the pulmonary artery region in the optimal segmentation level, e.g., the pulmonary artery centerline resembles a "herringbone". The pulmonary artery region may include a main pulmonary artery, a left pulmonary artery, and a right pulmonary artery. Thus, the branching point of the pulmonary artery midline may divide the pulmonary artery midline into three segments, i.e., a main pulmonary artery midline, a left pulmonary artery midline, and a right pulmonary artery midline, e.g., see fig. 2, a branching point O of the pulmonary artery midline, a main pulmonary artery midline OA, a left pulmonary artery midline OC, and a right pulmonary artery midline OB.
320: and taking the part of the central line of the main pulmonary artery with a preset distance from the central point of the bifurcation point area as an effective section of the central line of the main pulmonary artery.
Specifically, the centerline direction of the pulmonary artery centerline where each pixel point is located on the pulmonary artery centerline can be calculated according to the pulmonary artery centerline, so that each pixel point is ensured to fall on the centerline position. The central line direction may be calculated based on the current position of the pixel and the adjacent position relationship with other pixels, for example, the tangential direction of the current position and the adjacent position of the pixel is taken as the central line direction of the pulmonary artery central line of the pixel at the current position.
And then, calculating the central point of the bifurcation point area contained in the optimal segmentation level. On the main pulmonary artery midline, calculating an effective position point which is away from the central point of the bifurcation point area by a preset distance, wherein the preset distance can be 3cm, and the embodiment of the application does not specifically limit the preset distance. The portion between the position point of the preset distance on the central line of the main pulmonary artery and the branch point of the central line is used as the effective segment of the central line of the main pulmonary artery, such as icon OA1 in fig. 2.
330: and respectively making a perpendicular line for the central point of the bifurcation point region to the central line of the left pulmonary artery and the central line of the right pulmonary artery, and determining the entrance of the left pulmonary artery and the entrance of the right pulmonary artery.
Specifically, a central point of the bifurcation point region is taken as a perpendicular line to a centerline of the left pulmonary artery, and a line segment of a portion where the perpendicular line intersects with a boundary of the pulmonary artery is taken as an entrance of the left pulmonary artery, such as an icon PL in fig. 2. The central point of the bifurcation point region is taken as a perpendicular line to the centerline of the right branch pulmonary artery, and a line segment of the intersection part of the perpendicular line and the pulmonary artery boundary is taken as the entrance of the right branch pulmonary artery, such as the icon PR in fig. 2.
340: and obtaining a main pulmonary artery boundary based on the pulmonary artery segmentation result, the left branch pulmonary artery inlet and the right branch pulmonary artery inlet which are included in the segmentation result.
In particular, the segmentation results include pulmonary artery segmentation results having pulmonary artery boundaries. Based on the pulmonary artery boundary, the left pulmonary artery entrance and the right pulmonary artery entrance, three segmented pulmonary artery regions can be obtained, namely a main pulmonary artery region (e.g., the main pulmonary artery region S1 in fig. 2) and a main pulmonary artery boundary, a left pulmonary artery region (e.g., the left pulmonary artery region S3 in fig. 2) and a left pulmonary artery boundary, and a right pulmonary artery region (e.g., the right pulmonary artery region S2 in fig. 2) and a right pulmonary artery boundary.
Therefore, the embodiment of the application facilitates the subsequent determination of the measuring point (or line) of the pulmonary artery caliber by determining the entrance of the left pulmonary artery and the entrance of the right pulmonary artery.
Fig. 5 is a flowchart illustrating an image processing method according to an exemplary embodiment of the present application. The method of fig. 5 is performed by a computing device, e.g., a server. As shown in fig. 5, the image processing method includes the following.
410: and obtaining a measuring point of the pulmonary artery caliber based on a caliber measuring method.
In an embodiment, the pipe diameter measuring method is the pipe diameter measuring method described in the above embodiments of fig. 1 to 4.
420: and determining the measurement point of the aortic diameter based on the optimal segmentation level.
Specifically, a center point (or centroid) of the aorta region is determined based on an optimal segmentation level, wherein the optimal segmentation level includes the aorta region and an aorta boundary; determining a plurality of line segments passing through the center point of the aorta region and intersecting with the aorta boundary based on the center point of the aorta region; and taking two intersection points of the line segment with the minimum length in the plurality of line segments and the aorta boundary as measurement points of the aorta diameter.
430: and judging whether pulmonary artery high pressure exists or not based on a pulmonary artery caliber measuring line determined by the pulmonary artery caliber measuring point and an aorta caliber measuring line determined by the aorta caliber measuring point.
Specifically, two pulmonary artery caliber measuring points are connected to determine a pulmonary artery caliber measuring line. Connecting the measuring points of the aorta caliber, and determining the measuring line of the aorta caliber.
