System for identifying MASH and MASH inflammation degree

Abstract

The invention discloses a system for identifying MASH and MASH inflammation degree, and belongs to the technical field of medical treatment. Comprising a fat content distribution matrix acquisition module, a liver elasticity distribution matrix acquisition module, a severe fat lesion area acquisition module, a hepatic fibrosis area acquisition module, a severe fat lesion surrounding area acquisition module, a hepatic fibrosis surrounding area acquisition module, a weighted IQ envelope signal acquisition module, and an MASH and MASH inflammation degree identification module. According to the method, the MASH and the inflammation degree of the MASH can be safely, quickly and accurately identified.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical treatment, and more particularly to a system for identifying MASH and the inflammation degree of MASH. BACKGROUND

[0002] Among the spectrum of liver diseases, metabolic dysfunction-associated steatohepatitis (MASH) has become one of the most common chronic liver diseases worldwide. Its early feature is the abnormal accumulation of fat in liver cells (fat content > 5%), which is usually not accompanied by significant inflammation or fibrosis, and is a reversible condition that can be normalized by lifestyle intervention (liver cell fat content < 5%). However, if not treated in time, MASLD can gradually progress to MASH, accompanied by hepatocyte ballooning and lobular inflammation, and further induce liver fibrosis, cirrhosis and even hepatocellular carcinoma. Therefore, accurate identification of MASH is of great significance for blocking disease progression and implementing early intervention.

[0003] Currently, liver tissue biopsy is still the gold standard for clinically diagnosing MASH, which can directly observe key pathological features such as steatosis, inflammation activity and ballooning. However, liver biopsy is an invasive procedure that has the risk of sampling error, bleeding and infection, and is difficult to be used as an ideal means for repeated screening and dynamic monitoring. In recent years, non-invasive diagnostic techniques have become a research hotspot, among which liver stiffness measurement has been widely used to assess the degree of fibrosis. The traditional view often considers liver stiffness values greater than 7.3 kPa as the threshold for cirrhosis, but recent studies suggest that liver stiffness has increased significantly in the early stages of MASH. For example, a patent entitled "Tissue inflammation activity detection device" in the prior art discloses that liver stiffness in the range of 8.7 kPa to 9.7 kPa indicates that MASH is in the mild inflammation stage, and stiffness exceeding 9.7 kPa indicates that MASH has progressed to severe inflammation, which will rapidly evolve into irreversible cirrhosis if not controlled. This finding has revised the previous understanding of the change pattern of liver stiffness, indicating that the stiffness threshold alone cannot fully reflect the inflammation degree of MASH.

[0004] Therefore, how to provide a system for identifying MASH and the inflammation degree of MASH, which can safely, quickly and accurately identify MASH and the inflammation degree of MASH, is a problem that those skilled in the art need to solve. SUMMARY

[0005] Therefore, the purpose of the present application is to provide a system for identifying MASH and the inflammation degree of MASH.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0007] The system for identifying MASH and MASH inflammation degree comprises a fat content distribution matrix acquisition module, a liver elasticity distribution matrix acquisition module, a severe fatty lesion area acquisition module, a liver fibrosis area acquisition module, a severe fatty lesion surrounding area acquisition module, a liver fibrosis surrounding area acquisition module, a weighted IQ envelope signal acquisition module, and a MASH and MASH inflammation degree identification module.

[0008] The fat content distribution matrix acquisition module is configured to extract a fat content distribution matrix from a single-frame IQ envelope signal, wherein the single-frame IQ envelope signal is an IQ envelope signal corresponding to a single-frame liver ultrasound signal.

[0009] The liver elasticity distribution matrix acquisition module is configured to extract a liver elasticity distribution matrix corresponding to the single-frame IQ envelope signal.

[0010] The severe fatty lesion area acquisition module is configured to perform preset threshold judgment on the clustered fat content distribution matrix to obtain a severe fatty lesion area.

[0011] The liver fibrosis area acquisition module is configured to perform preset threshold judgment on the clustered liver elasticity distribution matrix to obtain a liver fibrosis area.

[0012] The severe fatty lesion surrounding area acquisition module is configured to perform dilation processing on the severe fatty lesion area and then subtract the severe fatty lesion area to obtain a severe fatty lesion surrounding area.

[0013] The liver fibrosis surrounding area acquisition module is configured to perform dilation processing on the liver fibrosis area and then subtract the liver fibrosis area to obtain a liver fibrosis surrounding area.

[0014] The weighted IQ envelope signal acquisition module is configured to process multiple-frame IQ envelope signals based on the severe fatty lesion surrounding area and the liver fibrosis surrounding area to obtain a weighted IQ envelope signal.

