Focus severity display method, device and equipment and readable storage medium

Abstract

The invention discloses a focus severity display method, device and equipment and a readable storage medium, and the method comprises the steps: obtaining a medical image, and determining a target focus in the medical image; for each frame of medical image in the medical image, determining metric values corresponding to at least two severity levels according to at least one severity level corresponding to the target focus in the medical image; at least two severity levels and corresponding metrics are displayed in the medical image. By determining and displaying the at least two severity levels and the measurement values of the severity levels corresponding to the target lesion in the medical image, the real information of the lesion can be prevented from being ignored, and the risk of misdiagnosis of a doctor is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to a method, device, equipment and readable storage medium for displaying the severity of a lesion. Background Art

[0002] With the development of AI imaging technology, image scanning has become a common auxiliary diagnosis and treatment method in modern medical diagnosis and treatment. Medical imaging can provide doctors with more and more intuitive internal information of the human body, thereby speeding up doctors' diagnosis of patients' conditions.

[0003] However, when AI scanning equipment provides doctors with a display of the severity of lesions, it usually compares the severity confidence value of the current lesion section with the severity screening threshold provided in the lesion grading standard, and then gives the severity level of the lesion according to the comparison result. However, this display method is relatively mechanical, and the real information of many lesions will be ignored, resulting in the risk of misdiagnosis by doctors. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and readable storage medium for displaying the severity of a lesion, which can prevent the true information of the lesion from being ignored and reduce the risk of misdiagnosis by doctors.

[0005] In a first aspect, an embodiment of the present application provides a method for displaying the severity of a lesion, the method comprising:

[0006] Acquire a medical image and determine a target lesion in the medical image;

[0007] For each frame of the medical image, determining at least two metric values ​​corresponding to the severity levels according to at least one severity level corresponding to the target lesion in the medical image;

[0008] At least two severity levels and corresponding metric values ​​are displayed in the medical image.

[0009] Optionally, determining the target lesion in the medical image includes:

[0010] Extracting characteristic information and physiological tissue types corresponding to the medical image;

[0011] According to the physiological tissue type, querying a preset physiological tissue lesion feature database to obtain lesion feature information corresponding to the type of the physiological tissue;

[0012] A target lesion is determined based on the lesion characteristic information and the characteristic information.

[0013] Optionally, determining the metric values ​​corresponding to at least two severity levels according to at least one severity level corresponding to the target lesion in the medical image includes:

[0014] Based on the target lesion, selecting a first target recognition model corresponding to the target lesion from a preset first recognition model set;

[0015] Analyzing the medical image by using the first target recognition model to determine a confidence level and a reference metric level corresponding to at least one severity level corresponding to the target lesion in the medical image;

[0016] Determining at least two severity levels based on the confidence level;

[0017] According to the reference metric level and a preset mapping relationship, metric values ​​corresponding to at least two of the severity levels are determined; the preset mapping relationship is a mapping relationship between confidence and metric value.

[0018] Optionally, determining the metric values ​​corresponding to at least two severity levels according to at least one severity level corresponding to the target lesion in the medical image includes:

[0019] Based on the target lesion, selecting a second target recognition model corresponding to the target lesion from a preset second recognition model set;

[0020] Analyzing the medical image by using the second target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and confidence levels of the severity levels;

[0021] A metric value is determined according to the confidence level and a preset conversion rule.

[0022] Optionally, analyzing the medical image by the second target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and confidence levels of the severity levels includes:

[0023] Analyzing the medical image by the second target recognition model to determine a prediction confidence set corresponding to the target lesion in the medical image; the prediction confidence set includes prediction confidences corresponding to each severity level of the target lesion;

[0024] Based on the prediction confidence set, at least two severity levels corresponding to the target lesion in the medical image and confidences of the severity levels are determined.

[0025] Optionally, displaying at least two severity levels and corresponding metric values ​​in the medical image includes:

[0026] determining a target display area in the medical image;

[0027] Each of the severity levels and a metric value corresponding to the severity level are displayed in the target display area.

[0028] Optionally, determining a target display area in the medical image includes:

[0029] Determine, according to a mapping relationship between the severity level corresponding to the target lesion and the lesion region feature, a reference lesion region feature corresponding to each severity level;

[0030] Extracting lesion sub-region features corresponding to each sub-region in the target lesion region of the medical image;

[0031] According to the reference lesion features and the lesion sub-region features, a target display area corresponding to each severity level is determined in the medical image.

[0032] Optionally, determining, in the medical image, a target display area corresponding to each severity level according to the reference lesion feature and the lesion sub-region feature, comprises:

[0033] For each severity level, respectively calculating the similarity between the reference lesion feature corresponding to the severity level and each lesion sub-region feature;

[0034] Determine the lesion sub-region corresponding to the lesion sub-region feature with the greatest similarity as the target lesion sub-region;

[0035] According to the target lesion sub-region, a target display region corresponding to the severity level is determined in the medical image.

[0036] In a second aspect, an embodiment of the present application provides a device for displaying the severity of a lesion.

[0037] A first determination unit is used to acquire a medical image and determine a target lesion in the medical image;

[0038] A second determining unit is used to determine, for each frame of the medical image in the medical image, metric values ​​corresponding to at least two severity levels according to at least one severity level corresponding to the target lesion in the medical image;

[0039] A display unit is used to display at least two severity levels and corresponding measurement values ​​in the medical image.

[0040] In a third aspect, an embodiment of the present application also provides a lesion severity display device, comprising a memory storing a computer program; a processor loads the computer program from the memory to execute the steps of any lesion severity display method provided in the embodiment of the present application.