Then, comparing the measuring line of the pulmonary artery caliber with a first preset threshold value to obtain a first comparison result; comparing the ratio of the length of the measuring line of the pulmonary artery caliber to the length of the measuring line of the aorta caliber with a second preset threshold value to obtain a second comparison result; based on the first comparison result and the second comparison result, it is determined whether pulmonary hypertension is present. Please refer to the record in the embodiment of fig. 7 for details of the detailed description of step 430, which is not repeated herein to avoid repetition.
Therefore, a set of complete system for judging the pulmonary artery high pressure is established in the embodiment of the application, the judgment result of the pulmonary artery high pressure is also given on the basis of a relatively objective measurement line for measuring the diameter of the pulmonary artery and a relatively objective measurement line for measuring the diameter of the aorta, and the efficiency of judging the pulmonary artery high pressure is improved.
Fig. 6 is a flowchart illustrating an image processing method according to another exemplary embodiment of the present application. The embodiment of fig. 6 is an example of the embodiment of fig. 5, and the same parts are not repeated, and the differences are mainly described here. As shown in fig. 6, the image processing method includes the following.
510: and obtaining a measuring point of the pulmonary artery caliber based on a caliber measuring method.
In an embodiment, the pipe diameter measuring method is the pipe diameter measuring method described in the above embodiments of fig. 1 to 4.
520: the central point of the aortic region is determined based on the optimal segmentation level.
In one embodiment, the optimal segmentation level includes the aorta region and the aorta boundary.
Specifically, referring to fig. 2, the optimal segmentation level includes an aorta region S4, and a center point (or centroid) D of the aorta region is calculated, where an algorithm for calculating the center point may be used to calculate the center point, and the calculation manner of the center point is not particularly limited in the embodiments of the present application.
530: based on the center point of the aorta region, a plurality of line segments passing through the center point of the aorta region and intersecting the aorta boundary are determined.
In particular, the optimal segmentation level includes the aorta boundary, such as the boundary of the aorta region S4 in fig. 2. And (4) counting a plurality of straight lines with any angle when passing through the central point of the aorta area. Based on the plurality of straight lines, a plurality of line segments intersecting the aorta boundary are determined.
540: and taking two intersection points of the line segment with the minimum length in the plurality of line segments and the aorta boundary as measurement points of the aorta diameter.
Specifically, referring to fig. 2, two intersection points, i.e., P3, P4, at which the line segment P3P4 having the smallest length among the plurality of line segments intersects with the aorta boundary are taken as the measurement points of the aortic diameter.
It should be noted that, since the aorta contracts correspondingly with the contraction and pulsation of the heart, the line segment with the minimum segment length is selected to predict the pulmonary artery high pressure in the embodiment of the present application, so as to avoid the problem that the measurement point of the aortic diameter is selected inaccurately due to aorta edge contrast caused by aortic contraction.
550: and judging whether pulmonary artery high pressure exists or not based on a pulmonary artery caliber measuring line determined by the pulmonary artery caliber measuring point and an aorta caliber measuring line determined by the aorta caliber measuring point.
It should be understood that fig. 2 may be represented as the best segmentation level containing the processing results. As shown in fig. 2, this fig. 2 includes a pulmonary artery region and an aortic region. Wherein the pulmonary artery region comprises: a branch point O of the pulmonary artery midline, a main pulmonary artery area S1, a main pulmonary artery midline OA and a main pulmonary artery midline effective section OA1, a left pulmonary artery area S3, a left pulmonary artery inlet PL, a left pulmonary artery midline OC, a right pulmonary artery area S2, a right pulmonary artery inlet PR, a right pulmonary artery midline OB, and pulmonary artery caliber measuring points P1 and P2. The aorta region S4 includes: the center point (or centroid) D of the aortic region, the measurement points of the aortic caliber P3 and P4.
Therefore, the shortest line segment of the central point of the aorta passing region is used as the measuring point of the aorta diameter in the embodiment of the application, and the problem that the measuring point for determining the aorta diameter is inaccurate due to aorta contraction is avoided.
Fig. 7 is a flowchart illustrating an image processing method according to another exemplary embodiment of the present application. The embodiment of fig. 7 is an example of the embodiment of fig. 4, and the same parts are not repeated, and the differences are mainly described here. As shown in fig. 7, the image processing method includes the following.
610: and obtaining a measuring point of the pulmonary artery caliber based on a caliber measuring method.
In an embodiment, the pipe diameter measuring method is the pipe diameter measuring method described in the above embodiments of fig. 1 to 4.
620: and determining the measurement point of the aortic diameter based on the optimal segmentation level.
630: and comparing the measuring line of the pulmonary artery caliber with a first preset threshold value to obtain a first comparison result.
Specifically, on the flat-scan image, the first preset threshold may be 33 cm. In the enhanced image, the first predetermined threshold may be 29cm, and the specific values of the first predetermined threshold are not particularly limited in the embodiments of the present application.
