An analysis system for lung disease rehabilitation data

Abstract

The present invention relates to the technical field of data analysis, and in particular to an analysis system for lung disease rehabilitation data, comprising: a preprocessing layer, an analysis layer and a determination layer; a user's lung CT image is uploaded through the preprocessing layer, the preprocessing layer synchronously performs pixel-level segmentation and lesion position marking on the user's lung CT image, and stores the user's lung CT image that has completed the segmentation and marking operations, the analysis layer synchronously receives the user's lung CT image stored in the preprocessing layer, and based on the pixel-level segmentation and lesion position marking results of the user's lung CT image, the present invention analyzes the user's lung CT image to monitor and compare the lesion changes displayed by chest CT during the user's rehabilitation process in real time, and further digitally represents the changes in the user's rehabilitation process, and then further converts the digitally represented changes in the user's rehabilitation process into visual graphics, so that system end users can read them more quickly and clearly.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to an analysis system for lung disease rehabilitation data. Background Art

[0002] Lung disease refers to diseases that occur in the lung organs and also affect the patient's respiratory function. During the diagnosis and treatment of lung disease, chest CT scans are often used to analyze and characterize the lesions and the severity of the disease.

[0003] The invention patent with application number 202310352094.8 discloses a respiratory rehabilitation assessment system for chronic obstructive pneumonia, which is characterized by comprising a processor and a data acquisition module, a data analysis module, an early warning prompt module and a data storage module connected to the processor in communication:

[0004] After receiving the information sent by the data acquisition module, the data analysis module uses the processor to call the data stored in the data storage module to analyze and process the respiratory rehabilitation training effect of chronic obstructive pneumonia, obtain different evaluation levels, and send the evaluation levels to the early warning prompt module;

[0005] The data analysis module obtains the respiratory muscle rehabilitation evaluation index, the respiratory training evaluation index and the exercise training evaluation index according to the respiratory muscle training data, the respiratory training data and the exercise training data, respectively, and uses the weighted sum of the respiratory muscle rehabilitation evaluation index, the respiratory training evaluation index and the exercise training evaluation index as the comprehensive respiratory rehabilitation evaluation index;

[0006] This application aims to solve the problem that "since respiratory rehabilitation for chronic obstructive pneumonia involves many factors, the existing rehabilitation assessment methods can often only analyze them singly, and the judgment of the effectiveness of respiratory rehabilitation training is inaccurate and superficial, making it difficult to conduct scientific and accurate analysis and evaluation of the rehabilitation effect of respiratory rehabilitation training."

[0007] However, during the rehabilitation and treatment of lung diseases, chest CT scans are often observed and analyzed by specialists to make a diagnosis of the patient's latest condition. This process relies heavily on the specialist's professional knowledge and experience, and it is impossible to objectively and absolutely accurately analyze the patient's recovery progress.

[0008] To this end, we propose an analysis system for lung disease rehabilitation data. Summary of the invention

[0009] In view of the above-mentioned shortcomings of the prior art, the present invention provides an analysis system for lung disease rehabilitation data, which solves the technical problems raised in the above-mentioned background technology.

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0011] An analysis system for lung disease rehabilitation data, comprising: a preprocessing layer, an analysis layer and a determination layer;

[0012] The user's lung CT image is uploaded through the preprocessing layer, the preprocessing layer synchronously performs pixel-level segmentation and lesion position marking on the user's lung CT image, and stores the user's lung CT image that has completed the segmentation and marking operations. The analysis layer synchronously receives the user's lung CT image stored in the preprocessing layer, and analyzes the user's rehabilitation process change situation based on the pixel-level segmentation and lesion position marking results of the user's lung CT image. The determination layer synchronously receives the user's rehabilitation process change situation analyzed in the analysis layer, and determines the user's rehabilitation effect based on the user's rehabilitation process change situation.

[0013] The analysis layer includes a receiving module, a coincidence module and an analysis module. The receiving module is used to receive the user's lung CT images stored in the preprocessing layer that have completed pixel-level segmentation and lesion position marking processing. The coincidence module is used to obtain the user's lung CT images received in the receiving module, and map a group of user's lung CT images uploaded earlier to a group of user's lung CT images uploaded most recently. The analysis module is used to receive the mapping results of the user's lung CT images in the coincidence module, and analyze the user's rehabilitation process change status based on the mapping results.