[0041] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program is suitable for loading by a processor to execute the steps of any lesion severity display method provided in the embodiment of the present application.

[0042] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the lesion severity display methods provided in the embodiments of the present application.

[0043] By adopting the scheme of the embodiment of the application, a medical image is acquired, and a target lesion in the medical image is determined; for each frame of the medical image, at least two measurement values ​​corresponding to the severity levels are determined according to at least one severity level corresponding to the target lesion in the medical image; and at least two severity levels and corresponding measurement values ​​are displayed in the medical image. By determining and displaying at least two severity levels corresponding to the target lesion in the medical image and the measurement values ​​of the severity levels, the real information of the lesion can be prevented from being ignored, and the risk of misdiagnosis by doctors can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 This is a schematic flow chart of a first embodiment of a method for displaying lesion severity provided by the present application;

[0046] Figure 2 It is a flowchart of a second embodiment of the method for displaying the severity of lesions provided by the present application;

[0047] Figure 3 is a schematic flow chart of a third embodiment of the method for displaying the severity of lesions provided by the present application;

[0048] Figure 4 4 is a flowchart of a fourth embodiment of a method for displaying lesion severity provided by the present application;

[0049] Figure 5It is a schematic diagram showing the severity of lesions provided by the present application;

[0050] Figure 6 This is a schematic diagram of dynamic changes in the severity of a lesion provided by the present application;

[0051] Figure 7 is another schematic diagram showing the severity of lesions provided in the present application;

[0052] Figure 8 is a schematic structural diagram of a lesion severity display device provided in an embodiment of the present application;

[0053] Fig. 9 It is a structural schematic diagram of a lesion severity display device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application. At the same time, in the description of the embodiments of the present application, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0055] Embodiments of the present application provide a method, device, equipment and readable storage medium for displaying the severity of a lesion.

[0056] Specifically, this embodiment will be described from the perspective of a lesion severity display device, which can be specifically integrated into a lesion severity display apparatus, that is, the lesion severity display method of the embodiment of the present application can be executed by a lesion severity display device.

[0057] The lesion severity display method provided in the embodiment of the present application can be applied to a lesion severity display device, which can be a smart terminal, a PC terminal, a mobile terminal, or other device.

[0058] The following is a detailed description in conjunction with the accompanying drawings. In this embodiment, the execution subject is taken as an example of a lesion severity display device. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments. Although the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that shown in the accompanying drawings.

[0059] Please refer to Figure 1 , a first embodiment of the method for displaying the severity of a lesion is proposed, and the first embodiment comprises the following steps:

[0060] Step 101, obtaining a medical image and determining a target lesion in the medical image;

[0061] Step 102, for each frame of the medical image, determining at least two metric values ​​corresponding to severity levels according to at least one severity level corresponding to the target lesion in the medical image;

[0062] Step 103: display at least two severity levels and corresponding metric values ​​in the medical image.

[0063] In this embodiment, when performing a medical imaging examination on a patient, the lesion severity display device obtains a medical image of the patient's target physiological tissue, and determines a target lesion existing in the target physiological tissue based on the medical image of the target physiological tissue; the lesion severity display device displays each frame of the medical image to the doctor based on the doctor's continuous adjustment of different positions, angles, and strengths; for each frame of the medical image, the lesion severity display device determines at least two severity levels corresponding to the target lesion in the medical image and measurement values ​​corresponding to the severity levels; further, when displaying the medical image to the doctor, the lesion severity display device displays at least two severity levels and measurement values ​​corresponding to the severity levels in the medical image.

[0064] It is understandable that the physiological tissue can be the heart, liver, kidney, etc., and the medical imaging examination can be X-ray, ultrasound, etc. These medical imaging examinations all require the doctor to manually and continuously control the scanner at different positions, angles and forces to examine the patient's target physiological tissue to identify the target lesions in the target physiological tissue. At the same time, the medical image obtained by each scan will be displayed in real time during the scanning process. At least two severity levels corresponding to the target lesions and the confidence level of the severity level will be displayed on the medical image. Compared with the more mechanized display method of lesion severity levels in the prior art, this can avoid the real information of many lesions from being ignored and reduce the risk of misdiagnosis by doctors.

[0065] The lesion severity display device of this embodiment acquires a medical image and determines a target lesion in the medical image; for each frame of the medical image, determines at least two measurement values ​​corresponding to the severity levels according to at least one severity level corresponding to the target lesion in the medical image; and displays at least two severity levels and measurement values ​​corresponding to the severity levels in the medical image. By determining and displaying at least two severity levels corresponding to the target lesion in the medical image and measurement values ​​corresponding to the severity levels, it is possible to avoid ignoring the real information of the lesion and reduce the risk of misdiagnosis by doctors.

[0066] Specifically, each step is described in detail below:

[0067] Step 101, obtaining a medical image and determining a target lesion in the medical image;

[0068] In this step, the lesion severity display device displays a medical image of the target physiological tissue of the patient, and determines the target lesion existing in the target physiological tissue based on the medical image of the target physiological tissue. Optionally, the lesion severity display device extracts the characteristic information of the target physiological tissue in the medical image, obtains the lesion characteristic information corresponding to each lesion of the target physiological tissue in a preset physiological tissue lesion database, compares the characteristic information with the lesion characteristic information, and then determines the target lesion of the target physiological tissue. Optionally, the lesion severity display device extracts the characteristic information of the target physiological tissue in the medical image, inputs the characteristic information into a pre-created recognition model, and recognizes the lesion of the target physiological tissue based on the characteristic information through the recognition model, thereby determining the target lesion of the target physiological tissue; wherein the recognition model is obtained by training with training samples of multiple lesions of multiple different physiological tissues in advance.