In an example, when the measurement line of the pulmonary artery caliber is greater than a first preset threshold, the first comparison result may be a suspected pulmonary artery high pressure; when the measurement line of the pulmonary artery caliber is smaller than a first preset threshold value, the first comparison result can be non-suspected pulmonary artery high pressure.
640: and comparing the ratio of the measuring line of the pulmonary artery caliber to the measuring line of the aorta caliber with a second preset threshold value to obtain a second comparison result.
Specifically, when the length ratio of the measuring line of the pulmonary artery caliber to the measuring line of the aorta caliber is greater than a second preset threshold, the second comparison result may be suspected pulmonary artery high pressure; when the length ratio of the measuring line of the pulmonary artery caliber to the measuring line of the aorta caliber is smaller than a second preset threshold, the second comparison result can be non-suspected pulmonary artery high pressure. The second preset threshold may be 1, which is not specifically limited in this embodiment of the present application.
650: based on the first comparison result and the second comparison result, it is determined whether pulmonary hypertension is present.
Specifically, when the first comparison result and the second comparison result are both non-suspected pulmonary hypertension, it is determined that there is no pulmonary hypertension. And when any one of the first comparison result and the second comparison result is the suspected pulmonary arterial hypertension, or when the first comparison result and the second comparison result are both the suspected pulmonary arterial hypertension, determining that the pulmonary arterial hypertension exists.
Therefore, the embodiment of the application determines whether the pulmonary hypertension exists or not through the two comparison results, and the accuracy of the pulmonary hypertension prediction is improved.
Fig. 8 is a schematic structural diagram of a caliber measuring device for lung images provided by an exemplary embodiment of the present application. As shown in fig. 8, the pipe diameter measuring apparatus 700 includes: a first acquisition module 710, a determination module 720, and a second acquisition module 730.
The first obtaining module 710 is configured to obtain a central line valid segment of a main pulmonary artery and a boundary of the main pulmonary artery based on an optimal segmentation level in a segmentation result of a lung image; the determining module 720 is configured to determine a plurality of vertical segments by using a plurality of pixel points on the central line effective segment of the main pulmonary artery as the vertical feet; the second obtaining module 730 is configured to obtain a measurement point of the pulmonary artery caliber based on the plurality of vertical segments and the main pulmonary artery boundary.
The embodiment of the application provides a device for measuring the caliber of a lung image, the two-dimensional optimal segmentation level is selected from three-dimensional segmentation results, the calculation efficiency is improved, the subsequent processing steps only depend on the segmentation results, and the robustness is also improved. Meanwhile, the measurement precision of the pipe diameter measurement line (or point) is also ensured by selecting one vertical line segment from the plurality of vertical line segments through the effective segment of the central line of the main pulmonary artery and the plurality of vertical line segments.
According to an embodiment of the present application, the second obtaining module 730 is configured to use an intersection point of a vertical line segment that does not intersect with the left pulmonary artery entrance and the right pulmonary artery entrance and has the largest segment length and the main pulmonary artery boundary as a measurement point of the pulmonary artery caliber.
According to an embodiment of the present application, the first obtaining module 710 is configured to determine an optimal segmentation level based on gray-scale values of pixel points in a bifurcation segmentation result included in the segmentation result, where the optimal segmentation level includes a pulmonary artery region and a bifurcation region; determining a pulmonary artery central line of the pulmonary artery region based on a central line extraction algorithm; determining a branch point of the pulmonary artery midline based on the pulmonary artery midline; based on the branching point of the pulmonary artery midline and the pulmonary artery midline, the main pulmonary artery midline effective segment and the main pulmonary artery boundary are determined.
According to an embodiment of the present application, the first obtaining module 710 is further configured to obtain a main pulmonary artery centerline, a left pulmonary artery centerline, and a right pulmonary artery centerline based on a branch point of the pulmonary artery centerline and the pulmonary artery centerline; taking part of the central line of the main pulmonary artery with a preset distance from the central point of the bifurcation point area as an effective section of the central line of the main pulmonary artery; respectively making a vertical line from the central point of the bifurcation point region to the central line of the left pulmonary artery and the central line of the right pulmonary artery, and determining the entrance of the left pulmonary artery and the entrance of the right pulmonary artery; and obtaining a main pulmonary artery boundary based on the pulmonary artery segmentation result, the left branch pulmonary artery inlet and the right branch pulmonary artery inlet which are included in the segmentation result.