[0014] The analysis logic of the user's recovery process change situation in the analysis module is expressed as:

[0015]

[0016] Where: τ is the performance value of the user's rehabilitation process change; n is the set of user lesion locations; f former is the size of the corresponding area of ​​the pixel blocks marked with numbers in the group of user lung CT images uploaded earlier in the group of user lung CT images uploaded most recently in the i-th group of lesion locations; fnow is the size of the corresponding area of ​​the pixel blocks marked with numbers in the group of user lung CT images uploaded most recently in the i-th group of lesion locations; m(f former ∪f now ) is the size of the union of two groups of regions; sim(f former ,f now ) is the structural similarity of the two groups of regions;

[0017] Among them, the larger the user rehabilitation process change performance value τ is, the better the user rehabilitation effect is, and vice versa, the worse the user rehabilitation effect is.

[0018] Furthermore, the preprocessing layer includes an uploading module, a processing module and a storage module, the uploading module is used to upload the user's lung CT image, the processing module is used to receive the user's lung CT image uploaded in the uploading module, perform pixel-level segmentation and lesion position marking on the user's lung CT image, the storage module is used to obtain the pixel-level segmentation and lesion position marking results of the user's lung CT image in the processing module, and store the user's lung CT image that has completed pixel-level segmentation and lesion position marking;

[0019] The operation of uploading the user's lung CT image by the uploading module is continuously executed, and the pixel-level segmentation operation of the user's lung CT image in the processing module makes the user's lung CT image be segmented into no less than Group equal-sized pixel blocks;

[0020] In the formula, represents the ratio of the width to the length of the user's lung CT image, 1080 represents the number of equally divided pixel blocks on the long side of the user's lung CT image, Indicates the number of equally divided pixel blocks on the wide edge of the user's lung CT image.

[0021] Furthermore, after the user's lung CT image is segmented at the pixel level, the system end user synchronously traverses each pixel block in the user's lung CT image, and selects the pixel block in the user's lung CT image. The selected pixel block is the lesion position marking target. When marking the pixel block, the selected pixel block is respectively assigned a number, and the number assigned to the pixel block is the marking of the pixel block;

[0022] The system end user selects any two sets of characteristic pixel blocks in the user's lung CT image, and simultaneously identifies the shortest distance and angle between the two sets of characteristic pixel blocks and any two sets of pixel blocks on the edge of the area formed by the selected pixel blocks;

[0023] Among them, the characteristic pixel blocks in the user's lung CT image are all pixel blocks representing the user's sternum endpoints in the user's lung CT image. The lung CT images in the processing module come from the same user. Each time pixel-level segmentation and lesion position marking are performed, the size and number of segmented pixel blocks are equal.

[0024] Furthermore, during the operation phase of the receiving module, the number of user lung CT images stored in the storage module is synchronously received, and when the number of user lung CT images is not less than two groups, the receiving operation of the user lung CT images is performed, and the user lung CT images received each time are the two groups most recently stored in the storage module;

[0025] Among them, the receiving module receives the user's lung CT image from the storage module. After receiving the user's lung CT image, the receiving module synchronously stores the user's lung CT image. A group of user's lung CT images received by the receiving module with an earlier upload time in the storage module are deleted from the storage module.

[0026] Furthermore, during the operation of the overlap module, the operation of mapping a group of user lung CT images uploaded earlier to a group of user lung CT images uploaded most recently is:

[0027] A group of user lung CT images uploaded earlier and a group of user lung CT images uploaded most recently are denoted as x and y, respectively. Two groups of selected characteristic pixel blocks in x are found in y. Further, based on the distance and angle pointed by the characteristic pixel blocks in x, two groups of selected pixel blocks in y are determined. Then, the determined pixel blocks are used to place the marked pixel blocks in x into y accordingly, so that the adjacent position relationship, angle, and distance of each marked pixel block placed in y are consistent with each marked pixel block in x.

[0028] Based on this, there are two sets of lesion location marking results in y, which represents a set of user lung CT images uploaded recently.