[0015] The MASH and MASH inflammation degree identification module is configured to perform channel splicing, feature extraction, and classification on the weighted IQ envelope signal and the multiple-frame IQ envelope signals to obtain a MASH and MASH inflammation degree identification result.

[0016] Preferably, the fat content distribution matrix acquisition module comprises a Shannon entropy matrix acquisition submodule and an alignment submodule.

[0017] The Shannon entropy matrix acquisition submodule is configured to traverse the single-frame IQ envelope signal by using a sliding window and calculate a Shannon entropy value of each sliding window to obtain a Shannon entropy matrix of the single-frame IQ envelope signal.

[0018] The alignment submodule is configured to sample the Shannon entropy matrix to the same size as the single-frame IQ envelope signal to obtain the fat content distribution matrix.

[0019] Preferably, the Shannon entropy value of each sliding window is obtained based on the following formula:

[0020]

[0021] wherein w(x i ) represents the probability of the i-th gray level appearing in the gray histogram of the IQ envelope signal in the sliding window; n represents the total number of gray levels into which the amplitude range of the IQ envelope signal in the sliding window is divided; H c represents the Shannon entropy value of the sliding window.

[0022] Preferably, the sliding window is a square, and the side length of the square is one pulse length of the ultrasonic transducer.

[0023] Preferably, the severe fat lesion area obtaining module comprises a first clustering submodule and a first threshold judgment submodule.

[0024] The first clustering submodule is configured to perform K-means clustering on the fat content distribution matrix to obtain a healthy liver region, a mild-to-moderate fatty liver region, and a severe fatty liver region.

[0025] The first threshold judgment submodule is configured to obtain the severe fat lesion area based on a first preset threshold and the cluster center values of the healthy liver region, the mild-to-moderate fatty liver region, and the severe fatty liver region; if the cluster center values of the healthy liver region, the mild-to-moderate fatty liver region, and the severe fatty liver region are all less than the first preset threshold, the severe fat lesion area is set as a 0 matrix; if the cluster center values of the healthy liver region, the mild-to-moderate fatty liver region, and the severe fatty liver region are not all less than the first preset threshold, the severe fat lesion area is a region in which all cluster center values are greater than or equal to the first preset threshold.

[0026] Preferably, the liver fibrosis area obtaining module comprises a second clustering submodule and a second threshold judgment submodule.

[0027] The second clustering submodule is configured to perform K-means clustering on the liver elasticity distribution matrix to obtain a healthy liver stiffness region, a mild-to-moderate liver fibrosis region, and a severe liver fibrosis region.

[0028] The second threshold determination submodule is used to obtain the liver fibrosis region based on a second preset threshold and the cluster center values ​​of the healthy liver stiffness region, the mild to moderate liver fibrosis region, and the severe liver fibrosis region. If the cluster center values ​​of the healthy liver stiffness region, the mild to moderate liver fibrosis region, and the severe liver fibrosis region are all less than the second preset threshold, then the liver fibrosis region is set to a 0 matrix. If the cluster center values ​​of the healthy liver stiffness region, the mild to moderate liver fibrosis region, and the severe liver fibrosis region are not all less than the second preset threshold, then the liver fibrosis region is the region where all cluster center values ​​are greater than or equal to the second preset threshold.

[0029] Preferably, the weighted IQ envelope signal acquisition module includes a 3D MASK region acquisition submodule, a MASK region merging submodule, and a weighted dot product submodule;

[0030] The 3D MASK region acquisition submodule is used to perform binarization processing on the 3D region surrounding severe fatty lesions and the 3D region surrounding liver fibrosis to obtain two 3D MASK regions; wherein, multiple frames of the region surrounding severe fatty lesions constitute the 3D region surrounding severe fatty lesions; and multiple frames of the region surrounding liver fibrosis constitute the 3D region surrounding liver fibrosis.

[0031] The MASK region merging submodule is used to calculate the union of the regions surrounding severe fatty lesions and liver fibrosis in each MASK frame, and then merge the two 3D MASK regions into one, obtaining a merged MASK region. If the number of pixels with a value of 1 in the merged MASK region is greater than a third preset threshold, the merged MASK region is input to the weighted dot multiplication submodule; if it is less than the third preset threshold, the IQ envelope signals of multiple frames are directly input into the convolutional neural network and the fully connected layer in sequence to obtain the MASH and MASH inflammation degree recognition results.