It should be understood that the specific working processes and functions of the first obtaining module 710, the determining module 720 and the second obtaining module 730 in the above embodiments may refer to the description in the caliber measurement of the lung image provided in the above embodiments of fig. 1 to 4, and are not described herein again to avoid repetition.
Fig. 9 is a schematic structural diagram of an image processing apparatus according to an exemplary embodiment of the present application. As shown in fig. 9, the pipe diameter measuring apparatus 800 includes: an obtaining module 810, a first determining module 820, and a second determining module 830.
The obtaining module 810 is configured to obtain a measurement point of the pulmonary artery caliber based on a caliber measurement method; the first determination module 820 is used for determining the measurement point of the aortic diameter based on the optimal segmentation level; the second determination module 830 is configured to determine whether there is pulmonary hypertension based on a pulmonary artery diameter measurement line determined by the pulmonary artery diameter measurement point and an aortic diameter measurement line determined by the aortic diameter measurement point
The embodiment of the application provides an image processing device, and a complete system for judging pulmonary artery high pressure is established, so that on the basis of a relatively objective measuring line for measuring the diameter of a pulmonary artery and a measuring line for measuring the diameter of an aorta, a judgment result of the pulmonary artery high pressure is also provided, and the efficiency of judging the pulmonary artery high pressure is improved.
According to an embodiment of the present application, the first determination module 820 is configured to determine a center point of the aorta region based on an optimal segmentation level, wherein the optimal segmentation level comprises the aorta region and an aorta boundary; determining a plurality of line segments passing through the center point of the aorta region and intersecting with the aorta boundary based on the center point of the aorta region; and taking two intersection points of the line segment with the minimum length in the plurality of line segments and the aorta boundary as measurement points of the aorta diameter.
According to an embodiment of the present application, the second determining module 830 is configured to compare the measurement line of the pulmonary artery caliber with a first preset threshold to obtain a first comparison result; comparing the ratio of the measuring line of the pulmonary artery caliber to the measuring line of the aorta caliber with a second preset threshold value to obtain a second comparison result; based on the first comparison result and the second comparison result, it is determined whether pulmonary hypertension is present.
It should be understood that the specific working processes and functions of the obtaining module 810, the first determining module 820 and the second determining module 830 in the above embodiments may refer to the description in the caliber measurement of the lung image provided in the above embodiments of fig. 5 to 6, and are not described herein again to avoid repetition.
Fig. 10 is a block diagram of an electronic device 900 for caliber measurement or image processing of lung images provided by an exemplary embodiment of the present application.
Referring to fig. 10, electronic device 900 includes a processing component 910 that further includes one or more processors, and memory resources, represented by memory 920, for storing instructions, such as applications, that are executable by processing component 910. The application programs stored in memory 920 may include one or more modules that each correspond to a set of instructions. Further, the processing component 910 is configured to execute instructions to perform the pipe diameter measuring method or the image processing method described above.
The electronic device 900 may also include a power component configured to perform power management for the electronic device 900, a wired or wireless network interface configured to connect the electronic device 900 to a network, and an input-output (I/O) interface. The electronic device 900 may be operated based on an operating system, such as Windows Server, stored in the memory 920TM，Mac OS XTM，UnixTM，LinuxTM，FreeBSDTMOr the like.
A non-transitory computer readable storage medium, wherein instructions of the storage medium, when executed by a processor of the electronic device 600, enable the electronic device 900 to perform a method for caliber measurement or image processing of images of lungs, comprising: acquiring a main pulmonary artery central line effective section and a main pulmonary artery boundary based on an optimal segmentation level in a segmentation result of a lung image; a plurality of pixel points on the central line effective section of the main pulmonary artery are used as the drop feet, and a plurality of vertical line sections are determined; and acquiring a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary.
Or obtaining a measuring point of the pulmonary artery caliber based on the caliber measuring method of the first aspect; determining a measurement point of the aortic diameter based on the optimal segmentation level; and judging whether pulmonary artery high pressure exists or not based on a pulmonary artery caliber measuring line determined by the pulmonary artery caliber measuring point and an aorta caliber measuring line determined by the aorta caliber measuring point.
All the above optional technical solutions can be combined arbitrarily to form optional embodiments of the present application, and are not described herein again.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program check codes, such as a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in the description of the present application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modifications, equivalents and the like that are within the spirit and principle of the present application should be included in the scope of the present application.