[0029] Furthermore, when fformer-fnow=fformer, it means that the lesion position in group i has completely recovered;

[0030]

[0031] Where: The number of pixel blocks in the area corresponding to the pixel blocks marked with numbers in a group of user lung CT images uploaded earlier in the mapped group of user lung CT images uploaded most recently for the lesion location; The number of pixel blocks in the area corresponding to the pixel blocks marked with numbers in a set of user's lung CT images uploaded recently for the lesion location; The number of edge pixel blocks in the region corresponding to the pixel blocks marked with numbers in a group of user lung CT images uploaded earlier in the mapping among the group of user lung CT images uploaded most recently for the lesion location; The number of edge pixel blocks in the area corresponding to the pixel blocks marked with numbers in a set of user's lung CT images uploaded recently for the lesion location.

[0032] Furthermore, f former Always not less than fnow, Always not less than On the contrary, the system decision layer determines f former 、fnow、 The recovery process of the corresponding lesion location changed for the worse.

[0033] Furthermore, the determination layer includes a visualization module, a determination module and an output module. The visualization module is used to receive the user rehabilitation process change situation performance value τ analyzed by the system continuous operation analysis module, and generate a visualization graph based on the received user rehabilitation process change situation performance value τ. The determination module is used to traverse the visualization graph generated in the visualization module, and determine whether the user's rehabilitation state is good based on the visualization graph. The output module is used to receive the determination result in the determination module and output the determination result.

[0034] Among them, the visualization graph generated in the visualization module is a line graph, the horizontal axis of the line graph represents time, and the vertical axis represents the user's rehabilitation process change status performance value τ. When the judgment module determines whether the user's rehabilitation status is good based on the visualization graph, it is determined according to the line shape of the user's rehabilitation process change status performance value τ in the visualization graph. An upward trend in the line indicates that the user's rehabilitation status is good, and a downward trend in the line indicates that the user's rehabilitation process is slowing down.

[0035] Furthermore, during the operation phase of the output module, the output content includes: the visualization graph generated by the visualization module, the determination result of the determination module, and the visualization graph corresponding to the performance value of the user's rehabilitation process change situation at each lesion position obtained by decomposing the visualization graph;

[0036] Among them, the generation logic of the visualization graph corresponding to the user rehabilitation process change status performance value of each lesion position obtained by the visualization graph decomposition is expressed as follows:

[0037]

[0038] Where: τ′ is the status performance value of the user's rehabilitation process change at the lesion location;

[0039] Based on the continuous operation of the system, τ′ is continuously obtained through the above formula, denoted as τ′1, τ′2, τ′3, ..., and a visualization graph representing the user rehabilitation progress change situation performance value τ′ of a group of lesion locations is generated according to τ′1, τ′2, τ′3, ..., and a visualization graph of the user rehabilitation progress change situation performance value τ′ of each group of lesion locations is further generated through the above logic. The visualization graph of the user rehabilitation progress change situation performance value τ′ of each group of lesion locations, that is, the visualization graph corresponding to the user rehabilitation progress change situation performance value of each lesion location obtained based on the decomposition of the visualization graph.

[0040] Furthermore, the upload module is interactively connected to the processing module and the storage module via a wireless network, the storage module is interactively connected to the receiving module via a wireless network, the receiving module is interactively connected to the overlap module and the analysis module via a wireless network, the analysis module is interactively connected to the visualization module via a wireless network, and the visualization module is interactively connected to the determination module and the output module via a wireless network.

[0041] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0042] The present invention provides an analysis system for lung disease rehabilitation data. During operation, the system analyzes the user's lung CT images to monitor and compare the changes in lesions displayed on chest CT during the user's rehabilitation process in real time, and further represents the changes in the user's rehabilitation process in a digital manner. The digitally represented changes in the user's rehabilitation process are further converted into visual graphics, so that system-side users can read them more quickly and clearly. The system-side users, who can be specialist doctors, provide diagnostic references and effectively maintain the stability of the treatment effect during the rehabilitation treatment of patients with lung diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A schematic diagram of a structure of an analysis system for lung disease rehabilitation data;

[0045] Figure 2 It is a schematic diagram of the process of mapping the lesion positions in a group of user lung CT images uploaded earlier and a group of user lung CT images uploaded most recently in the present invention;

[0046] The numbers in the figure represent: 1. A group of user lung CT images uploaded earlier; 2. A group of user lung CT images uploaded recently; 3. Feature pixel block 1; 4. Feature pixel block 2; 5. f former ; 6. fnow. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The present invention will be further described below in conjunction with the embodiments.