[0069] Specifically, step 101 includes:

[0070] Step 1011, extracting characteristic information and physiological tissue types corresponding to the medical image;

[0071] In this step, after obtaining the medical image, the lesion severity display device first preprocesses the medical image, and the preprocessing includes image standardization, noise reduction, edge detection and other processing to obtain the preprocessed medical image; the lesion severity display device extracts features of the preprocessed medical image to extract the morphological features, texture features, edge features and type features of the target physiological tissue; wherein the morphological features include: shape: the geometric shape of the tissue or organ, such as circle, ellipse, star, etc., size: the size of the tissue or organ, usually including the measurement of length, width and height, volume: the overall volume of the tissue or organ, position: the spatial position of the tissue or organ in the image, boundary: the edge contour of the tissue or organ, whether it is regular or irregular; texture features include: grayscale coplanarity Grayscale matrix (GLCM): describes the spatial relationship of gray values ​​in an image, and is often used to extract texture features such as contrast, correlation, uniformity, etc. Local binary pattern (LBP): used to capture local features of texture, wavelet transform: analyzes multi-scale texture features of an image, Fourier transform: analyzes texture features in the frequency domain, edge density: the density of texture details in an image; edge features include: edge detection: using edge detection algorithms (such as Canny, Sobel, etc.) to identify the edges of tissues or organs, edge sharpness: the clarity and sharpness of an edge, edge roughness: the smoothness or roughness of an edge, edge shape: the geometric shape of an edge, such as straight, curved, wavy, etc.; physiological tissue type is used to indicate that the physiological tissue belongs to the heart, liver, or kidney, etc.

[0072] Step 1012, according to the physiological tissue type, query a preset physiological tissue lesion feature database to obtain lesion feature information corresponding to the physiological tissue type;

[0073] In this step, the lesion severity display device queries a preset physiological tissue lesion feature database according to the physiological tissue type, and obtains lesion feature information corresponding to the type of physiological tissue; wherein the preset physiological tissue lesion feature database includes lesion features of different lesions corresponding to multiple physiological tissues. When the physiological tissue type is heart, the lesion feature information of different lesions corresponding to the heart is extracted from the physiological tissue lesion feature database; when the physiological tissue type is kidney, the lesion feature information of different lesions corresponding to the kidney is extracted from the physiological tissue lesion feature database.

[0074] Step 1013, determining a target lesion based on the lesion characteristic information and the characteristic information.

[0075] In this step, after determining the lesion characteristic information of each lesion corresponding to the type of physiological tissue, the lesion severity display device compares the characteristic information corresponding to the medical image with the lesion characteristic information of each lesion, calculates the similarity between the characteristic information and the lesion characteristic information of each lesion, and determines the lesion with the greatest similarity as the target lesion in the medical image.

[0076] Step 102, for each frame of the medical image, determining at least two metric values ​​corresponding to severity levels according to at least one severity level corresponding to the target lesion in the medical image;

[0077] In this step, after determining the target lesion in the medical image, the lesion severity display device displays each frame of the medical image to the doctor based on the doctor's continuous adjustments of different positions, angles, and strengths; for each frame of the medical image, the lesion severity display device determines measurement values ​​corresponding to at least two severity levels based on at least one severity level corresponding to the target lesion in the medical image.

[0078] Optionally, the lesion severity display device inputs each frame of medical image into a preset recognition model, analyzes the medical image through the recognition model, determines the confidence and reference measurement level corresponding to at least one severity level corresponding to the target lesion in the medical image, determines at least two severity levels based on the confidence, and determines measurement values ​​corresponding to at least two severity levels based on the reference measurement level and a preset mapping relationship, wherein the preset mapping relationship is a mapping relationship between confidence and measurement value.

[0079] Optionally, the lesion severity display device inputs each frame of medical image into a preset recognition model, and predicts at least two severity levels corresponding to the target lesion in the medical image and the measurement values ​​corresponding to the severity levels through the recognition model. The severity level is used to indicate the severity of the target lesion predicted based on the current medical image; the measurement value of the severity level is used to indicate the probability that the target lesion predicted based on the current medical image reaches a certain severity level.

[0080] Step 103: display at least two of the severity levels and metric values ​​corresponding to the severity levels in the medical image.

[0081] In this step, after the lesion severity display device determines at least two severity levels corresponding to the target lesion in the medical image and the metric values ​​corresponding to the severity levels, it displays the at least two severity levels and the metric values ​​corresponding to the severity levels in the medical image while showing the medical image to the doctor. Optionally, the lesion severity display device displays at least two severity levels and the metric values ​​corresponding to the severity levels in a preset display area in the medical image; optionally, the lesion severity display device determines a lesion sub-area that best meets the severity level in the target lesion in the medical image, and then determines a target display area in the medical image based on the lesion sub-area, and then displays at least two severity levels and the metric values ​​corresponding to the severity levels in the target display area.

[0082] The lesion severity display device of this embodiment acquires a medical image and determines a target lesion in the medical image; for each frame of the medical image, determines at least two measurement values ​​corresponding to the severity levels according to at least one severity level corresponding to the target lesion in the medical image; and displays at least two severity levels and measurement values ​​corresponding to the severity levels in the medical image. By determining and displaying at least two severity levels corresponding to the target lesion in the medical image and measurement values ​​corresponding to the severity levels, it is possible to avoid ignoring the real information of the lesion and reduce the risk of misdiagnosis by doctors.