Claims (9)

1. A method for measuring the caliber of a lung image is characterized by comprising the following steps:
acquiring a main pulmonary artery central line effective section and a main pulmonary artery boundary based on an optimal segmentation level in a segmentation result of a lung image;
a plurality of pixel points on the central line effective section of the main pulmonary artery are used as a drop foot, and a plurality of drop line sections are determined;
obtaining a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary,
wherein, the obtaining of the main pulmonary artery central line effective segment and the main pulmonary artery boundary based on the optimal segmentation level in the segmentation result of the lung image comprises:
determining the optimal segmentation level based on the gray values of pixel points in the bifurcation point segmentation result included in the segmentation result, wherein the optimal segmentation level comprises a pulmonary artery region and a bifurcation point region; determining a pulmonary artery centerline of the pulmonary artery region based on a centerline extraction algorithm; determining a branch point of the pulmonary artery midline based on the pulmonary artery midline; determining the main pulmonary artery midline valid segment and the main pulmonary artery boundary based on the branch point of the pulmonary artery midline and the pulmonary artery midline.
2. The method according to claim 1, wherein said obtaining a measurement point of pulmonary artery caliber based on said plurality of vertical segments and said main pulmonary artery boundary comprises:
and taking the intersection point of the vertical line segment which is not intersected with the left pulmonary artery inlet and the right pulmonary artery inlet and has the maximum line segment length and the main pulmonary artery boundary as the measuring point of the pulmonary artery caliber.
3. The method for caliber measurement according to claim 1, wherein the determining the main pulmonary artery midline effective segment and the main pulmonary artery boundary based on the branch point of the pulmonary artery midline and the pulmonary artery midline comprises:
obtaining a main pulmonary artery midline, a left pulmonary artery midline and a right pulmonary artery midline based on a branch point of the pulmonary artery midline and the pulmonary artery midline;
taking a part of the central line of the main pulmonary artery with a preset distance from the central point of the bifurcation point area as an effective section of the central line of the main pulmonary artery;
respectively making a vertical line from the central point of the bifurcation point region to the midline of the left pulmonary artery and the midline of the right pulmonary artery, and determining the entrance of the left pulmonary artery and the entrance of the right pulmonary artery;
obtaining the main pulmonary artery boundary based on the pulmonary artery segmentation result, the left pulmonary artery entrance and the right pulmonary artery entrance.
4. An image processing method, comprising:
obtaining a measurement point of the pulmonary artery caliber based on the caliber measuring method according to any one of claims 1 to 3;
determining a measurement point of the aortic diameter based on the optimal segmentation level;
and judging whether pulmonary artery high pressure exists or not based on a pulmonary artery caliber measuring line determined by the pulmonary artery caliber measuring point and an aorta caliber measuring line determined by the aorta caliber measuring point.
5. The image processing method according to claim 4, wherein the determining the measurement point of the aortic diameter based on the optimal segmentation level comprises:
determining a center point of an aorta region based on the optimal segmentation level, wherein the optimal segmentation level comprises the aorta region and an aorta boundary;