[0032] The weighted dot multiplier submodule is used to obtain a weighted IQ envelope signal based on the merged MASK region, preset weight coefficients, and the multi-frame IQ envelope signal; wherein, the calculation formula for the weighted IQ envelope signal is: M represents the weighted IQ envelope signal. IQ The multi-frame IQ envelope signal represents the signal, α represents the preset weighting coefficient, and M represents the multi-frame IQ envelope signal. ROI The '·' indicates the merged MASK region, and '·' indicates matrix dot product.

[0033] Preferably, the system also includes a 3D acquisition submodule for the area surrounding severe steatosis and a 3D acquisition submodule for the area surrounding liver fibrosis;

[0034] The 3D severe fatty lesion peripheral region acquisition submodule is configured to sequentially process the multiple frames of IQ envelope signals through the fat content distribution matrix acquisition module, the severe fatty lesion region acquisition submodule, and the severe fatty lesion peripheral region acquisition submodule, to obtain multiple frames of the severe fatty lesion peripheral region.

[0035] The 3D liver fibrosis peripheral region acquisition submodule is configured to sequentially extract multiple frames of liver elasticity distribution matrices corresponding to the multiple frames of IQ envelope signals by using the liver elasticity distribution matrix acquisition module, and sequentially process the multiple frames of liver elasticity distribution matrices through the liver fibrosis region acquisition submodule and the liver fibrosis peripheral region acquisition submodule, to obtain multiple frames of the liver fibrosis peripheral region.

[0036] Preferably, the system further comprises a 3D severe fatty lesion peripheral region acquisition submodule and a 3D liver fibrosis peripheral region acquisition submodule.

[0037] The 3D severe fatty lesion peripheral region acquisition submodule is configured to sequentially process the multiple frames of IQ envelope signals through the fat content distribution matrix acquisition module, the severe fatty lesion region acquisition submodule, and the severe fatty lesion peripheral region acquisition submodule, to obtain multiple frames of the severe fatty lesion peripheral region.

[0038] The 3D liver fibrosis peripheral region acquisition submodule is configured to extract a selected liver elasticity distribution matrix corresponding to a selected frame of IQ envelope signal by using the liver elasticity distribution matrix acquisition module, then expand the number of channels of the selected liver elasticity distribution matrix to the same number of frames as the multiple frames of IQ envelope signals, and sequentially process the multiple frames of IQ envelope signals through the liver fibrosis region acquisition submodule and the liver fibrosis peripheral region acquisition submodule, to obtain multiple frames of the liver fibrosis peripheral region; wherein the selected frame of IQ envelope signal is a certain frame of IQ envelope signal in the multiple frames of IQ envelope signals.

[0039] Preferably, the MASH and MASH inflammation degree recognition module comprises a channel splicing layer, a convolutional neural network, and a fully connected layer.

[0040] The channel splicing layer is configured to splice the weighted IQ envelope signal and the multiple frames of IQ envelope signals in the channel to obtain a spliced IQ envelope signal.

[0041] The convolutional neural network is configured to extract features from the spliced IQ envelope signal to obtain CNN features.

[0042] The fully connected layer is configured to classify the CNN features to obtain the MASH and MASH inflammation degree recognition result; wherein the MASH and MASH inflammation degree recognition result comprises no inflammation, mild inflammation, and severe inflammation.

[0043] As can be seen from the above technical solution, compared with the prior art, the present invention discloses a system for identifying MASH and the degree of MASH inflammation, which can safely, quickly and accurately identify MASH and the degree of MASH inflammation. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0045] Figure 1 This invention provides a schematic diagram of a system structure for identifying MASH and the degree of MASH inflammation. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] like Figure 1 As shown, this embodiment of the invention discloses a system for identifying MASH and the degree of MASH inflammation, including a fat content distribution matrix acquisition module, a liver elasticity distribution matrix acquisition module, a severe fatty lesion area acquisition module, a liver fibrosis area acquisition module, a severe fatty lesion surrounding area acquisition module, a liver fibrosis surrounding area acquisition module, a weighted IQ envelope signal acquisition module, and a MASH and MASH inflammation degree identification module;

[0048] The fat content distribution matrix acquisition module is used to extract the fat content distribution matrix from a single-frame IQ envelope signal; wherein, the single-frame IQ envelope signal is the IQ envelope signal corresponding to a single-frame liver ultrasound signal;

[0049] In one embodiment, the fat content distribution matrix acquisition module includes a Shannon entropy matrix acquisition submodule and an alignment submodule:

[0050] The Shannon entropy matrix acquisition submodule is used to traverse the single-frame IQ envelope signal using a sliding window and calculate the Shannon entropy value of each sliding window to obtain the Shannon entropy matrix of the single-frame IQ envelope signal.