[0083] Further, refer to Figure 2 A second embodiment of the lesion severity display method is proposed. The difference between the second embodiment and the first embodiment is that at least two metric values ​​corresponding to the severity levels are determined according to at least one severity level corresponding to the target lesion in the medical image, including:

[0084] Step 1021, based on the target lesion, selecting a first target recognition model corresponding to the target lesion from a preset first recognition model set;

[0085] In this step, the lesion severity display device selects a first target recognition model corresponding to the target lesion from a preset first recognition model set based on the target lesion. Specifically, the lesion severity display device pre-stores a plurality of first recognition models corresponding to lesions, and each first recognition model is stored in association with the corresponding lesion information. After determining the target lesion, the lesion severity display device compares the target lesion with the lesion information stored in association with each first recognition model, and determines the first recognition model corresponding to the lesion information identical to the target lesion as the first target recognition model corresponding to the target lesion. Among them, each first recognition model is trained in advance using the lesion grading standard of the corresponding lesion, and can identify the severity level of the target lesion displayed in each frame of the medical image and the confidence level of the severity level.

[0086] Step 1022, analyzing the medical image by using the first target recognition model to determine a confidence level and a reference metric level corresponding to at least one severity level corresponding to the target lesion in the medical image;

[0087] In this step, after determining the first target recognition model corresponding to the target lesion, the lesion severity display device inputs the medical image into the first target recognition model, analyzes the lesion through the first target recognition model, and determines at least one severity level corresponding to the target lesion in the medical image as well as the confidence level and reference measurement level of the severity level.

[0088] Step 1023, determining at least two severity levels according to the confidence level;

[0089] In this step, after determining at least one severity level and the confidence of the severity level, the lesion severity display device determines at least two severity levels according to the confidence of the severity level. Exemplarily, the target lesions include four severity levels of A, B, C, and D. The lesion severity display device determines that the severity level is B, and the confidence of severity level B is 70%. At this time, the confidence 70% is less than 100%, and at least two severity levels can be determined: severity level A and severity level B. Exemplarily, the target lesions include four severity levels of A, B, C, and D. The lesion severity display device determines that the severity level is B, and the confidence of severity level B is 140%. At this time, the confidence 140% is less than 100%, and at least two severity levels can be determined: severity level B and severity level C.

[0090] Step 1024: Determine metric values ​​corresponding to at least two of the severity levels according to the reference metric level and a preset mapping relationship; the preset mapping relationship is a mapping relationship between confidence and metric value.

[0091] In this step, after determining at least two severity levels, the lesion severity display device determines the metric values ​​corresponding to at least two severity levels according to the reference metric level and the preset mapping relationship; the preset mapping relationship is the mapping relationship between the confidence and the metric value. Exemplarily, the target lesion includes four severity levels A, B, C, and D, and the metric value is calibrated in advance between each two severity levels, such as: 10%-100% metric values ​​are calibrated in advance between each two severity levels, and the reference metric level is divided into ten levels from 1 to 10; when it is determined that at least two severity levels are severity level A and severity level B, respectively, and the reference metric level of severity level B is 6, then according to the mapping relationship between the confidence and the metric value, it can be determined that the metric value of severity level B is 60%, and the metric value of severity level A is 40%.

[0092] The lesion severity display device of this embodiment selects a first target recognition model corresponding to the target lesion from a preset first recognition model set based on the target lesion; analyzes the medical image through the first target recognition model to determine the confidence and reference measurement level corresponding to at least one severity level corresponding to the target lesion in the medical image; determines at least two severity levels based on the confidence; determines measurement values ​​corresponding to at least two severity levels based on the reference measurement level and a preset mapping relationship; the preset mapping relationship is a mapping relationship between a reference measurement level and a measurement value. The accuracy of the severity level corresponding to the target lesion in the medical image and the confidence of the severity level can be improved, thereby improving the accuracy of the measurement value for determining the severity level, further avoiding the real information of the lesion from being ignored, and reducing the risk of misdiagnosis by doctors.

[0093] Further, refer to Figure 3 A third embodiment of the lesion severity display method is proposed. The difference between the third embodiment and the first to second embodiments is that at least two metric values ​​corresponding to the severity levels are determined according to at least one severity level corresponding to the target lesion in the medical image, including:

[0094] Step 1025, based on the target lesion, selecting a second target recognition model corresponding to the target lesion from a preset second recognition model set;

[0095] In this step, the lesion severity display device selects a second target recognition model corresponding to the target lesion from a preset second recognition model set based on the target lesion. Specifically, the lesion severity display device pre-stores a plurality of recognition models corresponding to lesions, and each second recognition model is stored in association with the corresponding lesion information. After determining the target lesion, the lesion severity display device compares the target lesion with the lesion information stored in association with each second recognition model, and determines the second recognition model corresponding to the lesion information identical to the target lesion as the second target recognition model corresponding to the target lesion. Among them, each second recognition model is trained in advance using the lesion grading standard of the corresponding lesion, and can identify the severity level of the target lesion displayed in each frame of the medical image and the confidence level of the severity level.

[0096] Step 1026, analyzing the medical image by using the second target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and confidence levels of the severity levels;

[0097] In this step, after determining the second target recognition model corresponding to the target lesion, the lesion severity display device inputs the medical image into the second target recognition model, analyzes the lesion through the second target recognition model, and determines at least two severity levels corresponding to the target lesion in the medical image and the confidence levels of the severity levels.