determining a plurality of line segments passing through the center point of the aorta region and intersecting the aorta boundary based on the center point of the aorta region;
and taking two intersection points of the line segment with the minimum length in the plurality of line segments and the aorta boundary as measurement points of the aorta caliber.
6. The image processing method according to claim 4, wherein the determining whether pulmonary hypertension exists or not based on the measurement line of the pulmonary artery caliber determined by the measurement point of the pulmonary artery caliber and the measurement line of the aorta caliber determined by the measurement point of the aorta caliber comprises:
comparing the measuring line of the pulmonary artery caliber with a first preset threshold value to obtain a first comparison result;
comparing the ratio of the measuring line of the pulmonary artery caliber to the measuring line of the aorta caliber with a second preset threshold value to obtain a second comparison result;
determining whether pulmonary hypertension is present based on the first comparison result and the second comparison result.
7. A caliber measuring device of a lung image is characterized by comprising:
the first acquisition module is used for acquiring a main pulmonary artery central line effective section and a main pulmonary artery boundary based on an optimal segmentation level in a segmentation result of a lung image;
the determining module is used for determining a plurality of vertical line segments by taking a plurality of pixel points on the central line effective segment of the main pulmonary artery as vertical feet;
a second obtaining module for obtaining a measuring point of the pulmonary artery caliber based on the plurality of vertical line segments and the main pulmonary artery boundary,
the first obtaining module is further configured to determine the optimal segmentation level based on a gray value of a pixel point in a bifurcation point segmentation result included in the segmentation result, where the optimal segmentation level includes a pulmonary artery region and a bifurcation point region; determining a pulmonary artery centerline of the pulmonary artery region based on a centerline extraction algorithm; determining a branch point of the pulmonary artery midline based on the pulmonary artery midline; determining the main pulmonary artery midline valid segment and the main pulmonary artery boundary based on the branch point of the pulmonary artery midline and the pulmonary artery midline.
8. An image processing apparatus characterized by comprising:
an obtaining module, configured to obtain a measurement point of a pulmonary artery caliber based on the caliber measurement method according to any one of claims 1 to 3;
the first determination module is used for determining a measurement point of the aortic diameter based on the optimal segmentation level;
and the second determination module is used for determining whether pulmonary hypertension exists or not based on the measurement line of the pulmonary artery caliber determined by the measurement point of the pulmonary artery caliber and the measurement line of the aorta caliber determined by the measurement point of the aorta caliber.
9. An electronic device, the electronic device comprising:
a processor;
a memory for storing the processor-executable instructions,
wherein the processor is used for executing the pipe diameter measuring method of any one of the above claims 1 to 3 or executing the image processing method of any one of the above claims 4 to 6.
CN202110707743.2A 2021-06-24 2021-06-24 Lung image caliber measuring method and device and image processing method and device Active CN113344897B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110707743.2A CN113344897B (en) 2021-06-24 2021-06-24 Lung image caliber measuring method and device and image processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110707743.2A CN113344897B (en) 2021-06-24 2021-06-24 Lung image caliber measuring method and device and image processing method and device