[0051] In an embodiment, the Shannon entropy value of each sliding window is obtained based on the following formula:

[0052]

[0053] wherein w(x i ) represents the probability of occurrence of the i-th gray level in the gray level histogram of the IQ envelope signal in the sliding window; n represents the total number of gray levels into which the amplitude range of the IQ envelope signal in the sliding window is divided; H c represents the Shannon entropy value of the sliding window.

[0054] In an embodiment, the sliding window is a square, and the side length of the square is one pulse length of the ultrasonic transducer.

[0055] It can be understood that, in the process of traversing the sliding window from left to right and from top to bottom, each window obtains a Shannon entropy value, and after the traversal of the sliding window is completed, a Shannon entropy matrix is obtained; the step length of the traversal can be set to half of the size of the sliding window, so that the generated Shannon entropy matrix has sufficient resolution while the calculation amount is not excessively large.

[0056] The aligning submodule is configured to sample the Shannon entropy matrix to the same size as the single-frame IQ envelope signal to obtain the fat content distribution matrix.

[0057] It can be understood that: the sampling is to align the Shannon entropy matrix and the single-frame IQ envelope data.

[0058] The liver elasticity distribution matrix acquisition module is configured to extract a liver elasticity distribution matrix corresponding to the single-frame IQ envelope signal.

[0059] It can be understood that: because ARFI can obtain the hardness distribution of a specified region and qualitatively realize the detection of light, moderate and severe liver fibrosis, the Acoustic Radiation Force Impulse (ARFI) can be used to extract the liver elasticity distribution matrix corresponding to the single-frame IQ envelope signal.

[0060] The severe fat lesion area acquisition module is configured to perform preset threshold judgment on the fat content distribution matrix after clustering to obtain a severe fat lesion area.

[0061] In an embodiment, the severe fat lesion area acquisition module includes a first clustering submodule and a first threshold judgment submodule.

[0062] The first clustering submodule is configured to perform K-means clustering on the fat content distribution matrix to obtain a healthy liver area, a light-moderate fatty liver area and a severe fatty liver area.

[0063] The specific steps of K-means clustering are as follows:

[0064] (1) Set the cluster number K of clustering to 3;

[0065] It can be understood that in the process of fatty liver progression, the distribution of fat content is not uniform, and there is a part of liver tissue that is healthy liver tissue, and some areas have different degrees of fatty lesions. The cluster number set to 3 indicates that the liver is divided into healthy liver area, mild to moderate fatty liver area and severe fatty liver area.

[0066] (2) Randomly select an element in the fat content distribution matrix as the initial value of the cluster center value of each cluster;

[0067] (3) Calculate the distance (which can be the Euclidean distance) from each element in the fat content distribution matrix to each cluster center value, and then assign each element in the fat content distribution matrix to the cluster closest to it;

[0068] (4) Update the cluster center value of each cluster; wherein the updated cluster center value is the average of all elements included in the cluster before updating;

[0069] (5) Repeat steps (3), (4) until the difference between the cluster center values before and after updating is less than a preset threshold or a preset maximum iteration number Tmax (such as Tmax = 100 times), to obtain the healthy liver area, the mild to moderate fatty liver area and the severe fatty liver area.

[0070] The first threshold judgment submodule is configured to obtain the severe fatty lesion area based on the first preset threshold and the cluster center value of the healthy liver area, the cluster center value of the mild to moderate fatty liver area, and the cluster center value of the severe fatty liver area. If the cluster center value of the healthy liver area, the cluster center value of the mild to moderate fatty liver area, and the cluster center value of the severe fatty liver area are all less than the first preset threshold, the severe fatty lesion area is set to a 0 matrix. If the cluster center value of the healthy liver area, the cluster center value of the mild to moderate fatty liver area, and the cluster center value of the severe fatty liver area are not all less than the first preset threshold, the severe fatty lesion area is the area where all cluster center values are greater than or equal to the first preset threshold.

[0071] In an embodiment, the first preset threshold is 4.1;

[0072] In an embodiment, if the fat content distribution matrix is constructed by the shape parameter m of Nakagami distribution, the first preset threshold is 1;

[0073] It can be understood that: for any fat content distribution matrix, K-means clustering will forcibly cluster the matrix into 3 categories (i.e. healthy liver region, mild to moderate fatty liver region and severe fatty liver region), but when the cluster center value of a certain cluster is higher than the first preset threshold, it is considered that the region corresponding to the cluster belongs to the severe fatty lesion region, so threshold judgment needs to be performed on the three regions after clustering, so as to obtain a more accurate severe fatty lesion region.