[0098] Specifically, step 1026 includes:

[0099] Step 10261, analyzing the medical image by using the second target recognition model to determine a prediction confidence set corresponding to the target lesion in the medical image; the prediction confidence set includes prediction confidences corresponding to each severity level of the target lesion;

[0100] In this step, the lesion severity display device analyzes the medical image through the second target recognition model to determine the prediction confidence set corresponding to the target lesion in the medical image; the prediction confidence set includes the prediction confidence corresponding to each severity level of the target lesion. Exemplarily, the target lesions include four severity levels A, B, C, and D. The target recognition model analyzes the medical image to determine the prediction confidence of the target lesion being severity level A, the prediction confidence of the target lesion being severity level B, the prediction confidence of the target lesion being severity level C, and the prediction confidence of the target lesion being severity level D.

[0101] Step 10262: Based on the prediction confidence set, determine at least two severity levels corresponding to the target lesion in the medical image and the confidence levels of the severity levels.

[0102] In this step, after determining the prediction confidence set corresponding to the target lesion in the medical image, the lesion severity display device determines at least two severity levels corresponding to the target lesion in the medical image and the confidence of the severity level based on the prediction confidence set. Optionally, the lesion severity display device uses all prediction confidences in the prediction confidence set as the confidence of the severity level, and determines the severity level corresponding to all prediction confidences as the severity level corresponding to the target lesion; optionally, the lesion severity display device compares each prediction confidence in the prediction confidence set with a preset confidence threshold, selects the prediction confidence greater than the preset confidence threshold as the confidence of the severity level, and selects the severity level corresponding to the prediction confidence greater than the preset confidence threshold as the severity level corresponding to the target lesion.

[0103] Step 1027: Determine a metric value according to the confidence level and a preset conversion rule.

[0104] In this step, after determining the confidence corresponding to each severity level corresponding to the target lesion in the medical image, the lesion severity display device combines the corresponding confidence with a preset conversion rule for each severity level to determine the measurement value corresponding to each severity level.

[0105] Exemplarily, for a certain frame of medical image, the lesion severity display device determines two severity levels A and B corresponding to the target lesion, the confidence level corresponding to severity level A is 60%, and the confidence level corresponding to severity level B is 30%. The lesion severity display device calculates the metric value of severity level A = 60% / (30%+60%) = 66.7%, and the lesion severity display device calculates the metric value of severity level B = 30% / (30%+60%) = 33.3%.

[0106] The lesion severity display device of this embodiment selects a target recognition model corresponding to the target lesion from a preset recognition model set based on the target lesion; analyzes the medical image through the target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and the confidence of the severity levels. The accuracy of the severity level corresponding to the target lesion in the medical image and the confidence of the severity level can be improved, thereby improving the accuracy of the measurement value for determining the severity level, further avoiding the real information of the lesion from being ignored, and reducing the risk of misdiagnosis by doctors.

[0107] Further, refer to Figure 4A fourth embodiment of the method for displaying the severity of a lesion is proposed. The difference between the fourth embodiment and the first embodiment and the third embodiment is that at least two severity levels and corresponding measurement values ​​are displayed in the medical image, including:

[0108] Step 1031, determining a target display area in the medical image;

[0109] In this step, the lesion severity display device determines a target display area in the medical image. Optionally, the lesion severity display device determines a preset display area in the medical image as the target display area, and the preset display area is set in advance. Optionally, the lesion severity display device determines a lesion sub-area corresponding to the severity level in the target lesion according to each severity level, and then determines the target display area around the lesion sub-area.

[0110] Step 1032: Display each severity level and the metric value corresponding to the severity level in the target display area.

[0111] In this step, the lesion severity display device displays each severity level and the measurement value corresponding to the severity level in the target display area. Optionally, when the target display area is a preset display area, the lesion severity display device displays each severity level in the target display area, and displays the corresponding measurement value in the display area of ​​each severity level. Optionally, when the target display area is a target display area determined around a lesion sub-area, the lesion severity display device displays the severity level and the corresponding measurement value corresponding to the lesion sub-area in the target display area, and associates the lesion sub-area with the target display area.

[0112] For example, for a certain frame of medical image, the lesion severity display device determines two severity levels A and B corresponding to the target lesion, the metric value corresponding to severity level A is 66.7%, and the metric value corresponding to severity level B is 33.3%; Figure 5 As shown, the lesion severity display device determines the preset display area in the upper right corner of the medical image as the target display area, and displays the measurement values ​​of severity level A and severity level B in the target display area; wherein the black area represents the measurement value corresponding to severity level A, and the white area represents the measurement value corresponding to severity level B; further, the measurement value corresponding to severity level A can be displayed as 66.7% in the black area, and the measurement value corresponding to severity level A can be displayed as 33.3% in the white area, which is used to prompt the doctor that the probability of the target lesion in the current frame medical image reaching severity level A is 66.7%, and the probability of reaching severity level A is 33.3%.

[0113] Furthermore, if Figure 6 As shown, when the lesion severity display device displays the next frame of medical image, two severity levels A and B corresponding to the target lesion of the next frame of medical image are determined, and the metric value corresponding to the severity level A is 40%, and the metric value corresponding to the severity level B is 60%. Then, the metric values ​​of severity level A and severity level B are displayed in the target display area in the medical image by Figure 6 The left picture changes to Figure 6 As shown in the right picture in the figure, as each frame of the medical image is displayed, the prompt bar of the severity level of the target lesion changes accordingly.

