Dynamic lung image intelligent detection method and device, program product and medical equipment

Abstract

The invention relates to a dynamic lung image intelligent detection method and device, a program product and medical equipment, and relates to the technical field of detection. The method comprises the following steps: acquiring corresponding dynamic diaphragm sequences of a right lung and a left lung in a breathing process; determining a right lung reference diaphragm length according to the shortest length in a first length sequence corresponding to the dynamic right lung diaphragm sequence; on the basis of the right lung reference diaphragm length, a first length except the right lung reference diaphragm length in the first length sequence and a first preset length difference value, determining that other right lung diaphragms are normal or abnormal right diaphragms; determining a left lung reference diaphragm length according to the shortest length in a second length sequence corresponding to the dynamic left lung diaphragm sequence; and on the basis of the left lung reference diaphragm length, a second length except the left lung reference diaphragm length in the second length sequence and a second preset length difference value, determining the other left lung diaphragms as normal or abnormal left diaphragms respectively.

Description

Technical Field

[0001] The present disclosure relates to the technical field of X-ray two-dimensional chest image detection, and in particular, to a dynamic lung image intelligent detection method, device, program product, and medical device. Background Art

[0002] X-rays are the most widely used main imaging technology in conventional chest and skeletal radiography because they are widely available, low-cost, fast in imaging, and easy to obtain. Specifically, by directly projecting the captured human body onto a two-dimensional planar image, digital X-ray images can be obtained within a few seconds after exposure. Therefore, it has become the preferred imaging device in clinical practice to improve work efficiency and facilitate the preliminary chest diagnosis of critically ill and / or emergency patients.

[0003] Compared with inspiratory and expiratory chest CT (Computed tomography) images (two time points), chest fluoroscopy X-ray images or chest spot film X-ray images include more time points during free breathing. Therefore, this makes a significant contribution to the dynamic quantitative analysis of lung motor function (such as hemidiaphragm movement).

[0004] Specifically, Tanaka et al. evaluated the correlation between diaphragmatic movement parameters and lung vital capacity. At the same time, Yamada et al. used DCR (dynamic chest radiography) to evaluate the mean diaphragmatic displacement of healthy volunteers and the differences in tidal breathing diaphragmatic movement between COPD (Chronic obstructive pulmonary disease) and healthy control groups. Subsequently, Yamada et al. further evaluated the correlation between diaphragmatic movement and anthropometry. In addition, Hida et al. evaluated the diaphragmatic movement in the standing position during forced breathing and evaluated its relationship with demographics and pulmonary function tests. Subsequently, Hida et al. further evaluated the differences in diaphragmatic movement speed and displacement between chronic obstructive pulmonary disease and control groups, as well as the correlation between pulmonary function tests and diaphragmatic movement. In addition, FitzMaurice et al. described the changes in diaphragmatic movement and lung area before and after modulator treatment in adults with cystic fibrosis bronchiectasis using DCR. Subsequently, FitzMaurice et al. further described the diaphragmatic movement in patients with hemidiaphragm paralysis treated with DCR, as well as the diaphragmatic joint movement in patients receiving treatment for exacerbation of cystic fibrosis bronchiectasis. In addition, Chen et al. quantitatively evaluated the diaphragmatic movement during forced breathing in patients with chronic obstructive pulmonary disease using DCR. Therefore, accurate detection of the hemidiaphragm in dynamic multiple X-ray two-dimensional chest images corresponding to the breathing process of DCR images is crucial for accurately evaluating diaphragmatic motor function.

[0005] However, due to the deformation of the lung field in DCR, which leads to abnormal lung field morphology, the existing measurement methods of the hemidiaphragm often result in abnormal measurement of the hemidiaphragm corresponding to the lung field. Therefore, it is necessary to propose an optimization algorithm to ensure the accuracy of the hemidiaphragm measurement on dynamic chest X-ray (dynamic multiple two-dimensional chest X-ray images) images for subsequent quantitative analysis. Among them, in the process of optimizing the positioning of the hemidiaphragm, the primary task is how to detect the normal or abnormal hemidiaphragm for subsequent positioning optimization of the abnormal hemidiaphragm. Summary of the Invention

[0006] The present disclosure proposes a technical solution for a dynamic lung image intelligent detection method, device, program product, and medical device.

[0007] According to one aspect of the present disclosure, there is provided a dynamic lung image intelligent detection method, including:

[0008] Obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence (dynamic right diaphragm sequence) and a dynamic left lung diaphragm sequence (dynamic left diaphragm sequence) corresponding to multiple dynamic two-dimensional chest X-ray images during the breathing process;

[0009] Determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and the first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms (normal right lung diaphragms) or abnormal right diaphragms (abnormal right lung diaphragms); and / or, determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and the second preset length difference, respectively determining the other left lung diaphragms as normal left diaphragms (normal left lung diaphragms) or abnormal left diaphragms (abnormal left lung diaphragms).

[0010] Preferably, the method of determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and the first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms includes: determining the right lung diaphragm with the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence as the right lung reference diaphragm; based on the first reference length corresponding to the right lung reference diaphragm, the first lengths corresponding to the other right lung diaphragms in the dynamic right lung diaphragm sequence except the right lung reference diaphragm, and the first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms.

[0011] Preferably, the method for determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and determining whether the other left lung diaphragms are normal or abnormal based on the left lung reference diaphragm length, the second lengths in the second length sequence other than the left lung reference diaphragm length, and the second preset length difference, includes: determining the left lung reference diaphragm as the left lung diaphragm with the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and determining whether the other left lung diaphragms are normal or abnormal based on the second reference length corresponding to the left lung reference diaphragm, the second lengths corresponding to the other left lung diaphragms in the dynamic left lung diaphragm sequence other than the left lung reference diaphragm, and the second preset length difference.

[0012] Preferably, the method for determining the first length sequence corresponding to the dynamic right lung diaphragm sequence includes: respectively counting the sum of the first pixel value numbers corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence; and respectively obtaining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the first pixel value numbers corresponding to each right lung diaphragm and the area corresponding to each pixel.

[0013] Preferably, the method for respectively obtaining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the first pixel value numbers corresponding to each right lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the first pixel value numbers corresponding to each right lung diaphragm by the area corresponding to each pixel to obtain the first length sequence corresponding to the dynamic right lung diaphragm sequence.

[0014] Preferably, the method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence includes: respectively counting the sum of the second pixel value numbers corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence; and respectively obtaining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the second pixel value numbers corresponding to each left lung diaphragm and the area corresponding to each pixel.

[0015] Preferably, the method for respectively obtaining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the second pixel value numbers corresponding to each left lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the second pixel value numbers corresponding to each left lung diaphragm by the area corresponding to each pixel to obtain the second length sequence corresponding to the dynamic left lung diaphragm sequence.

[0016] Preferably, before obtaining at least one diaphragmatic muscle sequence of the dynamic right lung diaphragmatic muscle sequence and the dynamic left lung diaphragmatic muscle sequence corresponding to the dynamic multiple X-ray two-dimensional chest images during the respiration process, the method for respectively determining the dynamic right lung diaphragmatic muscle sequence and / or the dynamic left lung diaphragmatic muscle sequence corresponding to the dynamic multiple X-ray two-dimensional chest images during the respiration process includes: respectively obtaining at least one masked edge image sequence of the right lung masked edge image sequence (right lung masked edge image) and the left lung masked edge image sequence (left lung masked edge image) corresponding to the dynamic multiple X-ray two-dimensional chest images (dynamic X-ray two-dimensional chest images to be located during the respiration process / dynamic lung images during the respiration process); respectively determining the right lung apex corresponding to the right lung masked edge image sequence; respectively positioning the right lung diaphragmatic muscle (right diaphragmatic muscle) based on the right lung apex, the right costophrenic angle point, and the right lung masked edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images; and / or, respectively determining the left lung apex corresponding to the left lung masked edge image sequence, and respectively determining the right costophrenic angle point corresponding to the right lung masked edge image sequence and / or the left costophrenic angle point corresponding to the left lung masked edge image sequence; respectively positioning the left lung diaphragmatic muscle (left diaphragmatic muscle) based on the right cardiophrenic angle corresponding to the right lung diaphragmatic muscle, the left lung apex, the left costophrenic angle point, and the left lung masked edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images.

[0017] Preferably, the method for respectively determining the right lung apex corresponding to the right lung masked edge image sequence includes: respectively detecting the right lung vertex corresponding to each right lung masked edge image in the right lung masked edge image sequence, and respectively configuring the right lung vertex as the right lung apex corresponding to the right lung masked edge image sequence.

[0018] Preferably, the method for respectively determining the left lung apex corresponding to the left lung masked edge image sequence includes: respectively detecting the left lung vertex corresponding to each left lung masked edge image in the left lung masked edge image sequence, and respectively configuring the left lung vertex as the left lung apex corresponding to the left lung masked edge image sequence.

[0019] Preferably, the method for respectively determining the right costophrenic angle point corresponding to the right lung masked edge image sequence includes: respectively detecting the lowest point of the right lung corresponding to each right lung masked edge image in the right lung masked edge image sequence, and respectively configuring the lowest point of the right lung as the right costophrenic angle point corresponding to the right lung masked edge image sequence.

[0020] Preferably, the method for respectively determining the left costophrenic angle point corresponding to the left lung masked edge image sequence includes: respectively detecting the lowest point of the left lung corresponding to each left lung masked edge image in the left lung masked edge image sequence, and respectively configuring the lowest point of the left lung as the left costophrenic angle point corresponding to the left lung masked edge image sequence.

[0021] Preferably, the method for positioning the right pulmonary diaphragm respectively based on the right lung apex, the right costophrenic angle point, and the right lung mask edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images includes: respectively determining a corresponding first straight line based on the right lung apex and the right costophrenic angle point corresponding to each of the dynamic multiple X-ray two-dimensional chest images; respectively calculating multiple first distances from multiple first pixel position points (first pixel points) on the right edge line of the right lung mask edge image (the right heart border line close to the heart side) from the right lung apex to the right costophrenic angle point to the first straight line; configuring the first pixel position point corresponding to the maximum distance among the multiple first distances as the right cardiophrenic angle, and respectively configuring the mask edge line segment corresponding to the right lung mask edge image between the right cardiophrenic angle and the right costophrenic angle point as the corresponding right pulmonary diaphragm.

[0022] Preferably, the method for positioning the left pulmonary diaphragm respectively based on the right cardiophrenic angle corresponding to the right pulmonary diaphragm, the left lung apex, the left costophrenic angle point, and the left lung mask edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images includes: respectively determining auxiliary points corresponding to the lung mask edge image based on the coordinate points of the right cardiophrenic angle corresponding to each of the dynamic multiple X-ray two-dimensional chest images and a set increment in the y direction; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle point; respectively calculating multiple second distances from multiple second pixel position points (second pixel points) on the left edge line of the left lung mask edge image (the left heart border line close to the heart side) from the right lung apex to the auxiliary point to the second straight line; configuring the second pixel position point corresponding to the maximum distance among the multiple second distances as the left cardiophrenic angle (left cardiophrenic angle point), and configuring the mask edge line segment corresponding to the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle point as the corresponding left pulmonary diaphragm.