[0074] The liver fibrosis region acquisition module is configured to perform preset threshold judgment on the liver elasticity distribution matrix after clustering, and obtain a liver fibrosis region.

[0075] In an embodiment, the liver fibrosis region acquisition module includes a second clustering submodule and a second threshold judgment submodule.

[0076] The second clustering submodule is configured to perform K-means clustering on the liver elasticity distribution matrix, and obtain a healthy liver stiffness region, a mild to moderate liver fibrosis region and a severe liver fibrosis region.

[0077] The specific steps of K-means clustering are as follows:

[0078] (1) Set the number of clusters K to 3;

[0079] It can be understood that: setting the number of clusters to 3 means that the liver is divided into a healthy liver stiffness region, a mild to moderate liver fibrosis region and a severe liver fibrosis region.

[0080] (2) Randomly select an element in the liver elasticity distribution matrix as the initial value of the cluster center value of each cluster;

[0081] (3) Calculate the distance (which can be the Euclidean distance) from each element in the liver elasticity distribution matrix to each cluster center value, and then assign each element in the liver elasticity distribution matrix to the cluster closest to it,

[0082] (4) Update the cluster center value of each cluster; wherein the updated cluster center value is the average of all elements included in the cluster before updating;

[0083] (5) Repeat steps (3) and (4) until the difference between the cluster center values before and after updating is less than a preset threshold or a preset maximum iteration number Tmax is reached, and obtain a healthy liver stiffness region, a mild to moderate liver fibrosis region and a severe liver fibrosis region.

[0084] The second threshold judgment submodule is configured to obtain the liver fibrosis region based on a second preset threshold and the cluster center value of the liver stiffness healthy region, the cluster center value of the mild-to-moderate liver fibrosis region, and the cluster center value of the severe liver fibrosis region; if the cluster center value of the liver stiffness healthy region, the cluster center value of the mild-to-moderate liver fibrosis region, and the cluster center value of the severe liver fibrosis region are all less than the second preset threshold, the liver fibrosis region is set as a 0 matrix; if the cluster center value of the liver stiffness healthy region, the cluster center value of the mild-to-moderate liver fibrosis region, and the cluster center value of the severe liver fibrosis region are not all less than the second preset threshold, the liver fibrosis region is a region with all cluster center values greater than or equal to the second preset threshold.

[0085] In an embodiment, the second preset threshold is 7.3.

[0086] It can be understood that, for any liver elasticity distribution matrix, K_means clustering will forcibly cluster the matrix into three categories (i.e., the liver stiffness healthy region, the mild-to-moderate liver fibrosis region, and the severe liver fibrosis region), but when the cluster center value of a certain cluster is higher than the second preset threshold, it is considered that the region corresponding to the cluster belongs to the liver fibrosis region, so threshold judgment needs to be performed on the three regions after clustering, so as to obtain a more accurate liver fibrosis region.

[0087] The severe fat lesion surrounding region acquisition module is configured to perform inflation processing on the severe fat lesion region and then subtract the severe fat lesion region, to obtain a severe fat lesion surrounding region.

[0088] It can be understood that the inflation kernel can be set as needed, for example, it can be set to 5x5, and the inflation times are set to 3 times.

[0089] The liver fibrosis surrounding region acquisition module is configured to perform inflation processing on the liver fibrosis region and then subtract the liver fibrosis region, to obtain a liver fibrosis surrounding region.

[0090] It can be understood that the inflation kernel can be set as needed, for example, it can be set to 5x5, and the inflation times are set to 3 times.

[0091] The weighted IQ envelope signal acquisition module is configured to process multiple frames of IQ envelope signals based on the severe fat lesion surrounding region and the liver fibrosis surrounding region, to obtain a weighted IQ envelope signal.

[0092] In an embodiment, the weighted IQ envelope signal acquisition module includes a 3D MASK region acquisition submodule, a MASK region merging submodule, and a weighted point multiplication submodule.

[0093] The 3D MASK region acquisition submodule is configured to perform binaryzation processing on the 3D severe fatty lesion surrounding region and the 3D liver fibrosis surrounding region, and obtain two 3D MASK regions (pixels are 0 or 1); wherein, a plurality of frames of the severe fatty lesion surrounding region constitute the 3D severe fatty lesion surrounding region; and a plurality of frames of the liver fibrosis surrounding region constitute the 3D liver fibrosis surrounding region.