[0114] Specifically, determining a target display area in the medical image according to each severity level includes:

[0115] Step 10311, determining a reference lesion region feature corresponding to each severity level according to a mapping relationship between the severity level corresponding to the target lesion and the lesion region feature;

[0116] In this step, the lesion severity display device determines the reference lesion region features corresponding to each severity level according to the mapping relationship between the severity level corresponding to the target lesion and the lesion region features. It is understandable that when the same lesion corresponds to different severity levels, the lesion region features displayed are different. The lesion severity display device stores the reference lesion region features displayed when the target lesion corresponds to different severity levels in advance. The lesion severity display device can find the corresponding reference lesion region features based on the determined severity level.

[0117] Step 10312, extracting lesion sub-region features corresponding to each sub-region in the target lesion region of the medical image;

[0118] In this step, the lesion severity display device segments the target lesion area in the medical image to obtain each lesion sub-region corresponding to the target lesion area, and then identifies each lesion sub-region to extract the lesion sub-region features corresponding to each lesion sub-region.

[0119] Step 10313: Determine a target display area corresponding to each severity level in the medical image based on the reference lesion features and the lesion sub-region features.

[0120] In this step, the lesion severity display device determines a target display area corresponding to each severity level in the medical image according to the reference lesion features and the lesion sub-region features.

[0121] For example, Figure 7As shown, for a certain frame of medical image, the lesion severity display device determines two severity levels A and B corresponding to the target lesion, the measurement value corresponding to severity level A is 66.7%, and the measurement value corresponding to severity level B is 33.3%, wherein severity level A is determined based on lesion sub-region 1 in the target lesion, and severity level B is determined based on lesion sub-region 2 in the target lesion; at this time, the lesion severity display device displays severity level A and measurement value 66.7% in the target display area around lesion sub-region 1, and associates lesion sub-region 1 with the target display area; the lesion severity display device displays severity level B and measurement value 33.3% in the target display area around lesion sub-region 2, and associates lesion sub-region 2 with the target display area.

[0122] It can be understood that by displaying the severity level around the lesion sub-area in the corresponding target lesion, at least two severity levels corresponding to the target lesion and the measurement values ​​of the severity levels can be displayed in the same frame of medical image, and the lesion sub-area associated with the severity level in the target lesion can also be determined, which can further provide the doctor with more real information about the target lesion, further avoid the real information of the lesion from being ignored, and reduce the risk of misdiagnosis by the doctor.

[0123] Specifically, determining the target display area corresponding to each severity level in the medical image according to the reference lesion feature and the lesion sub-region feature includes:

[0124] Step 103131, for each severity level, respectively calculating the similarity between the reference lesion feature corresponding to the severity level and each lesion sub-region feature;

[0125] Step 103132, determining the lesion sub-region corresponding to the lesion sub-region feature with the greatest similarity as the target lesion sub-region;

[0126] Step 103133: Determine a target display area corresponding to the severity level in the medical image based on the target lesion sub-area.

[0127] In steps 103131 to 103133, the lesion severity display device determines, for each severity level, the similarity between the reference lesion feature corresponding to the severity level and the feature of each lesion sub-region, and determines the lesion sub-region corresponding to the lesion sub-region feature with the greatest similarity as the target lesion sub-region; based on the target lesion sub-region, determine the target display region corresponding to the severity level in the medical image. Exemplarily, the target lesion includes three lesion sub-regions, namely lesion sub-region 1, lesion sub-region 2 and lesion sub-region 3. For severity level A, the lesion severity display device calculates similarity between the reference lesion feature corresponding to severity level A and the lesion sub-region feature of lesion sub-region 1, the lesion sub-region feature of lesion sub-region 2 and the lesion sub-region feature of lesion sub-region 3, respectively, to obtain similarity 1, similarity 2 and similarity 3. The lesion severity display device then compares similarity 1, similarity 2 and similarity 3. If it is determined that similarity 3 is the largest, lesion sub-region 3 is determined to be the target lesion sub-region, and then a target display region corresponding to severity level A is determined around lesion sub-region 3. The target display region will not block the target lesion region.

[0128] The lesion severity display device in this embodiment determines a target display area in the medical image according to each severity level; and displays each severity level and a metric value of the severity level in the target display area. Each severity level can be displayed in the target display area, which can prevent the real information of the lesion from being ignored and reduce the risk of misdiagnosis by doctors.

[0129] This embodiment also provides a lesion severity display device, which can be integrated into a lesion severity display device such as a smart terminal, a PC terminal, a mobile terminal, etc. Figure 8 As shown, the lesion severity display device may include:

[0130] The first determining unit 1001 is used to obtain a medical image and determine a target lesion in the medical image;

[0131] A second determining unit 1002 is configured to determine, for each frame of the medical image in the medical image, at least two metric values ​​corresponding to severity levels according to at least one severity level corresponding to the target lesion in the medical image;

[0132] The display unit 1003 is used to display at least two severity levels and corresponding measurement values ​​in the medical image.

[0133] In an optional example, the first determining unit is further configured to:

[0134] Extracting characteristic information and physiological tissue types corresponding to the medical image;

[0135] According to the physiological tissue type, querying a preset physiological tissue lesion feature database to obtain lesion feature information corresponding to the type of the physiological tissue;

[0136] A target lesion is determined based on the lesion characteristic information and the characteristic information.