[0049] Embodiment 1:

[0050] In this embodiment, a system for analyzing lung disease rehabilitation data is provided. Figure 1 As shown, it includes: a pre-processing layer, an analysis layer and a decision layer;

[0051] The user's lung CT image is uploaded through the preprocessing layer, the preprocessing layer synchronously performs pixel-level segmentation and lesion position marking on the user's lung CT image, and stores the user's lung CT image that has completed the segmentation and marking operations. The analysis layer synchronously receives the user's lung CT image stored in the preprocessing layer, and analyzes the user's rehabilitation process change situation based on the pixel-level segmentation and lesion position marking results of the user's lung CT image. The determination layer synchronously receives the user's rehabilitation process change situation analyzed in the analysis layer, and determines the user's rehabilitation effect based on the user's rehabilitation process change situation.

[0052] The preprocessing layer includes an upload module, a processing module and a storage module. The upload module is used to upload the user's lung CT image. The processing module is used to receive the user's lung CT image uploaded in the upload module, perform pixel-level segmentation and lesion position marking on the user's lung CT image, and the storage module is used to obtain the pixel-level segmentation and lesion position marking results of the user's lung CT image in the processing module, and store the user's lung CT image that has completed pixel-level segmentation and lesion position marking;

[0053] The operation of uploading the user's lung CT image by the uploading module is continuously executed, and the pixel-level segmentation operation of the user's lung CT image in the processing module makes the user's lung CT image be segmented into no less than Group equal-sized pixel blocks;

[0054] In the formula, represents the ratio of the width to the length of the user's lung CT image, 1080 represents the number of equally divided pixel blocks on the long side of the user's lung CT image, Indicates the number of equally divided pixel blocks on the wide edge of the user's lung CT image;

[0055] The analysis layer includes a receiving module, a coincidence module and an analysis module. The receiving module is used to receive the user's lung CT images that have completed pixel-level segmentation and lesion position marking processing and are stored in the preprocessing layer. The coincidence module is used to obtain the user's lung CT images received in the receiving module, and map a group of user's lung CT images uploaded earlier to a group of user's lung CT images uploaded most recently. The analysis module is used to receive the mapping results of the user's lung CT images in the coincidence module, and analyze the user's rehabilitation process change status based on the mapping results.

[0056] The analysis logic of the user recovery process change situation in the analysis module is expressed as:

[0057]

[0058] Where: τ is the performance value of the user's rehabilitation process change; n is the set of user lesion locations; f former is the size of the corresponding area of ​​the pixel blocks marked with numbers in the group of user lung CT images uploaded most recently at the i-th group of lesion locations, mapped to a group of user lung CT images with an earlier upload time; fnow is the size of the corresponding area of ​​the pixel blocks marked with numbers in the group of user lung CT images uploaded most recently at the i-th group of lesion locations; is the size of the union of two groups of regions; sim(f former ,f now ) is the structural similarity of the two groups of regions;

[0059] Among them, the larger the user rehabilitation process change performance value τ is, the better the user rehabilitation effect is, and vice versa, the worse the user rehabilitation effect is;

[0060] f former Always not less than fnow, Always not less than On the contrary, the system decision layer determines f former 、fnow、 The change trend of the recovery process of the corresponding lesion location is worsening;

[0061] The determination layer includes a visualization module, a determination module and an output module. The visualization module is used to receive the user rehabilitation process change situation performance value τ analyzed by the system continuous operation analysis module, and generate a visualization graph based on the received user rehabilitation process change situation performance value τ. The determination module is used to traverse the visualization graph generated in the visualization module, and determine whether the user's rehabilitation status is good based on the visualization graph. The output module is used to receive the determination result in the determination module and output the determination result.

[0062] Among them, the visualization graph generated in the visualization module is a line graph, the horizontal axis of the line graph represents time, and the vertical axis represents the user's rehabilitation process change situation performance value τ. When the determination module determines whether the user's rehabilitation status is good based on the visualization graph, it determines according to the line shape representing the user's rehabilitation process change situation performance value τ in the visualization graph. An upward trend in the line shape indicates that the user's rehabilitation status is good, and a downward trend in the line shape indicates that the user's rehabilitation progress is slowing down;

[0063] The uploading module is interactively connected to the processing module and the storage module through a wireless network, the storage module is interactively connected to the receiving module through a wireless network, the receiving module is interactively connected to the overlap module and the analysis module through a wireless network, the analysis module is interactively connected to the visualization module through a wireless network, and the visualization module is interactively connected to the determination module and the output module through a wireless network.