[0023] Preferably, before respectively obtaining at least one mask edge image sequence of the right lung mask edge image sequence (right lung mask edge image) and the left lung mask edge image sequence (left lung mask edge image) corresponding to the dynamic multiple X-ray two-dimensional chest images (X-ray two-dimensional chest images to be positioned), the method for respectively determining the right lung mask edge image sequence and / or the left lung mask edge image sequence corresponding to the dynamic multiple X-ray two-dimensional chest images includes: respectively eroding the right lung mask image sequence and / or the left lung mask image sequence by using an erosion template with a set size to obtain a corresponding right lung mask eroded image sequence (right lung mask eroded image) and / or a left lung mask eroded image sequence (left lung mask eroded image); respectively determining the right lung mask edge image sequence and / or the left lung mask edge image sequence based on the right lung mask image sequence and its corresponding right lung mask eroded image sequence and / or based on the left lung mask image sequence and its corresponding left lung mask eroded image sequence.

[0024] Preferably, the method for determining the right lung mask edge image sequence based on the right lung mask image sequence and its corresponding right lung mask eroded image sequence includes: subtracting the pixel value at each position in the right lung mask image sequence from the pixel value at the corresponding position in the corresponding right lung mask eroded image sequence to determine the right lung mask edge image sequence.

[0025] Preferably, the method for determining the left lung mask edge image sequence based on the left lung mask image sequence and its corresponding left lung mask eroded image sequence includes: subtracting the pixel value at each position in the left lung mask image sequence from the pixel value at the corresponding position in the corresponding left lung mask eroded image sequence to determine the left lung mask edge image sequence.

[0026] Preferably, before separately determining the right lung mask edge image sequence and / or the left lung mask edge image sequence corresponding to the dynamic multiple X-ray two-dimensional chest images, a preset lung field segmentation model is used to separately perform lung field segmentation on the dynamic multiple X-ray two-dimensional chest images to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0027] Preferably, the method for using a preset lung field segmentation model to separately perform lung field segmentation on the dynamic multiple X-ray two-dimensional chest images to obtain the right lung mask image sequence and / or the left lung mask image sequence includes: using a preset lung field segmentation model to separately perform lung field segmentation on the dynamic multiple X-ray two-dimensional chest images to obtain a to-be-processed right lung mask image sequence (to-be-processed right lung mask images) and / or a to-be-processed left lung mask image sequence (to-be-processed left lung mask image sequences); using a connected component algorithm to separately process the to-be-processed right lung mask image sequence and / or the to-be-processed left lung mask image sequence to remove over-segmented regions outside the lung field to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0028] Preferably, the method for separately determining whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and the first preset length difference includes: separately calculating multiple first differences between the first length other than the right lung reference diaphragm length and the right lung reference diaphragm length; if a certain first difference among the multiple differences is greater than or equal to the first preset length difference, determining the right diaphragm corresponding to the certain first difference as an abnormal right diaphragm; otherwise, determining it as a normal right diaphragm.

[0029] Preferably, the method for determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and determining whether the other left lung diaphragms are normal or abnormal based on the left lung reference diaphragm length, the second lengths other than the left lung reference diaphragm length in the second length sequence, and the second preset length difference, includes: calculating multiple second differences between the second lengths other than the left lung reference diaphragm length and the left lung reference diaphragm length respectively; if a certain second difference among the multiple second differences is greater than or equal to the second preset length difference, determining the left diaphragm corresponding to the certain second difference as an abnormal left diaphragm; otherwise, determining it as a normal left diaphragm.

[0030] Preferably, it further includes: obtaining at least one diaphragm sequence of the normal right diaphragm and the abnormal right diaphragm corresponding to the dynamic multiple X-ray two-dimensional chest images during the breathing process, and the diaphragm sequence of the normal left diaphragm and the abnormal left diaphragm; wherein, the diaphragm sequence includes: the right diaphragm sequence and / or the left diaphragm sequence; optimizing the positioning of the right cardiophrenic angle corresponding to the abnormal right diaphragm based on the right cardiophrenic angle corresponding to the normal right diaphragm; and / or, optimizing the positioning of the left cardiophrenic angle corresponding to the abnormal left diaphragm based on the left cardiophrenic angle corresponding to the normal left diaphragm.

[0031] Preferably, it further includes: obtaining the optimized right cardiophrenic angle corresponding to each abnormal right diaphragm; respectively optimizing the positioning of each abnormal diaphragm based on the optimized right cardiophrenic angle, the right costophrenic angle point, and the right lung mask edge image corresponding to each abnormal right diaphragm; and / or, obtaining the optimized left cardiophrenic angle corresponding to each abnormal left diaphragm; respectively optimizing the positioning of each abnormal diaphragm based on the optimized left cardiophrenic angle, the left costophrenic angle point, and the left lung mask edge image corresponding to each abnormal left diaphragm.

[0032] Preferably, the unit of the first length sequence and / or the second length sequence is configured as a pixel value; wherein, the sum of the first pixel value numbers corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence is respectively counted to obtain the first length sequence; and / or, the sum of the second pixel value numbers corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence is respectively counted to obtain the second length sequence.

[0033] Preferably, the first preset length difference and the value configured for the first preset length difference are the same or different; and / or, the first value corresponding to the first preset length difference is configured as any value in the range of 10 - 50 pixels; the second value corresponding to the second preset length difference is configured as any value in the range of 10 - 50 pixels.

[0034] According to one aspect of the present disclosure, there is provided a dynamic lung image intelligent detection device, including:

[0035] An acquisition unit, configured to acquire at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to a plurality of dynamic two-dimensional chest X-ray images during the breathing process;

[0036] A detection unit, configured to determine the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determine the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or, determine the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determine the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms; or,

[0037] Including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to call the instructions stored in the memory to execute the above-mentioned dynamic lung image intelligent detection method; or,

[0038] Including: a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned dynamic lung image intelligent detection method is implemented.

[0039] According to one aspect of the present disclosure, there is provided a computer program product, including a computer program / instructions, characterized in that when the computer program / instructions are executed by a processor, the above-mentioned dynamic lung image intelligent detection method is implemented.

[0040] According to one aspect of the present disclosure, there is provided an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to: execute the above-mentioned dynamic lung image intelligent detection method.

[0041] According to one aspect of the present disclosure, there is provided a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above-mentioned dynamic lung image intelligent detection method is implemented.

[0042] According to one aspect of the present disclosure, there is provided a medical device, applying the above-mentioned dynamic lung image intelligent detection method and / or including the above-mentioned dynamic lung image intelligent detection device and / or including the above-mentioned computer program product.

[0043] In an embodiment of the present disclosure, a technical solution for a dynamic lung image intelligent detection method, device, program product, and medical device is proposed to solve the problems in the prior art that normal or abnormal diaphragms cannot be detected, resulting in the inability to localize and optimize abnormal diaphragms subsequently.

[0044] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present disclosure.

[0045] Other features and aspects of the present disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification. These drawings show embodiments consistent with the present disclosure and, together with the specification, are used to explain the technical solution of the present disclosure.

[0047] Figure 1 A flowchart showing a dynamic lung image intelligent detection method according to an embodiment of the present disclosure;

[0048] Figure 2 A block diagram of an electronic device 800 shown according to an exemplary embodiment;

[0049] Figure 3 A block diagram of an electronic device 1900 shown according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] The following will detail various exemplary embodiments, features, and aspects of the present disclosure with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0051] The special term "exemplary" herein means "serving as an example, embodiment, or illustration". Any embodiment described as "exemplary" herein need not be construed as superior to or better than other embodiments.

[0052] The term "and / or" herein is merely a description of the associated relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0053] In addition, to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. Those skilled in the art should understand that the present disclosure can be implemented without some specific details. In some instances, methods, means, elements, and circuits well-known to those skilled in the art are not described in detail so as to highlight the gist of the present disclosure.

[0054] It can be understood that the above-mentioned various method embodiments mentioned in the present disclosure can be combined with each other to form combined embodiments without violating the principle logic. Due to space limitations, the present disclosure will not elaborate further.

[0055] In addition, the present disclosure also provides a dynamic lung image intelligent detection device, an electronic device, a computer-readable storage medium, a program, and a medical device, all of which can be used to implement any one of the dynamic lung image intelligent detection methods provided by the present disclosure. The corresponding technical solutions and descriptions can be referred to the corresponding records in the part of the dynamic lung image intelligent detection method, and will not be elaborated further.

[0056] Figure 1 A flowchart showing a dynamic lung image intelligent detection method according to an embodiment of the present disclosure is as Figure 1 shown. The dynamic lung image intelligent detection method includes: Step S101: Obtain at least one of the dynamic right lung diaphragm sequence and the dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process; Step S102: Determine the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determine the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or, determine the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determine the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms. To solve the problems in the prior art that normal or abnormal diaphragms cannot be detected, resulting in the inability to localize and optimize abnormal diaphragms.

[0057] Among them, in the embodiments of the present disclosure and other possible embodiments, the X-ray two-dimensional chest image can be referred to as a chest (lung) X-ray two-dimensional image, or a two-dimensional X-ray chest (lung) image, or an X-ray two-dimensional lung image, etc. Any combination of two or more of X-ray / DR, two-dimensional, chest / lung, and image expresses the same meaning.

[0058] Step S101: Obtain at least one of the dynamic right lung diaphragm sequence and the dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process.

[0059] In embodiments of the present disclosure and other possible embodiments, a Digital X-Ray (DR) imaging device can provide high-resolution and real-time two-dimensional X-ray images. The DR imaging device can be used to image the chest to obtain corresponding two-dimensional X-ray chest images. For example, in embodiments of the present disclosure and other possible embodiments, during free breathing or forced breathing, the digital X-ray imaging device can be used to photograph the chest containing the lungs to obtain multiple dynamic two-dimensional X-ray chest images corresponding to multiple consecutive time series (dynamic two-dimensional X-ray chest images to be localized); at the same time, in the breath-holding state, the digital X-ray imaging device can also be used to photograph the chest containing the lungs to obtain multiple dynamic two-dimensional X-ray chest images corresponding to multiple consecutive time series in the breath-holding state (two-dimensional X-ray chest images to be localized). Specifically, the multiple dynamic two-dimensional X-ray chest images during the breathing process or the multiple dynamic two-dimensional X-ray chest images in the breath-holding state include at least one two-dimensional X-ray chest image.

[0060] In embodiments of the present disclosure and other possible embodiments, the lung image to be segmented (the multiple dynamic two-dimensional X-ray chest images during the breathing process / the dynamic two-dimensional X-ray chest images to be localized) is segmented into a left chest image and a right chest image; based on the left chest image and the right chest image respectively, the left lung and the right lung are segmented.