Publications (2)

Publication Number Publication Date
CN113344897A CN113344897A (en) 2021-09-03
CN113344897B true CN113344897B (en) 2022-01-11

Family

ID=77478571

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110707743.2A Active CN113344897B (en) 2021-06-24 2021-06-24 Lung image caliber measuring method and device and image processing method and device

Country Status (1)

Country Link
CN (1) CN113344897B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978725A (en) * 2014-04-03 2015-10-14 上海联影医疗科技有限公司 Method and device for dividing coronary artery
CN109740602A (en) * 2019-01-10 2019-05-10 上海联影医疗科技有限公司 Pulmonary artery phase vessel extraction method and system
CN111145226A (en) * 2019-11-28 2020-05-12 南京理工大学 Three-dimensional lung feature extraction method based on CT image
CN112862824A (en) * 2020-04-17 2021-05-28 中山仰视科技有限公司 Novel coronavirus pneumonia focus detection method, system, device and storage medium
CN112861961A (en) * 2021-02-03 2021-05-28 推想医疗科技股份有限公司 Pulmonary blood vessel classification method and device, storage medium and electronic equipment

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9069396B2 (en) * 2013-03-12 2015-06-30 Lightlab Imaging, Inc. Controller and user interface device, systems, and methods
CA2993458A1 (en) * 2015-07-25 2017-02-02 Lightlab Imaging, Inc. Guidewire detection systems, methods, and apparatuses
CN105943085A (en) * 2016-06-03 2016-09-21 上海市第人民医院 Method for non-invasive measurement of right ventricular pressure and pulmonary artery pressure method
CN107330888A (en) * 2017-07-11 2017-11-07 中国人民解放军第三军医大学 Each chamber dividing method of dynamic heart based on CTA images
EP3488774A1 (en) * 2017-11-23 2019-05-29 Koninklijke Philips N.V. Measurement guidance for coronary flow estimation from bernoulli´s principle
CN112132949B (en) * 2019-11-19 2024-01-23 苏州润迈德医疗科技有限公司 Three-dimensional modeling method, device and system for blood vessel with narrow lesion region
CN111311612A (en) * 2020-02-17 2020-06-19 北京推想科技有限公司 Lung segmentation method, device, medium, and electronic apparatus
CN111681242B (en) * 2020-08-14 2020-11-17 北京至真互联网技术有限公司 Retinal vessel arteriovenous distinguishing method, device and equipment
CN112102275B (en) * 2020-09-09 2023-08-08 东软熙康健康科技有限公司 Pulmonary aortic vessel image extraction method, device, storage medium and electronic equipment
CN115969310A (en) * 2020-12-28 2023-04-18 深圳硅基智能科技有限公司 System and method for measuring pathological change characteristics of hypertensive retinopathy
CN113012118B (en) * 2021-03-05 2022-04-19 推想医疗科技股份有限公司 Image processing method and image processing apparatus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978725A (en) * 2014-04-03 2015-10-14 上海联影医疗科技有限公司 Method and device for dividing coronary artery
CN109740602A (en) * 2019-01-10 2019-05-10 上海联影医疗科技有限公司 Pulmonary artery phase vessel extraction method and system
CN111145226A (en) * 2019-11-28 2020-05-12 南京理工大学 Three-dimensional lung feature extraction method based on CT image
CN112862824A (en) * 2020-04-17 2021-05-28 中山仰视科技有限公司 Novel coronavirus pneumonia focus detection method, system, device and storage medium
CN112861961A (en) * 2021-02-03 2021-05-28 推想医疗科技股份有限公司 Pulmonary blood vessel classification method and device, storage medium and electronic equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
动静脉血管自动分类方法及其管径测量;薛岚燕等;《仪器仪表学报》;20180122;第38卷(第9期);2307-2316 *

Also Published As

Publication number Publication date
CN113344897A (en) 2021-09-03

Similar Documents

Publication Publication Date Title
US10210612B2 (en) Method and system for machine learning based estimation of anisotropic vessel orientation tensor
CN109712131B (en) Method and device for quantifying lung nodule characteristics, electronic equipment and storage medium
EP3429465A1 (en) Systems and methods for estimating healthy lumen diameter and stenosis quantification in coronary arteries
CN111340756B (en) Medical image lesion detection merging method, system, terminal and storage medium
WO2017047819A1 (en) Blood vessel shape analysis device, method for same, and computer software program for same
CN102208105A (en) Medical image processing technology
EP3171333B1 (en) Apparatus and method for correcting lesion in image frame
US20120308110A1 (en) Automation Method For Computerized Tomography Image Analysis Using Automated Calculation Of Evaluation Index Of Degree Of Thoracic Deformation Based On Automatic Initialization, And Record Medium And Apparatus
CN109711321B (en) Structure-adaptive wide baseline image view angle invariant linear feature matching method
EP2415019A1 (en) Interactive iterative closest point algorithm for organ segmentation
KR101135205B1 (en) A pulmonary vessel extraction method for automatical disease detection using chest ct images
CN112711831B (en) Blood vessel simulation analysis method, device, apparatus, computer device and storage medium
WO2008035446A1 (en) Medical image processor and image processing method and program
CN114693604A (en) Spine medical image processing method, device, equipment and storage medium
EP2178047A2 (en) Ribcage segmentation
CN113344897B (en) Lung image caliber measuring method and device and image processing method and device
JP6975177B2 (en) Detection of biological objects
US20220301177A1 (en) Updating boundary segmentations
CN109767468B (en) Visceral volume detection method and device
CN111640102A (en) Aneurysm detection method, aneurysm detection device and computer equipment
CN113361584B (en) Model training method and device, and pulmonary arterial hypertension measurement method and device
CN116130090A (en) Ejection fraction measuring method and device, electronic device, and storage medium
Pflug et al. Ear detection in 3D profile images based on surface curvature
CN113379741B (en) Retinal blood vessel segmentation method, device and storage medium based on blood vessel characteristics
CN115409858A (en) Medical image segmentation method, equipment and device

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