[0064] In this embodiment, the uploading module runs to upload the user's lung CT image, the processing module is synchronized with the user's lung CT image uploaded in the receiving uploading module, and the user's lung CT image is segmented at the pixel level and the lesion position is marked. The storage module obtains the pixel level segmentation and lesion position marking results of the user's lung CT image in the processing module in real time, and stores the user's lung CT image that has completed the pixel level segmentation and lesion position marking. The receiving module further receives the user's lung CT image that has completed the pixel level segmentation and lesion position marking processing stored in the preprocessing layer, and then the user's lung CT image received in the receiving module is obtained by the overlap module, and the user's lung CT image with an earlier upload time is stored. A group of user lung CT images are mapped to a group of user lung CT images that have been uploaded most recently, and the analysis module receives the mapping results of the user lung CT images in the overlap module. The user rehabilitation process change situation is analyzed based on the mapping results. Finally, the visualization module receives the user rehabilitation process change situation performance value τ analyzed by the system continuous operation analysis module. A visualization graph is generated based on the received user rehabilitation process change situation performance value τ. The judgment module traverses the visualization graph generated in the visualization module in real time, and determines whether the user's rehabilitation status is good based on the visualization graph. The output module further receives the judgment result in the judgment module and outputs the judgment result.

[0065] Through the system operation in the above embodiment, image analysis based on chest CT images for patients with lung diseases is carried out, which brings about an intelligent rehabilitation status monitoring effect, so that more reference data can be provided for lung disease patient specialists to achieve a more intelligent, more accurate, more stable, safe and reliable monitoring effect of the rehabilitation progress of lung disease patients.

[0066] See also Figure 2 As shown, based on the numbers in the figure, the figure further shows the process of mapping the lesion locations in a group of user lung CT images uploaded earlier and a group of user lung CT images uploaded most recently;

[0067] It should be noted that the lines between the numbers 3 and 4 in the figure represent the shortest distances between the two groups of feature pixel blocks and any two groups of pixel blocks on the edge of the area formed by the selected pixel blocks.

[0068] Embodiment 2:

[0069] In terms of specific implementation, based on Example 1, this example refers to Figure 1 The analysis system for lung disease rehabilitation data in Example 1 is further described in detail:

[0070] After the user's lung CT image is segmented at the pixel level, the system end user synchronously traverses each pixel block in the user's lung CT image and selects the pixel block in the user's lung CT image. The selected pixel block is the lesion position marking target. When marking the pixel block, the selected pixel block is respectively assigned a number, and the number assigned to the pixel block is the marking of the pixel block;

[0071] The system end user selects any two sets of characteristic pixel blocks in the user's lung CT image, and simultaneously identifies the shortest distance and angle between the two sets of characteristic pixel blocks and any two sets of pixel blocks on the edge of the area formed by the selected pixel blocks;

[0072] Among them, the characteristic pixel blocks in the user's lung CT image are all pixel blocks representing the user's sternum endpoints in the user's lung CT image. The lung CT images in the processing module come from the same user. Each time pixel-level segmentation and lesion position marking are performed, the size and number of segmented pixel blocks are equal.

[0073] Through the above settings, the operating logic of the processing module in the preprocessing layer of the system is further limited to ensure the stable operation of the processing module and perform pixel-level segmentation and lesion location marking on the user's lung CT image.

[0074] like Figure 1 As shown, during the operation phase of the receiving module, the number of user lung CT images stored in the storage module is synchronously received, and when the number of user lung CT images is not less than two groups, the operation of receiving the user lung CT images is performed, and the user lung CT images received each time are the two groups most recently stored in the storage module;

[0075] Among them, the receiving module receives the user's lung CT image from the storage module. After receiving the user's lung CT image, the receiving module synchronously stores the user's lung CT image. A group of user's lung CT images received by the receiving module with an earlier upload time in the storage module are deleted from the storage module.

[0076] Through the above settings, the linkage operation logic of the storage module in the preprocessing layer and the receiving module in the analysis layer of the system is further limited, and based on the above logic, it is ensured that the storage module is not easily fully loaded due to storing user lung CT images.