[0094] The MASK region merging submodule is configured to, after performing the union of the severe fatty lesion surrounding region and the liver fibrosis surrounding region on each frame of MASK, merge the two 3D MASK regions into one, and obtain a merged MASK region; wherein, if the number of pixels with a pixel value of 1 in the merged MASK region is greater than a third preset threshold, the merged MASK region is input to the weighted point multiplication submodule; and if the number of pixels with a pixel value of 1 in the merged MASK region is less than the third preset threshold, a plurality of frames of the IQ envelope signal are directly input to the convolutional neural network and the full connection layer in sequence, to obtain the MASH and the MASH inflammation degree recognition result.

[0095] The weighted point multiplication submodule is configured to obtain a weighted IQ envelope signal based on the merged MASK region, a preset weight coefficient and the plurality of frames of the IQ envelope signal; wherein, the calculation formula of the weighted IQ envelope signal is: wherein, the weighted IQ envelope signal is represented by M IQ the plurality of frames of the IQ envelope signal is represented by M ROI the merged MASK region is represented by M

[0096] In an embodiment, the system further comprises a 3D severe fatty lesion surrounding region acquisition submodule and a 3D liver fibrosis surrounding region acquisition submodule.

[0097] The 3D severe fatty lesion surrounding region acquisition submodule is configured to process a plurality of frames of the IQ envelope signal through the fat content distribution matrix acquisition submodule, the severe fatty lesion region acquisition submodule and the severe fatty lesion surrounding region acquisition submodule in sequence, to obtain a plurality of frames of the severe fatty lesion surrounding region.

[0098] The 3D liver fibrosis surrounding region acquisition submodule is configured to extract a plurality of frames of liver elasticity distribution matrix corresponding to the plurality of frames of the IQ envelope signal by using the liver elasticity distribution matrix acquisition submodule, and process the plurality of frames of the liver elasticity distribution matrix through the liver fibrosis region acquisition submodule and the liver fibrosis surrounding region acquisition submodule in sequence, to obtain a plurality of frames of the liver fibrosis surrounding region.

[0099] In an embodiment, the system further comprises a 3D severe fatty lesion surrounding region acquisition submodule and a 3D liver fibrosis surrounding region acquisition submodule.

[0100] The 3D severe fat lesion surrounding area acquisition submodule is configured to sequentially process the multiple frames of IQ envelope signals through the fat content distribution matrix acquisition module, the severe fat lesion area acquisition submodule, and the severe fat lesion surrounding area acquisition submodule, to obtain multiple frames of the severe fat lesion surrounding area.

[0101] The 3D liver fibrosis surrounding area acquisition submodule is configured to extract a selected liver elasticity distribution matrix corresponding to a selected frame of IQ envelope signals by using the liver elasticity distribution matrix acquisition submodule, and then expand the number of channels of the selected liver elasticity distribution matrix to the same number of frames as the multiple frames of IQ envelope signals, and sequentially process the selected liver elasticity distribution matrix through the liver fibrosis area acquisition submodule and the liver fibrosis surrounding area acquisition submodule, to obtain multiple frames of the liver fibrosis surrounding area (this method can improve the final classification speed). The selected frame of IQ envelope signals is a certain frame of IQ envelope signal in the multiple frames of IQ envelope signals.

[0102] The MASH and MASH inflammation degree recognition module is configured to perform channel splicing, feature extraction, and classification on the weighted IQ envelope signal and the multiple frames of IQ envelope signals, to obtain a MASH and MASH inflammation degree recognition result.

[0103] In an embodiment, the MASH and MASH inflammation degree recognition module includes a channel splicing layer, a convolutional neural network, and a fully connected layer.

[0104] The channel splicing layer is configured to perform channel splicing on the weighted IQ envelope signal and the multiple frames of IQ envelope signals, to obtain a spliced IQ envelope signal.

[0105] The convolutional neural network is configured to perform feature extraction on the spliced IQ envelope signal, to obtain a CNN feature.

[0106] The fully connected layer is configured to classify the CNN feature, to obtain the MASH and MASH inflammation degree recognition result. The MASH and MASH inflammation degree recognition result includes no inflammation, mild inflammation, and severe inflammation.

[0107] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts of each embodiment can be referred to each other.