[0137] In an optional example, the second determining unit is further configured to:

[0138] Based on the target lesion, selecting a first target recognition model corresponding to the target lesion from a preset first recognition model set;

[0139] Analyzing the medical image by using the first target recognition model to determine a confidence level and a reference metric level corresponding to at least one severity level corresponding to the target lesion in the medical image;

[0140] Determining at least two severity levels based on the confidence level;

[0141] According to the reference metric level and a preset mapping relationship, metric values ​​corresponding to at least two of the severity levels are determined; the preset mapping relationship is a mapping relationship between the reference metric level and the metric value.

[0142] In an optional example, the second determining unit is further configured to:

[0143] Based on the target lesion, selecting a target recognition model corresponding to the target lesion from a preset recognition model set;

[0144] Analyzing the medical image by using the target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and confidence levels of the severity levels;

[0145] A metric value is determined according to the confidence level and a preset conversion rule.

[0146] In an optional example, the second determining unit is further configured to:

[0147] Analyzing the medical image by the target recognition model to determine a prediction confidence set corresponding to the target lesion in the medical image; the prediction confidence set includes prediction confidences corresponding to each severity level of the target lesion;

[0148] Based on the prediction confidence set, at least two severity levels corresponding to the target lesion in the medical image and confidences of the severity levels are determined.

[0149] In an optional example, the display unit is further configured to:

[0150] determining a target display area in the medical image;

[0151] Each of the severity levels and a metric value corresponding to the severity level are displayed in the target display area.

[0152] In an optional example, the second identification unit is further configured to:

[0153] Determine, according to a mapping relationship between the severity level corresponding to the target lesion and the lesion region feature, a reference lesion region feature corresponding to each severity level;

[0154] Extracting lesion sub-region features corresponding to each sub-region in the target lesion region of the medical image;

[0155] According to the reference lesion features and the lesion sub-region features, a target display area corresponding to each severity level is determined in the medical image.

[0156] In an optional example, the second identification unit is further configured to:

[0157] For each severity level, respectively calculating the similarity between the reference lesion feature corresponding to the severity level and each lesion sub-region feature;

[0158] Determine the lesion sub-region corresponding to the lesion sub-region feature with the greatest similarity as the target lesion sub-region;

[0159] According to the target lesion sub-region, a target display region corresponding to the severity level is determined in the medical image.

[0160] By adopting the solution of this embodiment, a medical image is acquired, and a target lesion in the medical image is determined; for each frame of the medical image, at least two measurement values ​​corresponding to the severity levels are determined according to at least one severity level corresponding to the target lesion in the medical image; and at least two severity levels and the corresponding measurement values ​​are displayed in the medical image. By determining and displaying at least two severity levels corresponding to the target lesion in the medical image and the measurement values ​​of the severity levels, the real information of the lesion can be prevented from being ignored, and the risk of misdiagnosis by doctors can be reduced.

[0161] Accordingly, the embodiment of the present application also provides a device for displaying the severity of a lesion, such as Fig. 9 As shown, Fig. 9A schematic diagram of the structure of a lesion severity display device provided in an embodiment of the present application. The lesion severity display device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will appreciate that the structure of the lesion severity display device shown in the figure does not constitute a limitation on the lesion severity display device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0162] The processor 1101 is the control center of the lesion severity display device 1100, and uses various interfaces and lines to connect various parts of the entire lesion severity display device 1100, and executes various functions and processes data of the lesion severity display device 1100 by running or loading software programs and / or units stored in the memory 1102, and calling data stored in the memory 1102, so as to monitor the lesion severity display device 1100 as a whole. The processor 1101 can be a processor CPU, a graphics processor GPU, a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.

[0163] In an embodiment of the present application, the processor 1101 in the lesion severity display device 1100 will load the instructions corresponding to the processes of one or more applications into the memory 1102 in accordance with the following steps, and the processor 1101 will run the applications stored in the memory 1102 to implement various functions. The specific implementation can be found in the previous embodiments and will not be repeated here.

[0164] Optional, such as Fig. 9 As shown, the lesion severity display device 1100 also includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106 and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106 and the power supply 1107 respectively. Those skilled in the art can understand that Fig. 9 The structure of the lesion severity display device shown in the figure does not constitute a limitation of the lesion severity display device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0165] The touch display screen 1103 can be used for displaying a graphical user interface and receiving an operation instruction generated by the user acting on the graphical user interface. The touch display screen 1103 can include a display panel and a touch panel. Wherein, the display panel can be used for displaying information input by the user or information provided to the user and various graphical user interfaces of the lesion severity display device, and these graphical user interfaces can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode) and the like. The touch panel can be used for collecting the user's touch operation on or near it (such as the user uses any suitable object or attachment such as a finger, a stylus, etc. on the touch panel or near the touch panel), and generates corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 1101, and can receive the command sent by the processor 1101 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event, and then the processor 1101 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 1103 can also be used as a part of the input unit 1106 to realize the input function.

[0166] The radio frequency circuit 1104 may be used to send and receive radio frequency signals, so as to establish wireless communication with a network device or other lesion severity display device through wireless communication, and to send and receive signals between the network device or other lesion severity display device.

[0167] The audio circuit 1105 can be used to provide an audio interface between the user and the lesion severity display device through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data, and then the audio data is output to the processor 1101 for processing, and then sent to another lesion severity display device through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earplug jack to provide communication between an external headset and the lesion severity display device.