[0061] In the embodiments of the present disclosure and other possible embodiments, the lung image to be segmented (the dynamic multiple X-ray two-dimensional chest images during the breathing process / the dynamic X-ray two-dimensional chest images to be located) is segmented into a left chest image and a right chest image; based on the left chest image and the right chest image respectively, the left lung and the right lung are segmented; or, a segmentation model of a preset convolutional neural network, a DR lung region label image for training the segmentation model, and multiple DR lung images to be segmented at multiple moments during the breathing process or in the breath-holding state (lung images to be segmented / dynamic multiple X-ray two-dimensional chest images to be segmented during the breathing process / dynamic X-ray two-dimensional chest images to be located to be segmented) are obtained; wherein, the method for determining the DR lung region label image for training the segmentation model includes: detecting the costal margin boundary, the lung apex boundary, and the mediastinal and diaphragmatic edges of the left chest image and the right chest image of multiple DR lung region images respectively, to obtain the DR lung region label images corresponding to the multiple DR lung region images; using the DR lung region label image for training the segmentation model to train the segmentation model; based on the trained segmentation model, completing the segmentation of the left lung and / or the right lung of the multiple DR lung images to be segmented (i.e., the X-ray two-dimensional chest images to be located / X-ray two-dimensional chest images), to obtain the right lung mask image and / or the left lung mask image. Among them, the lung field mask value corresponding to the right lung mask image can be configured as 1, and the lung field mask value corresponding to the left lung mask image can be configured as 2.

[0062] In the embodiments of the present disclosure and other possible embodiments, the lung region (lung field) of multiple DR lung images to be segmented at multiple moments during the breathing process or in the breath-holding state (lung images to be segmented / dynamic multiple X-ray two-dimensional chest images to be segmented during the breathing process / dynamic X-ray two-dimensional chest images to be located to be segmented) can be marked in a manual marking manner to obtain the DR lung region label image (X-ray two-dimensional lung region / lung field label image) for training the segmentation model; then, using the DR lung region label image (X-ray two-dimensional lung region / lung field label image) to train the segmentation model; finally, using the trained segmentation model (preset lung field segmentation model), performing lung field segmentation on the dynamic multiple X-ray two-dimensional chest images respectively, to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0063] In embodiments of the present disclosure and other possible embodiments, before obtaining at least one masked edge image sequence (right lung masked edge image) corresponding to a dynamic plurality of X-ray two-dimensional chest images (X-ray two-dimensional chest images to be positioned) and a masked edge image sequence (left lung masked edge image) respectively, the method for respectively determining the right lung masked edge image sequence and / or the left lung masked edge image sequence corresponding to the dynamic plurality of X-ray two-dimensional chest images includes: using an erosion template of a set size to respectively erode the right lung masked image sequence and / or the left lung masked image sequence to obtain a corresponding right lung masked erosion image sequence (right lung masked erosion image) and / or a left lung masked erosion image sequence (left lung masked erosion image); respectively determining the right lung masked edge image sequence and / or the left lung masked edge image sequence based on the right lung masked image sequence and its corresponding right lung masked erosion image sequence and / or based on the left lung masked image sequence and its corresponding left lung masked erosion image sequence.

[0064] Among them, in embodiments of the present disclosure and other possible embodiments, the set of left lung masked edge images corresponding to each X-ray two-dimensional chest image in the dynamic plurality of X-ray two-dimensional chest images constitutes a left lung masked edge image sequence; similarly, the set of right lung masked edge images corresponding to each X-ray two-dimensional chest image in the dynamic plurality of X-ray two-dimensional chest images constitutes a right lung masked edge image sequence.

[0065] Among them, in embodiments of the present disclosure and other possible embodiments, the set of right lung masked erosion images corresponding to each X-ray two-dimensional chest image in the dynamic plurality of X-ray two-dimensional chest images constitutes a right lung masked erosion image sequence; similarly, the set of left lung masked erosion images corresponding to each X-ray two-dimensional chest image in the dynamic plurality of X-ray two-dimensional chest images constitutes a left lung masked erosion image sequence.

[0066] In embodiments of the present disclosure and other possible embodiments, the method for determining the right lung masked edge image sequence based on the right lung masked image sequence and its corresponding right lung masked erosion image sequence includes: subtracting the pixel value at each position in the right lung masked erosion image sequence corresponding to the right lung masked image sequence from the pixel value at the corresponding position in the right lung masked image sequence to determine the right lung masked edge image sequence.

[0067] In embodiments of the present disclosure and other possible embodiments, the method for determining the left lung masked edge image sequence based on the left lung masked image sequence and its corresponding left lung masked erosion image sequence includes: subtracting the pixel value at each position in the left lung masked erosion image sequence corresponding to the left lung masked image sequence from the pixel value at the corresponding position in the left lung masked image sequence to determine the left lung masked edge image sequence.

[0068] In embodiments of the present disclosure and other possible embodiments, before separately determining the right lung mask edge image sequence and / or the left lung mask edge image sequence corresponding to the dynamic multiple X-ray two-dimensional chest images, the preset lung field segmentation model is used to separately perform lung field segmentation on the dynamic multiple X-ray two-dimensional chest images to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0069] In embodiments of the present disclosure and other possible embodiments, the erosion template of the set size can be configured as an N×N erosion template with each pixel value being 1; the right lung mask image and / or the left lung mask image are respectively eroded using the N×N erosion template with each pixel value being 1 to obtain the corresponding right lung mask eroded image and / or left lung mask eroded image. Specifically, the right lung mask image and / or the left lung mask image are traversed row / column by using the erosion template of the set size (N×N with each pixel value being 1) to obtain the corresponding right lung mask eroded image and / or left lung mask eroded image.

[0070] In embodiments of the present disclosure and other possible embodiments, the erosion template of the set size can be configured as a 3×3 erosion template with each pixel value being 1. Among them, the 3×3 erosion template with each pixel value being 1 traverses each lung field mask image (right lung mask image and / or left lung mask image) row / column with a step size of 1 pixel to generate the corresponding right lung mask eroded image and / or left lung mask eroded image. More specifically, if the 9 values with pixel value 1 in the 3×3 pixel correction template are multiplied by the points of the traversed right lung mask image and / or left lung mask image, and the first and last of these 9 values are not 0, it is considered that the lung field corresponding to the right lung mask image and / or left lung mask image has been detected. When the lung field is detected, the position information of the center of the 3×3 erosion template and its pixel value are recorded. Then, based on the recorded position information and its pixel value (1 or 2), the corresponding right lung mask eroded image and / or left lung mask eroded image are generated. Then, the right lung mask image and / or the left lung mask image are respectively subtracted from the corresponding right lung mask eroded image and / or left lung mask eroded image to obtain the corresponding right lung mask edge image and / or left lung mask edge image. Among them, 1 can represent the right lung and 2 can represent the left lung.

[0071] In the embodiments of the present disclosure and other possible embodiments, the method of using a preset lung field segmentation model to perform lung field segmentation on the dynamic multiple X-ray two-dimensional chest images respectively to obtain the right lung mask image sequence and / or the left lung mask image sequence includes: using the preset lung field segmentation model to perform lung field segmentation on the to-be-dynamic multiple X-ray two-dimensional chest images respectively to obtain a to-be-processed right lung mask image sequence (to-be-processed right lung mask image) and / or a to-be-processed left lung mask image sequence (to-be-processed left lung mask image sequence); using a connected component algorithm to process the to-be-processed right lung mask image sequence and / or the to-be-processed left lung mask image sequence respectively to remove over-segmented regions outside the lung field, so as to obtain the right lung mask image sequence and / or the left lung mask image sequence.

[0072] In the embodiments of the present disclosure and other possible embodiments, the preset convolutional neural network corresponding to the segmentation model (preset lung field segmentation model) can be configured as a Unet convolutional neural network or an nnUnet convolutional neural network or a convolutional neural network improved based on the Unet convolutional neural network or a convolutional neural network improved based on the nnUnet convolutional neural network. For example, the convolutional neural network improved based on the Unet convolutional neural network can be configured as a ResUnet convolutional neural network with a residual structure.

[0073] In the embodiments of the present disclosure and other possible embodiments, the Unet convolutional neural network or the nnUnet convolutional neural network or the convolutional neural network improved based on the Unet convolutional neural network or the convolutional neural network improved based on the nnUnet convolutional neural network at least includes: a downsampling contraction path, an upsampling expansion path, and a final classification layer.

[0074] In the embodiments of the present disclosure and other possible embodiments, before training the segmentation model using the DR lung region label image for training the segmentation model, data augmentation is performed on the DR lung region label image to obtain an enhanced DR lung region label image; and the enhanced DR lung region label image is used to train the segmentation model.

[0075] In the embodiments of the present disclosure and other possible embodiments, the method of performing data augmentation on the DR lung region label image to obtain an enhanced DR lung region label image includes: performing spatial geometric transformation and / or flipping and / or rotation and / or cropping and / or scaling and / or image shifting and / or edge padding and / or random erasing and / or random occlusion operations on the DR lung region label image to obtain an enhanced DR lung region label image.

[0076] In the embodiments of the present disclosure and other possible embodiments, the method for performing data augmentation on the DR lung region label image to obtain the enhanced DR lung region label image further includes: randomly extracting any two DR lung region label images from the DR lung region label image; performing a registration operation on the any two DR lung region label images to obtain the corresponding DR lung region label registration image; performing a fusion operation on the DR lung region label registration image to obtain the enhanced DR lung region label image. Among them, the registration operation on the any two DR lung region label images can adopt existing registration algorithms or models, such as one or several of the SIFT (Scale-invariant feature transform) registration algorithm or model, SURF (Speeded Up Robust Features) registration algorithm or model, ORB (Oriented FAST and Rotated BRIEF) registration algorithm or model, or other registration algorithms or models based on convolutional neural networks. For example, the registration algorithm or model based on convolutional neural networks can be configured as a registration algorithm or model based on the VGG network.

[0077] In the embodiments of the present disclosure and other possible embodiments, the method for performing a fusion operation on the DR lung region label registration image to obtain the enhanced DR lung region label image includes: respectively performing a minimum value taking, maximum value taking, or mean value taking operation on the pixel values corresponding to the DR lung region label registration image to obtain the enhanced DR lung region label image.

[0078] In the embodiments of the present disclosure, the method for determining the first length sequence corresponding to the dynamic right lung diaphragm sequence includes: respectively counting the sum of the numbers of the first pixel values corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence; respectively obtaining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the numbers of the first pixel values corresponding to each right lung diaphragm and the area corresponding to each pixel. Among them, the method for respectively determining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the numbers of the first pixel values corresponding to each right lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the numbers of the first pixel values corresponding to each right lung diaphragm by the area corresponding to each pixel to obtain the first length sequence corresponding to the dynamic right lung diaphragm sequence.

[0079] In an embodiment of the present disclosure, the method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence includes: respectively counting the sum of the numbers of second pixel values corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence; respectively obtaining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the numbers of second pixel values corresponding to each left lung diaphragm and the area corresponding to each pixel. Among them, the method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the numbers of second pixel values corresponding to each left lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the numbers of second pixel values corresponding to each left lung diaphragm by the area corresponding to each pixel to obtain the second length sequence corresponding to the dynamic left lung diaphragm sequence.