[0108] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and that the appended claims are intended to cover all such modifications that do not depart from the true spirit and scope of the application. Therefore, the application is not limited to the embodiments shown but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A system for identifying MASH and the degree of MASH inflammation, characterized in that, It includes modules for obtaining the fat content distribution matrix, the liver elasticity distribution matrix, the area of ​​severe steatosis, the area of ​​liver fibrosis, the area surrounding severe steatosis, the area surrounding liver fibrosis, the weighted IQ envelope signal, and MASH and MASH inflammation degree recognition. The fat content distribution matrix acquisition module is used to extract the fat content distribution matrix from a single-frame IQ envelope signal; wherein, the single-frame IQ envelope signal is the IQ envelope signal corresponding to a single-frame liver ultrasound signal; The liver elasticity distribution matrix acquisition module is used to extract the liver elasticity distribution matrix corresponding to a single frame IQ envelope signal; The severe lipopathy region acquisition module is used to cluster the fat content distribution matrix and then perform a preset threshold judgment to obtain the severe lipopathy region. The liver fibrosis region acquisition module is used to cluster the liver elastic distribution matrix and then perform a preset threshold judgment to obtain the liver fibrosis region. The module for obtaining the area surrounding the severe lipolesion is used to expand the area of ​​the severe lipolesion and then subtract the area of ​​the severe lipolesion to obtain the area surrounding the severe lipolesion. The liver fibrosis surrounding area acquisition module is used to expand the liver fibrosis area and then subtract the liver fibrosis area to obtain the liver fibrosis surrounding area. The weighted IQ envelope signal acquisition module is used to process multiple frames of IQ envelope signals based on the area surrounding the severe fatty lesion and the area surrounding the liver fibrosis to obtain a weighted IQ envelope signal. The MASH and MASH inflammation degree recognition module is used to perform channel splicing, feature extraction and classification on the weighted IQ envelope signal and the multi-frame IQ envelope signal to obtain the MASH and MASH inflammation degree recognition results.

2. The system for identifying MASH and the degree of MASH inflammation according to claim 1, characterized in that, The fat content distribution matrix acquisition module includes a Shannon entropy matrix acquisition submodule and an alignment submodule: The Shannon entropy matrix acquisition submodule is used to traverse the single-frame IQ envelope signal using a sliding window and calculate the Shannon entropy value of each sliding window to obtain the Shannon entropy matrix of the single-frame IQ envelope signal. The alignment submodule is used to sample the Shannon entropy matrix to the same size as the single-frame IQ envelope signal to obtain the fat content distribution matrix.

3. The system for identifying MASH and the degree of MASH inflammation according to claim 2, characterized in that, The Shannon entropy value for each sliding window is obtained based on the following formula: In the formula, w(x) i ) represents the probability of the i-th gray level appearing in the gray-level histogram of the IQ envelope signal within the sliding window; n represents the total number of gray levels into which the amplitude range of the IQ envelope signal within the sliding window is divided; H c This represents the Shannon entropy value of the sliding window.

4. The system for identifying MASH and the degree of MASH inflammation according to claim 3, characterized in that, The sliding window is square, and the side length of the square is one pulse length of the ultrasonic transducer.

5. The system for identifying MASH and the degree of MASH inflammation according to claim 1, characterized in that, The severe fat lesion area acquisition module includes a first clustering submodule and a first threshold judgment submodule; The first clustering submodule is used to perform K-means clustering on the fat content distribution matrix to obtain healthy liver regions, mild to moderate fatty liver regions, and severe fatty liver regions; The first threshold determination submodule is used to obtain the severe fatty lesion region based on a first preset threshold and the cluster center values ​​of the healthy liver region, the mild to moderate fatty liver region, and the severe fatty liver region; wherein, if the cluster center values ​​of the healthy liver region, the mild to moderate fatty liver region, and the severe fatty liver region are all less than the first preset threshold, then the severe fatty lesion region is set to a 0 matrix; if the cluster center values ​​of the healthy liver region, the mild to moderate fatty liver region, and the severe fatty liver region are not all less than the first preset threshold, then the severe fatty lesion region is the region where all cluster center values ​​are greater than or equal to the first preset threshold.

6. The system for identifying MASH and the degree of MASH inflammation according to claim 1, characterized in that, The liver fibrosis region acquisition module includes a second clustering submodule and a second threshold judgment submodule; The second clustering submodule is used to perform K-means clustering on the liver elasticity distribution matrix to obtain healthy liver stiffness regions, mild to moderate liver fibrosis regions, and severe liver fibrosis regions. The second threshold determination submodule is used to obtain the liver fibrosis region based on a second preset threshold and the cluster center values ​​of the healthy liver stiffness region, the mild to moderate liver fibrosis region, and the severe liver fibrosis region; wherein, if the cluster center values ​​of the healthy liver stiffness region, the mild to moderate liver fibrosis region, and the severe liver fibrosis region are all less than the second preset threshold, then the liver fibrosis region is set to a 0 matrix; If the cluster center values ​​of the healthy liver stiffness region, the mild to moderate liver fibrosis region, and the severe liver fibrosis region are not all less than the second preset threshold, then the liver fibrosis region is the region where all cluster center values ​​are greater than or equal to the second preset threshold.