[0077] like Figure 1 As shown, during the operation phase of the overlap module, the operation of mapping a group of user lung CT images uploaded earlier to a group of user lung CT images uploaded most recently is:

[0078] A group of user lung CT images uploaded earlier and a group of user lung CT images uploaded most recently are denoted as x and y, respectively. Two groups of selected characteristic pixel blocks in x are found in y. Further, based on the distance and angle pointed by the characteristic pixel blocks in x, two groups of selected pixel blocks in y are determined. Then, the determined pixel blocks are used to place the marked pixel blocks in x into y accordingly, so that the adjacent position relationship, angle, and distance of each marked pixel block placed in y are consistent with each marked pixel block in x.

[0079] Based on this, there are two sets of lesion location marking results in y, which represents a set of user lung CT images uploaded recently.

[0080] Through the above settings, the process and logic of mapping between a group of user lung CT images uploaded earlier and a group of user lung CT images uploaded most recently are further limited.

[0081] Embodiment 3:

[0082] In terms of specific implementation, based on Example 1, this example refers to Figure 1 The analysis system for lung disease rehabilitation data in Example 1 is further described in detail:

[0083] When fformer-fnow=fformer, it means that the lesion position in group i has completely recovered;

[0084]

[0085] Where: The number of pixel blocks in the area corresponding to the pixel blocks marked with numbers in a group of user lung CT images uploaded earlier in the mapped group of user lung CT images uploaded most recently for the lesion location; The number of pixel blocks in the area corresponding to the pixel blocks marked with numbers in a set of user's lung CT images uploaded recently for the lesion location; The number of pixel blocks at the edge of the region corresponding to the pixel blocks marked with numbers in a group of user lung CT images uploaded earlier in the mapping, among a group of user lung CT images uploaded most recently for the lesion location; The number of edge pixel blocks in the area corresponding to the pixel blocks marked with numbers in a set of user's lung CT images uploaded recently for the lesion location.

[0086] Through the above settings, further data and logical condition support are provided for the user rehabilitation city change situation analysis logic in the analysis module in Example 1, ensuring the stable execution of the user rehabilitation city change situation analysis logic in the analysis module.

[0087] like Figure 1 As shown, during the operation phase of the output module, the output contents include: the visualization graph generated by the visualization module, the determination result of the determination module, and the visualization graph corresponding to the performance value of the user's rehabilitation process change at each lesion position obtained by decomposing the visualization graph;

[0088] Among them, the generation logic of the visualization graph corresponding to the user rehabilitation process change status performance value of each lesion position obtained by the visualization graph decomposition is expressed as follows:

[0089]

[0090] Where: τ′ is the status performance value of the user's rehabilitation process change at the lesion location;

[0091] Based on the continuous operation of the system, τ′ is continuously obtained through the above formula, denoted as τ′1, τ′2, τ′3, ..., and a visualization graph representing the user rehabilitation progress change situation performance value τ′ of a group of lesion locations is generated according to τ′1, τ′2, τ′3, ..., and a visualization graph of the user rehabilitation progress change situation performance value τ′ of each group of lesion locations is further generated through the above logic. The visualization graph of the user rehabilitation progress change situation performance value τ′ of each group of lesion locations, that is, the visualization graph corresponding to the user rehabilitation progress change situation performance value of each lesion location obtained based on the decomposition of the visualization graph.

[0092] Through the above formula, the output content of the output module operation and the generation logic of the visualization graphics corresponding to the user's rehabilitation process change status performance value of each lesion position obtained by decomposing the visualization graphics in the output content are further limited, so as to realize further separate monitoring and rehabilitation process analysis and evaluation of each lesion position in the user's CT image.

[0093] In summary, during operation, the system in the above embodiment monitors and compares the changes in lesions displayed on the chest CT during the user's rehabilitation process in real time by analyzing the user's lung CT images, and further represents the changes in the user's rehabilitation process in a digital manner, and then further converts the digitally represented changes in the user's rehabilitation process into a visual graph, so that the system end user can read it more quickly and clearly, providing a diagnostic reference for the system end user, who can be a specialist doctor, and effectively maintaining the stability of the treatment effect during the rehabilitation treatment of patients with lung diseases.