[0080] In the embodiments of the present disclosure and other possible embodiments, the area corresponding to each pixel can be obtained by reading the DICOM (Digital Imaging and Communications in Medicine) file corresponding to multiple dynamic X-ray two-dimensional chest images during respiration; where DICOM, namely Digital Imaging and Communications in Medicine, is an international standard (ISO 12052) for medical images and related information, and it defines a medical image format that can be used for data exchange and whose quality meets clinical requirements. In addition, the area corresponding to each pixel can also be input through an input device (such as a keyboard, etc.).

[0081] In the embodiments of the present disclosure and other possible embodiments, the unit of the first length sequence and / or the second length sequence is configured as pixel value. Among them, the sum of the numbers of first pixel values corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence is respectively counted to obtain the first length sequence; and / or, the sum of the numbers of second pixel values corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence is respectively counted to obtain the second length sequence.

[0082] Meanwhile, in the embodiments of the present disclosure and other possible embodiments, the first preset length difference and the value configured for the first preset length difference are the same or different. For example, the first value corresponding to the first preset length difference is configured as any value in 10 - 50 pixels; the second value corresponding to the second preset length difference is configured as any value in 10 - 50 pixels. Meanwhile, those skilled in the art can also configure other values for the first value corresponding to the first preset length difference and the second value corresponding to the second preset length difference according to actual needs.

[0083] For example, in the embodiments of the present disclosure and other possible embodiments, the first value corresponding to the first preset length difference and the second value corresponding to the second preset length difference can be respectively configured as any value in 10, 20, 30, 40, 50.

[0084] In an embodiment of the present disclosure, before obtaining at least one diaphragmatic muscle sequence of a dynamic right lung diaphragmatic muscle sequence and a dynamic left lung diaphragmatic muscle sequence corresponding to dynamic multiple X-ray two-dimensional chest images during the respiration process, a method for respectively determining the corresponding dynamic right lung diaphragmatic muscle sequence and / or dynamic left lung diaphragmatic muscle sequence according to the dynamic multiple X-ray two-dimensional chest images during the respiration process includes: respectively obtaining at least one masked edge image sequence of a right lung masked edge image sequence (right lung masked edge image) and a left lung masked edge image sequence (left lung masked edge image) corresponding to the dynamic multiple X-ray two-dimensional chest images (dynamic X-ray two-dimensional chest images to be located during the respiration process / dynamic lung images during the respiration process); respectively determining the right lung apex corresponding to each right lung masked edge image in the right lung masked edge image sequence; respectively positioning the right lung diaphragmatic muscle based on the right lung apex, the right costophrenic angle point, and the right lung masked edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images (each right lung masked edge image); and / or, respectively determining the left lung apex corresponding to each left lung masked edge image in the left lung masked edge image sequence, and respectively determining the right costophrenic angle point corresponding to each left lung masked edge image in the right lung masked edge image sequence and / or the left costophrenic angle point corresponding to the left lung masked edge image sequence; respectively positioning the left lung diaphragmatic muscle based on the right cardiophrenic angle corresponding to the right lung diaphragmatic muscle, the left lung apex, the left costophrenic angle point, and the left lung masked edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images (each left lung masked edge image). Wherein, the set of right lung diaphragmatic muscles corresponding to each X-ray two-dimensional chest image in the dynamic multiple X-ray two-dimensional chest images constitutes a dynamic right lung diaphragmatic muscle sequence; similarly, the set of left lung diaphragmatic muscles corresponding to each X-ray two-dimensional chest image in the dynamic multiple X-ray two-dimensional chest images constitutes a dynamic left lung diaphragmatic muscle sequence.

[0085] In an embodiment of the present disclosure, the method for respectively determining the right lung apex corresponding to the right lung masked edge image sequence includes: respectively detecting the right lung vertex corresponding to each right lung masked edge image in the right lung masked edge image sequence, and respectively configuring the right lung vertex as the right lung apex corresponding to the right lung masked edge image sequence.

[0086] In an embodiment of the present disclosure, the method for respectively determining the left lung apex corresponding to the left lung masked edge image sequence includes: respectively detecting the left lung vertex corresponding to each left lung masked edge image in the left lung masked edge image sequence, and respectively configuring the left lung vertex as the left lung apex corresponding to the left lung masked edge image sequence.

[0087] In an embodiment of the present disclosure, the method for respectively determining the right costophrenic angle points corresponding to the right lung mask edge image sequence includes: respectively detecting the lowest points of the right lung in each right lung mask edge image in the right lung mask edge image sequence, and respectively configuring the lowest points of the right lung as the right costophrenic angle points corresponding to the right lung mask edge image sequence.

[0088] In an embodiment of the present disclosure, the method for respectively determining the left costophrenic angle points corresponding to the left lung mask edge image sequence includes: respectively detecting the lowest points of the left lung in each left lung mask edge image in the left lung mask edge image sequence, and respectively configuring the lowest points of the left lung as the left costophrenic angle points corresponding to the left lung mask edge image sequence.

[0089] In an embodiment of the present disclosure, the method for respectively positioning the right lung diaphragm based on the right lung apex, the right costophrenic angle points, and the right lung mask edge images corresponding to the respective dynamic multiple X-ray two-dimensional chest images includes: respectively determining a corresponding first straight line based on the right lung apex and the right costophrenic angle points corresponding to the respective dynamic multiple X-ray two-dimensional chest images; respectively calculating multiple first distances from multiple first pixel position points (first pixel points) on the right edge line of the right lung mask edge image (the right heart edge line closer to the heart) from the right lung apex to the right costophrenic angle point to the first straight line; configuring the first pixel position point corresponding to the maximum distance among the multiple first distances as the right cardiophrenic angle, and respectively configuring the mask edge line segment corresponding to the right lung mask edge image between the right cardiophrenic angle and the right costophrenic angle point as the corresponding right lung diaphragm.

[0090] In an embodiment of the present disclosure, the method for respectively positioning the left lung diaphragm based on the right cardiophrenic angle corresponding to the right lung diaphragm, the left lung apex, the left costophrenic angle points, and the left lung mask edge images corresponding to the respective dynamic multiple X-ray two-dimensional chest images includes: respectively determining auxiliary points corresponding to the corresponding lung mask edge images based on the coordinate points of the right cardiophrenic angle and the set increment in the y direction corresponding to the respective dynamic multiple X-ray two-dimensional chest images; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle points; respectively calculating multiple second distances from multiple second pixel position points (second pixel points) on the left edge line of the left lung mask edge image (the left heart edge line closer to the heart) from the right lung apex to the auxiliary point to the second straight line; configuring the second pixel position point corresponding to the maximum distance among the multiple second distances as the left cardiophrenic angle (left cardiophrenic angle point), and configuring the mask edge line segment corresponding to the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle point as the corresponding left lung diaphragm.

[0091] In embodiments of the present disclosure and other possible embodiments, the right costophrenic angle point or the left costophrenic angle point corresponding to the left lung or the right lung is close to the origin of the xoy coordinate system; the ordinate of the right lung apex or the left lung apex corresponding to the left lung or the right lung is greater than the ordinate of the corresponding right costophrenic angle point or left costophrenic angle point. For example, the right costophrenic angle point corresponding to the right lung is close to the origin of the xoy coordinate system, the y-axis is configured in the direction from the right costophrenic angle point to the right lung apex, and the y-axis is configured in the direction from the right costophrenic angle point to the left costophrenic angle point.

[0092] For example, in embodiments of the present disclosure and other possible embodiments, the method for determining the corresponding first straight line based on the right lung apex A1 and the right costophrenic angle point B1 includes: based on the right lung apex A1(x A1 ,y A1 ) and the right costophrenic angle point B1(x B1 ,y B1 ) to determine the first coefficient a1, the second coefficient b1 and the third coefficient c1 corresponding to the first straight line Line1; based on the first coefficient a1, the second coefficient b1 and the third coefficient c1 to determine the first straight line Line1.

[0093] Line1: a1x + b1y + c1 = 0.

[0094] Furthermore, before respectively calculating the multiple first distances from multiple first pixel points on the right edge line A1B1 (the right heart edge line close to the heart side) of the right lung mask edge image from the right lung apex A1 to the right costophrenic angle point B1 to the first straight line, based on the right lung apex A1 to the right costophrenic angle point B1 to determine the right edge line A1B1 of the right lung mask edge image, the determination method includes: respectively taking the right lung apex A1 as the starting point, respectively along the right lung mask edge line of the right lung mask edge image, calculating the length of the first edge line from the right lung apex A1 to the right costophrenic angle point B1 and the length of the second edge line of the right lung apex to the right costophrenic angle point / calculating the length of the first edge line from the right costophrenic angle point B1 to the right lung apex A1 and the length of the second edge line of the right lung apex to the right costophrenic angle point; wherein, the first edge line and the second edge line are respectively distributed on both sides of the first straight line Line1, and the longest edge line among the length of the first edge line and the length of the second edge line is configured as the right edge line A1B1 of the right lung mask edge image.

[0095] For example, in the embodiments of the present disclosure and other possible embodiments, calculating the multiple first distances from multiple first pixel points on the right edge line A1B1 (the right heart edge line on the side close to the heart) of the right lung mask edge image from the right lung apex A1 to the right costophrenic angle point B1 respectively includes: taking the right lung apex A1 as the starting / ending point and the right costophrenic angle point B1 as the ending / starting point, and successively calculating the multiple first distances from the multiple first pixel points to the first straight line Line1 along the right edge line A1B1 of the right lung mask edge image. Further, configure the first pixel point corresponding to the maximum distance among the multiple first distances as the right cardiophrenic angle C1, and configure and locate the mask edge line segment corresponding to the right lung mask edge image between the right cardiophrenic angle C1 and the right costophrenic angle point B1 as the right lung diaphragm B1C1.

[0096] Specifically, in the embodiments of the present disclosure and other possible embodiments, a calculation formula corresponding to the right cardiophrenic angle C1(x, y) is given.

[0097]

[0098] Among them, represents the multiple first pixel points p r1 , p r2 , p r3 ,..., p rn to the multiple first distances (d r1 (p r1 ), d r2 (p r2 ), d r3 (p r3 ),..., d rn (p rn )) of the first straight line Line1; r represents the right lung; n ≥ 1 and is a positive integer; max() represents the maximum function; (x r1 , y r1 ), (x r2 , y r2 ), (x r3 , y r3 ),...,(x rn , y rn ) respectively represent the coordinates corresponding to the multiple first pixel points p r1 , p r2 , p r3 ,..., p rn ; d r1 , d r2 , d r3 ,..., d rn respectively represent the multiple first pixel points p r1 , p r2 , pr3 ,..., p rn The corresponding Euclidean distance.

[0099] In an embodiment of the present disclosure, the method for locating the left lung diaphragm based on the right cardiophrenic angle corresponding to the right lung diaphragm, the left lung apex, the left costophrenic angle point, and the left lung mask edge image includes: determining an auxiliary point corresponding to the lung mask edge image based on the coordinate point of the right cardiophrenic angle and a set increment in the y direction; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle point; respectively calculating a plurality of second distances from a plurality of second pixel points on the left edge line of the left lung mask edge image (the left cardiac margin line close to the heart side) from the right lung apex to the second straight line; configuring the second pixel point corresponding to the maximum distance among the plurality of second distances as the left cardiophrenic angle (left cardiophrenic angle point), and configuring and positioning the mask edge line segment corresponding to the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle point as the left lung diaphragm.