[0168] The input unit 1106 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0169] The power supply 1107 is used to supply power to various components of the lesion severity display device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management device, so as to manage charging, discharging, and power consumption management through the power management device. The power supply 1107 can also include one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0170] although Fig. 9 Not shown in the figure, the lesion severity display device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be repeated here.

[0171] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0172] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0173] To this end, the embodiment of the present application provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer program can be loaded by a processor to execute any one of the lesion severity display methods provided in the embodiment of the present application. The computer program can execute the lesion severity display method, and the specific implementation can be referred to the previous embodiment, which will not be repeated here.

[0174] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0175] Since the computer program stored in the computer-readable storage medium can execute any of the lesion severity display methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the lesion severity display methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0176] According to one aspect of the present application, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. The processor of the lesion severity display device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the lesion severity display device performs the methods provided in various optional implementations in the above-mentioned embodiments.

[0177] In the above-mentioned lesion severity display device, computer-readable storage medium, lesion severity display equipment, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the lesion severity display device, computer-readable storage medium, computer program product, lesion severity display equipment and its corresponding units described above can refer to the description of the lesion severity display method in the above embodiment, and will not be repeated here.

[0178] The above is a detailed introduction to a lesion severity display method, device, equipment, readable storage medium and computer program product provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for displaying the severity of a lesion, characterized in that: The method for displaying the severity of lesions comprises: Acquire a medical image and determine a target lesion in the medical image; For each frame of the medical image, determining at least two metric values ​​corresponding to the severity levels according to at least one severity level corresponding to the target lesion in the medical image; At least two of the severity levels and corresponding metric values ​​are displayed in the medical image.

2. The method for displaying the severity of a lesion according to claim 1, characterized in that: Determining the target lesion in the medical image includes: Extracting characteristic information and physiological tissue types corresponding to the medical image; According to the physiological tissue type, querying a preset physiological tissue lesion feature database to obtain lesion feature information corresponding to the type of the physiological tissue; A target lesion is determined based on the lesion characteristic information and the characteristic information.

3. The method for displaying the severity of lesions according to claim 1, characterized in that: The determining of at least two metric values ​​corresponding to severity levels according to at least one severity level corresponding to the target lesion in the medical image includes: Based on the target lesion, selecting a first target recognition model corresponding to the target lesion from a preset first recognition model set; Analyzing the medical image by using the first target recognition model to determine a confidence level and a reference metric level corresponding to at least one severity level corresponding to the target lesion in the medical image; Determining at least two severity levels based on the confidence level; According to the reference metric level and a preset mapping relationship, metric values ​​corresponding to at least two of the severity levels are determined; the preset mapping relationship is a mapping relationship between the reference metric level and the metric value.

4. The method for displaying the severity of lesions according to claim 1, characterized in that: The determining of at least two metric values ​​corresponding to severity levels according to at least one severity level corresponding to the target lesion in the medical image includes: Based on the target lesion, selecting a second target recognition model corresponding to the target lesion from a preset second recognition model set; Analyzing the medical image by using the second target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and confidence levels of the severity levels; A metric value is determined according to the confidence level and a preset conversion rule.

5. The method for displaying the severity of lesions according to claim 4, characterized in that: The analyzing the medical image by the second target recognition model to determine at least two severity levels corresponding to the target lesion in the medical image and the confidence levels of the severity levels includes: Analyzing the medical image by the second target recognition model to determine a prediction confidence set corresponding to the target lesion in the medical image; the prediction confidence set includes prediction confidences corresponding to each severity level of the target lesion; Based on the prediction confidence set, at least two severity levels corresponding to the target lesion in the medical image and confidences of the severity levels are determined.

6. The method for displaying the severity of lesions according to claim 1, characterized in that: The displaying of at least two severity levels and corresponding metric values ​​in the medical image comprises: determining a target display area in the medical image; Each of the severity levels and a metric value corresponding to the severity level are displayed in the target display area.

7. The method for displaying the severity of lesions according to claim 6, characterized in that: The step of determining a target display area in the medical image comprises: Determine, according to a mapping relationship between the severity level corresponding to the target lesion and the lesion area feature, a reference lesion area feature corresponding to each severity level; Extracting lesion sub-region features corresponding to each sub-region in the target lesion region of the medical image; According to the reference lesion features and the lesion sub-region features, a target display area corresponding to each severity level is determined in the medical image.

8. The method for displaying the severity of lesions according to claim 7, characterized in that: The step of determining, in the medical image, a target display area corresponding to each severity level according to the reference lesion feature and the lesion sub-region feature, comprises: For each severity level, respectively calculating the similarity between the reference lesion feature corresponding to the severity level and each lesion sub-region feature; Determine the lesion sub-region corresponding to the lesion sub-region feature with the greatest similarity as the target lesion sub-region; According to the target lesion sub-region, a target display region corresponding to the severity level is determined in the medical image.

9. A device for displaying the severity of a lesion, characterized in that: The lesion severity display device comprises: A first determination unit is used to acquire a medical image and determine a target lesion in the medical image; A second determining unit is used to determine, for each frame of the medical image in the medical image, metric values ​​corresponding to at least two severity levels according to at least one severity level corresponding to the target lesion in the medical image; A display unit is used to display at least two severity levels and corresponding measurement values ​​in the medical image.

10. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a plurality of computer programs, and the processor loads the computer programs from the memory to execute the steps of the method for displaying the severity of a lesion as claimed in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of computer programs, and the computer programs are suitable for being loaded by a processor to execute the steps of the method for displaying the severity of a lesion according to any one of claims 1 to 8.

Images