[0094] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An analysis system for lung disease rehabilitation data, characterized in that: include: Preprocessing layer, analysis layer and decision layer; The user's lung CT image is uploaded through the preprocessing layer, the preprocessing layer synchronously performs pixel-level segmentation and lesion position marking on the user's lung CT image, and stores the user's lung CT image that has completed the segmentation and marking operations. The analysis layer synchronously receives the user's lung CT image stored in the preprocessing layer, and analyzes the user's rehabilitation process change situation based on the pixel-level segmentation and lesion position marking results of the user's lung CT image. The determination layer synchronously receives the user's rehabilitation process change situation analyzed in the analysis layer, and determines the user's rehabilitation effect based on the user's rehabilitation process change situation. The analysis layer includes a receiving module, a coincidence module and an analysis module. The receiving module is used to receive the user's lung CT images stored in the preprocessing layer that have completed pixel-level segmentation and lesion position marking processing. The coincidence module is used to obtain the user's lung CT images received in the receiving module, and map a group of user's lung CT images uploaded earlier to a group of user's lung CT images uploaded most recently. The analysis module is used to receive the mapping results of the user's lung CT images in the coincidence module, and analyze the user's rehabilitation process change status based on the mapping results. The analysis logic of the user's recovery process change situation in the analysis module is expressed as: Where: τ is the performance value of the user's rehabilitation process change; n is the set of user lesion locations; f former is the size of the corresponding area of ​​the pixel blocks marked with numbers in the group of user lung CT images uploaded earlier in the group of user lung CT images uploaded most recently in the i-th group of lesion locations; fnow is the size of the corresponding area of ​​the pixel blocks marked with numbers in the group of user lung CT images uploaded most recently in the i-th group of lesion locations; m(f former ∪f now ) is the size of the union of two groups of regions; sim(f former ,f now ) is the structural similarity of the two groups of regions; Among them, the larger the user rehabilitation process change performance value τ is, the better the user rehabilitation effect is, and vice versa, the worse the user rehabilitation effect is; During the operation phase of the overlap module, the operation of mapping a group of user lung CT images uploaded earlier to a group of user lung CT images uploaded most recently is: A group of user lung CT images uploaded earlier and a group of user lung CT images uploaded most recently are denoted as x and y, respectively. Two groups of selected characteristic pixel blocks in x are found in y. Further, based on the distance and angle pointed by the characteristic pixel blocks in x, two groups of selected pixel blocks in y are determined. Then, the determined pixel blocks are used to place the marked pixel blocks in x into y accordingly, so that the adjacent position relationship, angle, and distance of each marked pixel block placed in y are consistent with each marked pixel block in x. Based on this, it indicates that there are two sets of lesion location marking results in y of a set of user's lung CT images uploaded recently; When fformer-fnow=fformer, it means that the lesion position in group i has completely recovered; Where: The number of pixel blocks in the area corresponding to the pixel blocks marked with numbers in a group of user lung CT images uploaded earlier in the mapped group of user lung CT images uploaded most recently for the lesion location; The number of pixel blocks in the area corresponding to the pixel blocks marked with numbers in a set of user's lung CT images uploaded recently for the lesion location; The number of edge pixel blocks in the region corresponding to the pixel blocks marked with numbers in a group of user lung CT images uploaded earlier in the mapping among the group of user lung CT images uploaded most recently for the lesion location; The number of edge pixel blocks in the area corresponding to the pixel blocks marked with numbers in a group of user's lung CT images uploaded recently for the lesion location; f former Always not less than fnow, Always not less than On the contrary, the system decision layer determines f former 、fnow、 The change trend of the recovery process of the corresponding lesion location is worsening; The determination layer includes a visualization module, a determination module and an output module. The visualization module is used to receive the user rehabilitation process change situation performance value τ analyzed by the system continuous operation analysis module, and generate a visualization graph based on the received user rehabilitation process change situation performance value τ. The determination module is used to traverse the visualization graph generated in the visualization module, and determine whether the user's rehabilitation status is good based on the visualization graph. The output module is used to receive the determination result in the determination module and output the determination result. Among them, the visualization graph generated in the visualization module is a line graph, the horizontal axis of the line graph represents time, and the vertical axis represents the user's rehabilitation process change situation performance value τ. When the determination module determines whether the user's rehabilitation status is good based on the visualization graph, it determines according to the line shape representing the user's rehabilitation process change situation performance value τ in the visualization graph. An upward trend in the line shape indicates that the user's rehabilitation status is good, and a downward trend in the line shape indicates that the user's rehabilitation progress is slowing down; During the operation phase of the output module, the output content includes: the visualization graph generated by the visualization module, the determination result of the determination module, and the visualization graph corresponding to the performance value of the user's rehabilitation process change at each lesion position obtained by decomposing the visualization graph; Among them, the generation logic of the visualization graph corresponding to the user rehabilitation process change status performance value of each lesion position obtained by the visualization graph decomposition is expressed as follows: Where: τ′ is the status performance value of the user's rehabilitation process change at the lesion location; Based on the continuous operation of the system, τ′ is continuously obtained through the above formula, denoted as τ′1, τ′2, τ′3, ..., and a visualization graph representing the user rehabilitation progress change situation performance value τ′ of a group of lesion locations is generated according to τ′1, τ′2, τ′3, ..., and a visualization graph of the user rehabilitation progress change situation performance value τ′ of each group of lesion locations is further generated through the above logic. The visualization graph of the user rehabilitation progress change situation performance value τ′ of each group of lesion locations, that is, the visualization graph corresponding to the user rehabilitation progress change situation performance value of each lesion location obtained based on the decomposition of the visualization graph.