[0100] In an embodiment of the present disclosure, the method for determining an auxiliary point corresponding to the lung mask edge image based on the coordinate point of the right cardiophrenic angle and a set increment in the y direction includes: adding the set increment in the y direction to the ordinate of the coordinate point to obtain a corresponding auxiliary line parallel to the x direction; determining the intersection point of the auxiliary line and the left lung mask edge image as the auxiliary point corresponding to the lung mask edge image.

[0101] In an embodiment of the present disclosure, the method for determining the intersection point of the auxiliary line and the left lung mask edge image as the auxiliary point corresponding to the lung mask edge image includes: the intersection points of the auxiliary line and the left lung mask edge image include: a first group of intersection points and a second group of intersection points; determining the intersection point with the smaller / minimum abscissa among the first group of intersection points and the second group of intersection points as the auxiliary point corresponding to the lung mask edge image.

[0102] For example, in an embodiment of the present disclosure and other possible embodiments, the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle C1 is added / subtracted by the set increment Δy in the y direction to obtain a corresponding auxiliary line parallel to the x direction (y C1 + / -Δy); the intersection point of the auxiliary line (y C1 + / -Δy) and the left lung mask edge image is determined as the auxiliary point C2' corresponding to the lung mask edge image. Specifically, the intersection points of the auxiliary line and the left lung mask edge image include: a first group of intersection points and a second group of intersection points; determining the intersection point with the smaller / minimum abscissa among the first group of intersection points and the second group of intersection points as the auxiliary point C2' corresponding to the lung mask edge image.

[0103] Specifically, when adding the set increment Δy in the y direction to the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle, the set increment Δy is configured to be a negative value; or, when subtracting the set increment Δy in the y direction from the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle, the set increment Δy is configured to be a positive value. The calculation formula corresponding to the auxiliary point C2’(x, y) is given, that is, C'2(x, y) = C1(x, y - Δy). C1 Specifically, when adding the set increment Δy in the y direction to the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle, the set increment Δy is configured to be a negative value; or, when subtracting the set increment Δy in the y direction from the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle, the set increment Δy is configured to be a positive value. The calculation formula corresponding to the auxiliary point C2’(x, y) is given, that is, C'2(x, y) = C1(x, y - Δy). C1 Specifically, when adding the set increment Δy in the y direction to the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle, the set increment Δy is configured to be a negative value; or, when subtracting the set increment Δy in the y direction from the ordinate y of the coordinate point C1(x, y) of the right cardiophrenic angle, the set increment Δy is configured to be a positive value. The calculation formula corresponding to the auxiliary point C2’(x, y) is given, that is, C'2(x, y) = C1(x, y - Δy).

[0104] Further, in the embodiments of the present disclosure and other possible embodiments, based on the left lung apex A2 and the left costophrenic angle point B2, a corresponding second straight line Line2 is determined; the method for determining the corresponding second straight line Line2 based on the left lung apex A2 and the left costophrenic angle point B2 includes: based on the left lung apex A2(x A2 , y A2 ) and the left costophrenic angle point B2(x B2 , y B2 ) to determine the fourth coefficient a2, the fifth coefficient b2, and the sixth coefficient c2 corresponding to the second straight line Line2; based on the fourth coefficient a2, the fifth coefficient b2, and the sixth coefficient c2; determine the second straight line Line2.

[0105] Line2: a2x + b2y + c2 = 0.

[0106] Furthermore, before respectively calculating the multiple second distances from multiple second pixel points on the left edge line A2B2 of the left lung mask edge image (the left heart edge line close to the heart side) from the left lung apex A2 to the sitting costophrenic angle point B2 to the second straight line, based on the left lung apex A2 to the sitting costophrenic angle point B2, the left edge line A2B2 of the left lung mask edge image is determined, and the determination method includes: respectively taking the left lung apex A2 as the starting point, respectively along the left lung mask edge line of the left lung mask image, calculating the third edge line length and the fourth edge line length from the left lung apex A2 to the sitting costophrenic angle point B2 of the left lung apex to the left costophrenic angle point / calculating the third edge line length and the fourth edge line length from the sitting costophrenic angle point B2 to the left lung apex A2 of the left lung apex to the left costophrenic angle point; wherein, the third edge line and the fourth edge line are respectively distributed on both sides of the second straight line Line2, and the longest edge line among the lengths of the first edge line and the second edge line is configured as the left edge line A2B2 of the right lung mask edge image.

[0107] For example, in the embodiments of the present disclosure and other possible embodiments, calculating the multiple second distances from multiple second pixel points on the left edge line A1B1 (the left cardiac margin line on the side close to the heart) of the right lung mask edge image from the left lung apex A2 to the right costophrenic angle point B2 respectively includes: taking the left lung apex A2 as the starting point / ending point and the right costophrenic angle point B2 as the ending point / starting point, and successively calculating the multiple second distances from the multiple second pixel points to the second straight line Line2 along the left edge line A1B1 of the right lung mask edge image. Further, the second pixel point corresponding to the maximum distance among the multiple second distances is configured as the right cardiophrenic angle C2, and the mask edge line segment corresponding to the right lung mask edge image between the left cardiophrenic angle C2 and the right costophrenic angle point B2 is configured and positioned as the left lung diaphragm B2C2.

[0108] Specifically, in the embodiments of the present disclosure and other possible embodiments, a calculation formula for the right cardiophrenic angle C2(x, y) is given.

[0109]

[0110] Among them, represents the multiple first distances d l1 , d l2 , d l3 ,..., d ln from the multiple second pixel points p l1 (p l1 ), d l2 (p l2 ), d l3 (p l3 ),..., d ln (p ln ) to the second straight line Line2; l represents the right lung; n ≥ 1 and is a positive integer; max() represents the maximum function; (x l1 , y l1 ), (x l2 , y l2 ), (x l3 , y l3 ),...,(x ln , y ln ) respectively represent the coordinates corresponding to the multiple first pixel points p l1 , p l2 , p l3 ,..., p ln ; d l1 , d l2 , d l3 ,..., d ln respectively represent the multiple first pixel points p l1 , p l2 , pl3 ,..., p ln The corresponding Euclidean distance.

[0111] Step S102: Determine the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first lengths other than the right lung reference diaphragm length in the first length sequence, and the first preset length difference, respectively determine whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms; and / or, determine the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second lengths other than the left lung reference diaphragm length in the second length sequence, and the second preset length difference, respectively determine whether the other left lung diaphragms are normal left diaphragms or abnormal left diaphragms.

[0112] In an embodiment of the present disclosure, the method of determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; and based on the right lung reference diaphragm length, the first lengths other than the right lung reference diaphragm length in the first length sequence, and the first preset length difference, respectively determining whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms includes: determining the right lung diaphragm with the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence as the right lung reference diaphragm; based on the first reference length corresponding to the right lung reference diaphragm, the first lengths corresponding to the other right lung diaphragms in the dynamic right lung diaphragm sequence except the right lung reference diaphragm, and the first preset length difference, respectively determining whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms.

[0113] In an embodiment of the present disclosure, the method of determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and based on the left lung reference diaphragm length, the second lengths other than the left lung reference diaphragm length in the second length sequence, and the second preset length difference, respectively determining whether the other left lung diaphragms are normal left diaphragms or abnormal left diaphragms includes: determining the left lung diaphragm with the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence as the left lung reference diaphragm; based on the second reference length corresponding to the left lung reference diaphragm, the second lengths corresponding to the other left lung diaphragms in the dynamic left lung diaphragm sequence except the left lung reference diaphragm, and the second preset length difference, respectively determining whether the other left lung diaphragms are normal left diaphragms or abnormal left diaphragms.

[0114] In an embodiment of the present disclosure, the method for respectively determining whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms based on the right lung reference diaphragm length, the first length in the first length sequence except the right lung reference diaphragm length, and the first preset length difference includes: calculating a plurality of first differences between the first length except the right lung reference diaphragm length and the right lung reference diaphragm length; if a certain first difference among the plurality of differences is greater than or equal to the first preset length difference, determining the right diaphragm corresponding to the certain first difference as an abnormal right diaphragm; otherwise, determining it as a normal right diaphragm.

[0115] For example, in the embodiment of the present disclosure and other possible embodiments, the first preset length difference is configured to be 20 mm or 20 pixels. Calculate a plurality of first differences between the first length except the right lung reference diaphragm length and the right lung reference diaphragm length; if a certain first difference among the plurality of differences is greater than or equal to the first preset length difference of 20 mm or 20 pixels, determining the right diaphragm corresponding to the certain first difference as an abnormal right diaphragm; if a certain first difference among the plurality of differences is less than the first preset length difference of 20 mm or 20 pixels, determining the right diaphragm corresponding to the certain first difference as a normal right diaphragm.

[0116] In an embodiment of the present disclosure, the method for determining the left lung reference diaphragm length by determining the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and respectively determining whether the other left lung diaphragms are normal left diaphragms or abnormal left diaphragms based on the left lung reference diaphragm length, the second length in the second length sequence except the left lung reference diaphragm length, and the second preset length difference includes: calculating a plurality of second differences between the second length except the left lung reference diaphragm length and the left lung reference diaphragm length; if a certain second difference among the plurality of second differences is greater than or equal to the second preset length difference, determining the left diaphragm corresponding to the certain second difference as an abnormal left diaphragm; otherwise, determining it as a normal left diaphragm.

[0117] For example, in the embodiment of the present disclosure and other possible embodiments, the first preset length difference is configured to be 20 mm or 20 pixels. Calculate a plurality of second differences between the second length except the left lung reference diaphragm length and the left lung reference diaphragm length; if a certain second difference among the plurality of second differences is greater than or equal to the second preset length difference of 20 mm or 20 pixels, determining the left diaphragm corresponding to the certain second difference as an abnormal left diaphragm; if a certain second difference among the plurality of second differences is less than the second preset length difference of 20 mm or 20 pixels, if a certain second difference among the plurality of second differences is greater than or equal to the second preset length difference of 20 mm or 20 pixels, a normal left diaphragm.

[0118] In an embodiment of the present disclosure, the dynamic lung image intelligent detection method further includes: obtaining at least one diaphragm sequence of a normal right diaphragm and an abnormal right diaphragm corresponding to a sequence of dynamic multiple X-ray two-dimensional chest images during the breathing process, and a diaphragm sequence of a normal left diaphragm and an abnormal left diaphragm corresponding to the left diaphragm; wherein the diaphragm sequence includes: a right diaphragm sequence and / or a left diaphragm sequence; optimizing the positioning of the right cardiophrenic angle corresponding to the abnormal right diaphragm based on the right cardiophrenic angle corresponding to the normal right diaphragm; and / or optimizing the positioning of the left cardiophrenic angle corresponding to the abnormal left diaphragm based on the left cardiophrenic angle corresponding to the normal left diaphragm.