7. The system for identifying MASH and the degree of MASH inflammation according to claim 1, characterized in that, The weighted IQ envelope signal acquisition module includes a 3D MASK region acquisition submodule, a MASK region merging submodule, and a weighted dot product submodule; The 3D MASK region acquisition submodule is used to perform binarization processing on the 3D region surrounding severe fatty lesions and the 3D region surrounding liver fibrosis to obtain two 3D MASK regions; wherein, multiple frames of the region surrounding severe fatty lesions constitute the 3D region surrounding severe fatty lesions; and multiple frames of the region surrounding liver fibrosis constitute the 3D region surrounding liver fibrosis. The MASK region merging submodule is used to calculate the union of the regions surrounding severe fatty lesions and liver fibrosis in each MASK frame, and then merge the two 3D MASK regions into one, obtaining a merged MASK region. If the number of pixels with a value of 1 in the merged MASK region is greater than a third preset threshold, the merged MASK region is input to the weighted dot multiplication submodule; if it is less than the third preset threshold, the IQ envelope signal regions of multiple frames are directly input into the convolutional neural network and the fully connected layer in sequence to obtain the MASH and MASH inflammation degree recognition results. The weighted dot multiplier module is used to obtain a weighted IQ envelope signal based on the merged MASK region, preset weight coefficients, and the multi-frame IQ envelope signal; wherein, the calculation formula for the weighted IQ envelope signal is: M represents the weighted IQ envelope signal. IQ The multi-frame IQ envelope signal represents the signal, α represents the preset weighting coefficient, and M represents the multi-frame IQ envelope signal. ROI The '·' indicates the merged MASK region, and '·' indicates matrix dot product.

8. The system for identifying MASH and the degree of MASH inflammation according to claim 7, characterized in that, It also includes a 3D submodule for acquiring the area surrounding severe steatosis and a 3D submodule for acquiring the area surrounding liver fibrosis. The 3D severe lipopathy surrounding area acquisition submodule is used to process multiple frames of IQ envelope signals sequentially through the fat content distribution matrix acquisition module, the severe lipopathy area acquisition module, and the severe lipopathy surrounding area acquisition module to obtain multiple frames of the severe lipopathy surrounding area. The 3D liver fibrosis surrounding area acquisition submodule is used to extract the multi-frame liver elastic distribution matrix corresponding to the multi-frame IQ envelope signal sequentially using the liver elastic distribution matrix acquisition module, and process the multi-frame liver elastic distribution matrix sequentially through the liver fibrosis area acquisition module and the liver fibrosis surrounding area acquisition module to obtain the multi-frame liver fibrosis surrounding area.

9. A system for identifying MASH and the degree of MASH inflammation according to claim 7, characterized in that, It also includes a 3D submodule for acquiring the area surrounding severe steatosis and a 3D submodule for acquiring the area surrounding liver fibrosis. The 3D severe lipopathy surrounding area acquisition submodule is used to process multiple frames of IQ envelope signals sequentially through the fat content distribution matrix acquisition module, the severe lipopathy area acquisition module, and the severe lipopathy surrounding area acquisition module to obtain multiple frames of the severe lipopathy surrounding area. The 3D liver fibrosis surrounding region acquisition submodule is used to extract the selected liver elastic distribution matrix corresponding to the selected frame IQ envelope signal using the liver elastic distribution matrix acquisition module. Then, the number of channels of the selected liver elastic distribution matrix is ​​expanded to the same number of frames as the multiple frames of IQ envelope signals. After that, it is processed by the liver fibrosis region acquisition module and the liver fibrosis surrounding region acquisition module respectively to obtain multiple frames of the liver fibrosis surrounding region. The selected frame IQ envelope signal is one frame of IQ envelope signal in the multiple frames of IQ envelope signals.

10. A system for identifying MASH and the degree of MASH inflammation according to claim 1, characterized in that, The MASH and MASH inflammation degree recognition module include a channel splicing layer, a convolutional neural network, and a fully connected layer; The channel splicing layer is used to perform channel splicing on the weighted IQ envelope signal and the multi-frame IQ envelope signal to obtain a spliced ​​IQ envelope signal. The convolutional neural network is used to extract features from the spliced ​​IQ envelope signal to obtain CNN features; The fully connected layer is used to classify the CNN features to obtain the MASH and MASH inflammation degree recognition results; wherein, the MASH and MASH inflammation degree recognition results include no inflammation, mild inflammation, and severe inflammation.

Images