2. The analysis system for lung disease rehabilitation data according to claim 1, characterized in that: The preprocessing layer includes an uploading module, a processing module and a storage module. The uploading module is used to upload the user's lung CT image. The processing module is used to receive the user's lung CT image uploaded in the uploading module, perform pixel-level segmentation and lesion position marking on the user's lung CT image, and the storage module is used to obtain the pixel-level segmentation and lesion position marking results of the user's lung CT image in the processing module, and store the user's lung CT image that has completed pixel-level segmentation and lesion position marking. The operation of uploading the user's lung CT image by the uploading module is continuously executed, and the pixel-level segmentation operation of the user's lung CT image in the processing module makes the user's lung CT image be segmented into no less than Group equal-sized pixel blocks; In the formula, represents the ratio of the width to the length of the user's lung CT image, 1080 represents the number of equally divided pixel blocks on the long side of the user's lung CT image, Indicates the number of equally divided pixel blocks on the wide edge of the user's lung CT image.

3. The analysis system for lung disease rehabilitation data according to claim 2, characterized in that: After the user's lung CT image is segmented at the pixel level, the system end user synchronously traverses each pixel block in the user's lung CT image and selects the pixel block in the user's lung CT image. The selected pixel block is the lesion position marking target. When marking the pixel block, the selected pixel block is respectively assigned a number, and the number assigned to the pixel block is the marking of the pixel block; The system end user selects any two sets of characteristic pixel blocks in the user's lung CT image, and simultaneously identifies the shortest distance and angle between the two sets of characteristic pixel blocks and any two sets of pixel blocks on the edge of the area formed by the selected pixel blocks; Among them, the characteristic pixel blocks in the user's lung CT image are all pixel blocks representing the user's sternum endpoints in the user's lung CT image. The lung CT images in the processing module come from the same user. Each time pixel-level segmentation and lesion position marking are performed, the size and number of segmented pixel blocks are equal.

4. The analysis system for lung disease rehabilitation data according to claim 1, characterized in that: During the operation phase of the receiving module, the number of user lung CT images stored in the storage module is synchronously received, and when the number of user lung CT images is not less than two groups, the operation is performed to receive the user lung CT images, and the user lung CT images received each time are the two groups most recently stored in the storage module; Among them, the receiving module receives the user's lung CT image from the storage module. After receiving the user's lung CT image, the receiving module synchronously stores the user's lung CT image. A group of user's lung CT images received by the receiving module with an earlier upload time in the storage module are deleted from the storage module.

5. The analysis system for lung disease rehabilitation data according to claim 2, characterized in that: The uploading module is interactively connected to the processing module and the storage module via a wireless network, the storage module is interactively connected to the receiving module via a wireless network, the receiving module is interactively connected to the overlap module and the analysis module via a wireless network, the analysis module is interactively connected to the visualization module via a wireless network, and the visualization module is interactively connected to the determination module and the output module via a wireless network.

Images