[0119] In an embodiment of the present disclosure and other possible embodiments, the method for optimizing the positioning of the right cardiophrenic angle corresponding to the abnormal right diaphragm based on the right cardiophrenic angle corresponding to the normal right diaphragm includes: obtaining a normal right diaphragm sequence, an abnormal right diaphragm sequence, a normal left diaphragm sequence, and an abnormal left diaphragm sequence corresponding to a sequence of dynamic multiple X-ray two-dimensional chest images during the breathing process; using the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence to optimize the positioning of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence of the same first X-ray two-dimensional chest image; and / or using the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence to optimize the positioning of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence of the same second X-ray two-dimensional chest image.

[0120] In an embodiment of the present disclosure and other possible embodiments, before using the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence to optimize the positioning of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence of the same first X-ray two-dimensional chest image, the right diaphragm corresponding to the same first X-ray two-dimensional chest image is a normal right diaphragm. At the same time, before using the normal left cardiophrenic angle corresponding to the normal left diaphragm in the normal left diaphragm sequence to optimize the positioning of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence of the same second X-ray two-dimensional chest image, the left diaphragm corresponding to the same second X-ray two-dimensional chest image is a normal left diaphragm.

[0121] In the embodiments of the present disclosure and other possible embodiments, the method for optimizing the positioning of the abnormal left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence of the first X-ray two-dimensional chest image using the normal right cardiophrenic angle corresponding to the normal right diaphragm in the normal right diaphragm sequence includes: determining the standard X-ray two-dimensional chest images corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multiple X-ray two-dimensional chest images; configuring the normal left cardiophrenic angle corresponding to the normal left diaphragm in the standard X-ray two-dimensional chest image to the initialized left cardiophrenic angle corresponding to the abnormal left diaphragm in the abnormal left diaphragm sequence of the first X-ray two-dimensional chest image of the same sheet; calculating the first distance in the y direction between the normal left cardiophrenic angle corresponding to the normal left diaphragm in the standard X-ray two-dimensional chest image and the normal left cardiophrenic angle corresponding to the normal left diaphragm in the first X-ray two-dimensional chest image; adjusting the initialized left cardiophrenic angle using the first distance in the y direction to obtain an adjusted left cardiophrenic angle; and completing the positioning optimization of the abnormal left cardiophrenic angle based on the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image.

[0122] In the embodiments of the present disclosure and other possible embodiments, the method for adjusting the initialized left cardiophrenic angle using the first distance in the y direction to obtain an adjusted left cardiophrenic angle includes: adjusting the y-direction coordinate point of the initialized left cardiophrenic angle using the first distance in the y direction to obtain an adjusted left cardiophrenic angle; wherein, the method for adjusting the y-direction coordinate point of the initialized left cardiophrenic angle using the first distance in the y direction to obtain an adjusted left cardiophrenic angle includes: if the first distance in the y direction is greater than or equal to 0, adding the first distance in the y direction to the y-direction coordinate point of the initialized left cardiophrenic angle to obtain an adjusted left cardiophrenic angle; wherein, the x-direction coordinate point corresponding to the adjusted left cardiophrenic angle remains unchanged.

[0123] In the embodiments of the present disclosure and other possible embodiments, the method for completing the positioning optimization of the abnormal left cardiophrenic angle based on the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image includes: configuring the intersection point of the first straight line parallel to the x direction corresponding to the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image as the left cardiophrenic angle after positioning optimization; wherein, the method for configuring the intersection point of the first straight line parallel to the x direction corresponding to the adjusted left cardiophrenic angle and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image as the left cardiophrenic angle after positioning optimization includes: making a first straight line parallel to the x direction with the y-direction coordinate point corresponding to the adjusted left cardiophrenic angle; and configuring the intersection point with the smallest x-direction coordinate among the intersection points of the left lung mask edge of the first straight line and the left lung mask edge image corresponding to the first X-ray two-dimensional chest image as the left cardiophrenic angle after positioning optimization.

[0124] In the embodiments of the present disclosure and other possible embodiments, the method for determining the standard X-ray two-dimensional chest image corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multiple X-ray two-dimensional chest images includes: obtaining the first moment corresponding to the first X-ray two-dimensional chest image; determining the X-ray two-dimensional chest image corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multiple X-ray two-dimensional chest images that is closest to the first moment as the standard X-ray two-dimensional chest image.

[0125] In the embodiments of the present disclosure and other possible embodiments, the method for optimizing the positioning of the abnormal right cardiophrenic angle corresponding to the abnormal right diaphragm in the same second X-ray two-dimensional chest image by using the normal left cardiophrenic angle pair corresponding to the normal left diaphragm in the normal left diaphragm sequence includes: determining the standard X-ray two-dimensional chest image corresponding to the normal left diaphragm and the normal right diaphragm in the dynamic multiple X-ray two-dimensional chest images; configuring the normal right cardiophrenic angle corresponding to the normal right diaphragm in the standard X-ray two-dimensional chest image to the initialized right cardiophrenic angle corresponding to the abnormal right diaphragm in the abnormal right diaphragm sequence in the same second X-ray two-dimensional chest image; calculating a second distance in the y direction between the normal right cardiophrenic angle corresponding to the normal right diaphragm in the standard X-ray two-dimensional chest image and the normal right cardiophrenic angle corresponding to the normal right diaphragm in the second X-ray two-dimensional chest image; adjusting the initialized right cardiophrenic angle by using the second distance in the y direction to obtain an adjusted right cardiophrenic angle; and completing the positioning optimization of the abnormal right cardiophrenic angle based on the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image.

[0126] In the embodiments of the present disclosure and other possible embodiments, the method for adjusting the initialized right cardiophrenic angle by using the second distance in the y direction to obtain an adjusted right cardiophrenic angle includes: adjusting the y-direction coordinate point of the initialized right cardiophrenic angle by using the second distance in the y direction to obtain an adjusted right cardiophrenic angle; wherein, the method for adjusting the y-direction coordinate point of the initialized right cardiophrenic angle by using the second distance in the y direction to obtain an adjusted right cardiophrenic angle includes: if the second distance in the y direction is greater than or equal to 0, adding the second distance in the y direction to the y-direction coordinate point of the initialized right cardiophrenic angle to obtain an adjusted right cardiophrenic angle; wherein, the x-direction coordinate point corresponding to the adjusted right cardiophrenic angle remains unchanged.

[0127] In the embodiments of the present disclosure and other possible embodiments, the method for optimizing the positioning of the abnormal right cardiophrenic angle based on the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image includes: configuring the intersection point of the second straight line parallel to the x-direction corresponding to the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image as the right cardiophrenic angle after positioning optimization; wherein, the method of configuring the intersection point of the second straight line parallel to the x-direction corresponding to the adjusted right cardiophrenic angle and the right lung mask edge image corresponding to the second X-ray two-dimensional chest image as the right cardiophrenic angle after positioning optimization includes: making a second straight line parallel to the x-direction with the y-direction coordinate point corresponding to the adjusted right cardiophrenic angle; configuring the intersection point with the largest x-direction coordinate among the intersection points of the right lung mask edge in the right lung mask edge image between the right cardiophrenic angle after positioning optimization corresponding to each abnormal right diaphragm and the right costophrenic angle point as the right cardiophrenic angle after positioning optimization.

[0128] In the embodiments of the present disclosure and other possible embodiments, the method for determining the standard X-ray two-dimensional chest image corresponding to the normal left diaphragm and the normal right diaphragm in the dynamic multiple X-ray two-dimensional chest images includes: obtaining the second moment corresponding to the second X-ray two-dimensional chest image; determining the X-ray two-dimensional chest images corresponding to the normal right diaphragm and the normal left diaphragm in the dynamic multiple X-ray two-dimensional chest images closest to the second moment as the standard X-ray two-dimensional chest images.

[0129] In the embodiments of the present disclosure, the dynamic lung image intelligent detection method further includes: obtaining the right cardiophrenic angle after positioning optimization corresponding to each abnormal right diaphragm; respectively optimizing the positioning of each abnormal diaphragm based on the right cardiophrenic angle after positioning optimization, the right costophrenic angle point, and the right lung mask edge image corresponding to each abnormal right diaphragm; and / or, obtaining the left cardiophrenic angle after positioning optimization corresponding to each abnormal left diaphragm; respectively optimizing the positioning of each abnormal diaphragm based on the left cardiophrenic angle after positioning optimization, the left costophrenic angle point, and the left lung mask edge image corresponding to each abnormal left diaphragm.

[0130] In the embodiments of the present disclosure and other possible embodiments, the method for optimizing the positioning of each abnormal diaphragm based on the right cardiophrenic angle after positioning optimization, the right costophrenic angle point, and the right lung mask edge image corresponding to each abnormal right diaphragm includes: configuring the line segment between the right lung mask edges in the right lung mask edge image between the right cardiophrenic angle after positioning optimization corresponding to each abnormal right diaphragm and the right costophrenic angle point as the right diaphragm after positioning optimization.

[0131] Similarly, in the embodiments of the present disclosure and other possible embodiments, a method for optimizing the positioning of each of the abnormal diaphragms based on the left cardiophrenic angle, the left costophrenic angle point, and the left lung mask edge image optimized for the positioning corresponding to each of the abnormal left diaphragms respectively includes: configuring a line segment between the left lung mask edges in the left lung mask edge image between the left cardiophrenic angle optimized for the positioning corresponding to each of the abnormal left diaphragms and the left costophrenic angle point as the left diaphragm optimized for the positioning.

[0132] The execution subject of the dynamic lung image intelligent detection method may be an image processing device. For example, the dynamic lung image intelligent detection method may be executed by a terminal device, a server, or other processing devices. Among them, the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementation manners, the dynamic lung image intelligent detection method may be implemented by a processor calling computer-readable instructions stored in a memory.

[0133] Those skilled in the art can understand that in the above dynamic lung image intelligent detection method of the specific implementation manner, the writing order of each step does not mean a strict execution order and constitutes any limitation to the implementation process. The specific execution order of each step should be determined according to its function and possible internal logic.

[0134] The embodiments of the present disclosure also propose a dynamic lung image intelligent detection device, including: an acquisition unit, configured to acquire at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during a breathing process; a detection unit, configured to determine the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; and based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determine the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or determine the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determine the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms.

[0135] In the embodiments of the present disclosure and other possible embodiments, the dynamic lung image intelligent detection device further includes: a cardiophrenic angle positioning optimization unit configured to obtain at least one diaphragmatic muscle sequence of a normal right diaphragmatic muscle and an abnormal right diaphragmatic muscle corresponding to a series of right diaphragmatic muscles, and a normal left diaphragmatic muscle and an abnormal left diaphragmatic muscle corresponding to a series of left diaphragmatic muscles in dynamic multiple X-ray two-dimensional chest images during the breathing process; wherein the diaphragmatic muscle sequence includes: a right diaphragmatic muscle sequence and / or a left diaphragmatic muscle sequence; positioning and optimizing the right cardiophrenic angle corresponding to the abnormal right diaphragmatic muscle based on the right cardiophrenic angle corresponding to the normal right diaphragmatic muscle; and / or, positioning and optimizing the left cardiophrenic angle corresponding to the abnormal left diaphragmatic muscle based on the left cardiophrenic angle corresponding to the normal left diaphragmatic muscle.

[0136] In the embodiments of the present disclosure and other possible embodiments, the dynamic lung image intelligent detection device further includes: a diaphragmatic muscle positioning optimization unit configured to obtain a right cardiophrenic angle after positioning optimization corresponding to each abnormal right diaphragmatic muscle; respectively based on the right cardiophrenic angle after positioning optimization corresponding to each abnormal right diaphragmatic muscle, a right costophrenic angle point, and a right lung mask edge image, perform positioning optimization on each abnormal diaphragmatic muscle; and / or, obtain a left cardiophrenic angle after positioning optimization corresponding to each abnormal left diaphragmatic muscle; respectively based on the left cardiophrenic angle after positioning optimization corresponding to each abnormal left diaphragmatic muscle, a left costophrenic angle point, and a left lung mask edge image, perform positioning optimization on each abnormal diaphragmatic muscle.

[0137] In the embodiments of the present disclosure and other possible embodiments, the detection unit includes at least one of a right diaphragmatic muscle detection unit and a left diaphragmatic muscle detection unit; wherein the right diaphragmatic muscle detection unit is configured to determine the shortest length in a first length sequence corresponding to the dynamic right lung diaphragmatic muscle sequence as the right lung reference diaphragmatic muscle length; based on the right lung reference diaphragmatic muscle length, a first length other than the right lung reference diaphragmatic muscle length in the first length sequence, and a first preset length difference, respectively determine the other right lung diaphragmatic muscles as normal right diaphragmatic muscles or abnormal right diaphragmatic muscles; the left diaphragmatic muscle detection unit is configured to determine the shortest length in a second length sequence corresponding to the dynamic left lung diaphragmatic muscle sequence as the left lung reference diaphragmatic muscle length; based on the left lung reference diaphragmatic muscle length, a second length other than the left lung reference diaphragmatic muscle length in the second length sequence, and a second preset length difference, respectively determine the other left lung diaphragmatic muscles as normal left diaphragmatic muscles or abnormal left diaphragmatic muscles.

[0138] In the embodiments of the present disclosure and other possible embodiments, the right diaphragm detection unit includes: a right lung reference diaphragm length determination unit and a first comparison unit; wherein, the right lung reference diaphragm length determination unit is configured to determine the right lung reference diaphragm by determining the right lung diaphragm with the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; the first comparison unit is configured to respectively determine whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms based on the first reference length corresponding to the right lung reference diaphragm, the first lengths corresponding to the other right lung diaphragms in the dynamic right lung diaphragm sequence except the right lung reference diaphragm, and a first preset length difference.

[0139] In the embodiments of the present disclosure and other possible embodiments, the left diaphragm detection unit includes: a left lung reference diaphragm length determination unit and a second comparison unit; wherein, the left lung reference diaphragm length determination unit is configured to determine the left lung reference diaphragm by determining the left lung diaphragm with the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; the second comparison unit is configured to respectively determine whether the other left lung diaphragms are normal left diaphragms or abnormal left diaphragms based on the second reference length corresponding to the left lung reference diaphragm, the second lengths corresponding to the other left lung diaphragms in the dynamic left lung diaphragm sequence except the left lung reference diaphragm, and a second preset length difference.

[0140] In the embodiments of the present disclosure and other possible embodiments, it further includes one or several of a dynamic right lung diaphragm sequence determination unit and a dynamic left lung diaphragm sequence determination unit; wherein, the dynamic right lung diaphragm sequence determination unit is configured to obtain a right lung mask edge image sequence corresponding to a dynamic plurality of X-ray two-dimensional chest images; respectively determine the right lung apex corresponding to the right lung mask edge image sequence; respectively locate the right lung diaphragm based on the right lung apex, the right costophrenic angle point, and the right lung mask edge image corresponding to each of the dynamic plurality of X-ray two-dimensional chest images. The dynamic left lung diaphragm sequence determination unit is configured to obtain a left lung mask edge image sequence corresponding to a dynamic plurality of X-ray two-dimensional chest images; respectively determine the left lung apex corresponding to the left lung mask edge image sequence, and respectively determine the right costophrenic angle point corresponding to the right lung mask edge image sequence and / or the left costophrenic angle point corresponding to the left lung mask edge image sequence; respectively locate the left lung diaphragm based on the right cardiophrenic angle corresponding to the right lung diaphragm, the left lung apex, the left costophrenic angle point, and the left lung mask edge image corresponding to each of the dynamic plurality of X-ray two-dimensional chest images

[0141] In the embodiments of the present disclosure and other possible embodiments, the right diaphragmatic muscle detection unit further includes one or several of a first length sequence determination unit and a second length sequence determination unit; wherein, the first length sequence determination unit is configured to respectively count the sum of the number of first pixel values corresponding to each right diaphragmatic muscle in the dynamic right lung diaphragmatic muscle sequence; and respectively obtain the first length sequence corresponding to the dynamic right lung diaphragmatic muscle sequence based on the sum of the number of first pixel values corresponding to each right diaphragmatic muscle and the area corresponding to each pixel. Wherein, the second length sequence determination unit is configured to respectively count the sum of the number of second pixel values corresponding to each left diaphragmatic muscle in the dynamic left lung diaphragmatic muscle sequence; and respectively obtain the second length sequence corresponding to the dynamic left lung diaphragmatic muscle sequence based on the sum of the number of second pixel values corresponding to each left diaphragmatic muscle and the area corresponding to each pixel.

[0142] Further, in the embodiments of the present disclosure and other possible embodiments, the first length sequence determination unit includes: a first multiplication unit; the first multiplication unit is configured to respectively multiply the sum of the number of first pixel values corresponding to each right diaphragmatic muscle by the area corresponding to each pixel to obtain the first length sequence corresponding to the dynamic right lung diaphragmatic muscle sequence.

[0143] Further, in the embodiments of the present disclosure and other possible embodiments, the second length sequence determination unit includes: a second multiplication unit; the second multiplication unit is configured to respectively multiply the sum of the number of second pixel values corresponding to each left diaphragmatic muscle by the area corresponding to each pixel to obtain the second length sequence corresponding to the dynamic left lung diaphragmatic muscle sequence.

[0144] The embodiments of the present disclosure also propose a dynamic lung image intelligent detection device, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to call the instructions stored in the memory to execute the above-mentioned dynamic lung image intelligent detection method; wherein, the above-mentioned dynamic lung image intelligent detection method at least includes the following steps: obtaining at least one diaphragmatic muscle sequence of a dynamic right lung diaphragmatic muscle sequence and a dynamic left lung diaphragmatic muscle sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process; determining the right lung reference diaphragmatic muscle length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragmatic muscle sequence; based on the right lung reference diaphragmatic muscle length, the first length other than the right lung reference diaphragmatic muscle length in the first length sequence, and a first preset length difference, respectively determining the other right diaphragmatic muscles as normal right diaphragmatic muscles or abnormal right diaphragmatic muscles; and / or, determining the left lung reference diaphragmatic muscle length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragmatic muscle sequence; based on the left lung reference diaphragmatic muscle length, the second length other than the left lung reference diaphragmatic muscle length in the second length sequence, and a second preset length difference, respectively determining the other left diaphragmatic muscles as normal left diaphragmatic muscles or abnormal left diaphragmatic muscles.

[0145] An embodiment of the present disclosure also provides a dynamic lung image intelligent detection device, including: a computer-readable storage medium storing computer program instructions thereon, and when the computer program instructions are executed by a processor, the above-mentioned dynamic lung image intelligent detection method is implemented; wherein, the above-mentioned dynamic lung image intelligent detection method at least includes the following steps: obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to multiple dynamic X-ray two-dimensional chest images during the breathing process; determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or, determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms.

[0146] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the dynamic lung image intelligent detection method described in the above method embodiments, and its specific implementation can refer to the description of the above dynamic lung image intelligent detection method embodiments. For the sake of brevity, it will not be repeated here.

[0147] An embodiment of the present disclosure also provides a computer-readable storage medium storing computer program instructions thereon, and when the computer program instructions are executed by a processor, the above-mentioned dynamic lung image intelligent detection method is implemented; wherein, the above-mentioned dynamic lung image intelligent detection method at least includes the following steps: obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to multiple dynamic X-ray two-dimensional chest images during the breathing process; determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or, determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms.. The computer-readable storage medium can be a non-volatile computer-readable storage medium.

[0148] An embodiment of the present disclosure also provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to perform the above-mentioned dynamic lung image intelligent detection method; wherein, the above-mentioned dynamic lung image intelligent detection method at least includes the following steps: obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process; determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or, determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms. Wherein, the electronic device can be provided as a terminal, a server or other forms of devices.

[0149] An embodiment of the present disclosure also provides a computer program product, including computer programs / instructions, which when executed by a processor implement the above-mentioned dynamic lung image intelligent detection method; wherein, the above-mentioned dynamic lung image intelligent detection method at least includes the following steps: obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process; determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms; and / or, determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms.

[0150] An embodiment of the present disclosure also provides a dynamic lung image intelligent detection system or medical device, applying the above-mentioned dynamic lung image intelligent detection method and / or including the above-mentioned dynamic lung image intelligent detection device and / or including the above-mentioned computer program product.

[0151] Figure 2FIG. 0 is a block diagram of an electronic device 800 shown in accordance with an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0152] Referring Figure 2 to FIG. 5, the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0153] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-described methods. In addition, the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

[0154] The memory 804 is configured to store various types of data to support the operation of the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a disk, or an optical disc.

[0155] The power component 806 provides power to the various components of the electronic device 800. The power component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

[0156] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). Meanwhile, the audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive external audio signals when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals can be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting audio signals.

[0157] The I / O interface 812 provides an interface between the processing component 802 and a peripheral interface module, and the peripheral interface module can be a keyboard, a click wheel, buttons, etc. These buttons can include but are not limited to: a home button, a volume button, a power button, and a lock button.

[0158] The sensor component 814 includes one or more sensors for providing status assessments of various aspects of the electronic device 800. For example, the sensor component 814 can detect the on / off state of the electronic device 800, the relative positioning of components, such as the display and keypad of the electronic device 800. The sensor component 814 can also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor component 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 814 can also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 814 can further include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0159] The communication component 816 is configured to facilitate communication between the electronic device 800 and other devices in a wired or wireless manner. The electronic device 800 can access a wireless network based on communication standards, such as WiFi, 2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0160] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above method.

[0161] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions, and the computer program instructions can be executed by a processor 820 of the electronic device 800 to complete the above method.

[0162] Figure 3 FIG. 1900 is a block diagram of an electronic device 1900 shown in accordance with an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. Referring to Figure 3 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0163] The electronic device 1900 may further include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

[0164] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, and the computer program instructions can be executed by a processing component 1922 of the electronic device 1900 to complete the above method.

[0165] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0166] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the market, or to enable other ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A dynamic lung image intelligent detection method, characterized in that Including: Obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process; Determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference; and / or determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference.

2. The dynamic lung image intelligent detection method according to claim 1, wherein The method of determining the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; and respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference includes: determining the right lung diaphragm with the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence as the right lung reference diaphragm; respectively determining the other right lung diaphragms as normal right diaphragms or abnormal right diaphragms based on the first reference length corresponding to the right lung reference diaphragm, the first lengths of the other right lung diaphragms in the dynamic right lung diaphragm sequence except the right lung reference diaphragm, and a first preset length difference; and / or The method of determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; and respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference includes: determining the left lung diaphragm with the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence as the left lung reference diaphragm; respectively determining the other left lung diaphragms as normal left diaphragms or abnormal left diaphragms based on the second reference length corresponding to the left lung reference diaphragm, the second lengths of the other left lung diaphragms in the dynamic left lung diaphragm sequence except the left lung reference diaphragm, and a second preset length difference.

3. The intelligent detection method for dynamic lung images according to any one of claims 1-2, characterized in that, Before obtaining at least one diaphragm sequence of a dynamic right lung diaphragm sequence and a dynamic left lung diaphragm sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images during the breathing process, the method of respectively determining the corresponding dynamic right lung diaphragm sequence and / or dynamic left lung diaphragm sequence according to the plurality of dynamic X-ray two-dimensional chest images during the breathing process includes: Respectively obtaining at least one mask edge image sequence of a right lung mask edge image sequence and a left lung mask edge image sequence corresponding to a plurality of dynamic X-ray two-dimensional chest images. Determine the right lung apex corresponding to the right lung mask edge image sequence respectively; locate the right lung diaphragm respectively based on the right lung apex, the right costophrenic angle point and the right lung mask edge image corresponding to each of the dynamic multi - slice X - ray two - dimensional chest images; and / or, determine the left lung apex corresponding to the left lung mask edge image sequence respectively, and determine the right costophrenic angle point corresponding to the right lung mask edge image sequence and / or the left costophrenic angle point corresponding to the left lung mask edge image sequence respectively; locate the left lung diaphragm respectively based on the right cardiophrenic angle corresponding to the right lung diaphragm, the left lung apex, the left costophrenic angle point and the left lung mask edge image corresponding to each of the dynamic multi - slice X - ray two - dimensional chest images; and / or, The method for determining the first length sequence corresponding to the dynamic right lung diaphragm sequence includes: respectively counting the sum of the number of first pixel values corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence; respectively obtaining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the number of first pixel values corresponding to each right lung diaphragm and the area corresponding to each pixel; and / or, the method for determining the first length sequence corresponding to the dynamic right lung diaphragm sequence based on the sum of the number of first pixel values corresponding to each right lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the number of first pixel values corresponding to each right lung diaphragm by the area corresponding to each pixel to obtain the first length sequence corresponding to the dynamic right lung diaphragm sequence; and / or, The method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence includes: respectively counting the sum of the number of second pixel values corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence; respectively obtaining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the number of second pixel values corresponding to each left lung diaphragm and the area corresponding to each pixel; and / or, the method for determining the second length sequence corresponding to the dynamic left lung diaphragm sequence based on the sum of the number of second pixel values corresponding to each left lung diaphragm and the area corresponding to each pixel includes: respectively multiplying the sum of the number of second pixel values corresponding to each left lung diaphragm by the area corresponding to each pixel to obtain the second length sequence corresponding to the dynamic left lung diaphragm sequence.

4. The dynamic lung image intelligent detection method according to claim 3, wherein, The method for respectively determining the right lung apex corresponding to the right lung mask edge image sequence includes: respectively detecting the right lung vertex corresponding to each right lung mask edge image in the right lung mask edge image sequence, and respectively configuring the right lung vertex as the right lung apex corresponding to the right lung mask edge image sequence; and / or, The method for respectively determining the left lung apex corresponding to the left lung mask edge image sequence includes: respectively detecting the left lung vertex corresponding to each left lung mask edge image in the left lung mask edge image sequence, and respectively configuring the left lung vertex as the left lung apex corresponding to the left lung mask edge image sequence; and / or, The method for respectively determining the right costophrenic angle points corresponding to the right lung mask edge image sequence includes: respectively detecting the lowest points of the right lung in each right lung mask edge image in the right lung mask edge image sequence, and respectively configuring the lowest points of the right lung as the right costophrenic angle points corresponding to the right lung mask edge image sequence; and / or, The method for respectively determining the left costophrenic angle points corresponding to the left lung mask edge image sequence includes: respectively detecting the lowest points of the left lung in each left lung mask edge image in the left lung mask edge image sequence, and respectively configuring the lowest points of the left lung as the left costophrenic angle points corresponding to the left lung mask edge image sequence.

5. The intelligent dynamic lung image detection method according to any one of claims 3-4, characterized in that, The method for respectively positioning the right lung diaphragm based on the right lung apex, the right costophrenic angle points, and the right lung mask edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images includes: respectively determining a corresponding first straight line based on the right lung apex and the right costophrenic angle points corresponding to each of the dynamic multiple X-ray two-dimensional chest images; respectively calculating multiple first distances from multiple first pixel position points on the right edge line of the right lung mask edge image from the right lung apex to the right costophrenic angle point to the first straight line; configuring the first pixel position point corresponding to the maximum distance among the multiple first distances as the right cardiophrenic angle, and respectively configuring the mask edge line segment corresponding to the right lung mask edge image between the right cardiophrenic angle and the right costophrenic angle point as the corresponding right lung diaphragm; and / or, The method for respectively positioning the left lung diaphragm based on the right cardiophrenic angle corresponding to the right lung diaphragm, the left lung apex, the left costophrenic angle points, and the left lung mask edge image corresponding to each of the dynamic multiple X-ray two-dimensional chest images includes: respectively determining auxiliary points corresponding to the lung mask edge image based on the coordinate points of the right cardiophrenic angle corresponding to each of the dynamic multiple X-ray two-dimensional chest images and a set increment in the y direction; determining a corresponding second straight line based on the left lung apex and the left costophrenic angle points; respectively calculating multiple second distances from multiple second pixel position points on the left edge line of the left lung mask edge image from the right lung apex to the auxiliary point to the second straight line; configuring the second pixel position point corresponding to the maximum distance among the multiple second distances as the left cardiophrenic angle, and configuring the mask edge line segment corresponding to the left lung mask edge image between the left cardiophrenic angle and the left costophrenic angle point as the corresponding left lung diaphragm.

6. The intelligent detection method for dynamic lung images according to any one of claims 1-5, characterized in that The method for respectively determining whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and the first preset length difference includes: respectively calculating multiple first differences between the first length other than the right lung reference diaphragm length and the right lung reference diaphragm length; if a certain first difference among the multiple differences is greater than or equal to the first preset length difference, determining the right diaphragm corresponding to the certain first difference as an abnormal right diaphragm; otherwise, determining it as a normal right diaphragm; and / or, Determining the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; the method for determining whether the other left lung diaphragms are normal or abnormal based on the left lung reference diaphragm length, the second lengths other than the left lung reference diaphragm length in the second length sequence, and the second preset length difference includes: calculating multiple second differences between the second lengths other than the left lung reference diaphragm length and the left lung reference diaphragm length respectively; if a certain second difference among the multiple second differences is greater than or equal to the second preset length difference, determining the left diaphragm corresponding to the certain second difference as an abnormal left diaphragm; otherwise, determining it as a normal left diaphragm.

7. The intelligent detection method for dynamic lung images according to any one of claims 1-6, characterized in that, Further comprising: Obtaining at least one diaphragm sequence of the right diaphragm sequence corresponding to the normal right diaphragm and the abnormal right diaphragm, and the left diaphragm sequence corresponding to the normal left diaphragm and the abnormal left diaphragm in the dynamic multiple X-ray two-dimensional chest images during the breathing process; wherein, the diaphragm sequence includes: a right diaphragm sequence and / or a left diaphragm sequence; optimizing the positioning of the right cardiophrenic angle corresponding to the abnormal right diaphragm based on the right cardiophrenic angle corresponding to the normal right diaphragm; and / or, optimizing the positioning of the left cardiophrenic angle corresponding to the abnormal left diaphragm based on the left cardiophrenic angle corresponding to the normal left diaphragm; and / or, Obtaining the optimized right cardiophrenic angle corresponding to each abnormal right diaphragm; respectively optimizing the positioning of each abnormal diaphragm based on the optimized right cardiophrenic angle corresponding to each abnormal right diaphragm, the right costophrenic angle point, and the right lung mask edge image; and / or, obtaining the optimized left cardiophrenic angle corresponding to each abnormal left diaphragm; respectively optimizing the positioning of each abnormal diaphragm based on the optimized left cardiophrenic angle corresponding to each abnormal left diaphragm, the left costophrenic angle point, and the left lung mask edge image; and / or, Wherein, the unit of the first length sequence and / or the second length sequence is configured as a pixel value; wherein, respectively counting the sum of the first pixel value numbers corresponding to each right lung diaphragm in the dynamic right lung diaphragm sequence to obtain the first length sequence; and / or, respectively counting the sum of the second pixel value numbers corresponding to each left lung diaphragm in the dynamic left lung diaphragm sequence to obtain the second length sequence; and / or, the first preset length difference and the value configured by the first preset length difference are the same or different; and / or, the first value corresponding to the first preset length difference is configured as any value in 10 - 50 pixels; the second value corresponding to the second preset length difference is configured as any value in 10 - 50 pixels.

8. An intelligent detection device for dynamic lung images, characterized in that, Comprising: An obtaining unit, configured to obtain at least one diaphragm sequence of the dynamic right lung diaphragm sequence and the dynamic left lung diaphragm sequence in the dynamic multiple X-ray two-dimensional chest images during the breathing process; A detection unit, configured to determine the right lung reference diaphragm length as the shortest length in the first length sequence corresponding to the dynamic right lung diaphragm sequence; based on the right lung reference diaphragm length, the first length other than the right lung reference diaphragm length in the first length sequence, and a first preset length difference, respectively determine whether the other right lung diaphragms are normal right diaphragms or abnormal right diaphragms; and / or, determine the left lung reference diaphragm length as the shortest length in the second length sequence corresponding to the dynamic left lung diaphragm sequence; based on the left lung reference diaphragm length, the second length other than the left lung reference diaphragm length in the second length sequence, and a second preset length difference, respectively determine whether the other left lung diaphragms are normal left diaphragms or abnormal left diaphragms; Or, comprising: a processor; a memory for storing instructions executable by the processor; wherein, the processor is configured to call the instructions stored in the memory to execute the dynamic lung image intelligent detection method according to any one of claims 1 to 7; or, comprising: a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the dynamic lung image intelligent detection method according to any one of claims 1 to 7 is implemented.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by a processor, the dynamic lung image intelligent detection method according to any one of claims 1 to 7 is implemented.

10. A medical device, characterized in that, Applying the dynamic lung image intelligent detection method according to any one of claims 1 to 7 and / or comprising the dynamic lung image intelligent detection device according to claim 8 and / or comprising the computer program product according to claim 9.

Images