Bleeding risk assessment method, device and equipment and computer readable storage medium
By scanning and extracting the patient's target body area and evaluating the bleeding characteristic information based on the bleeding characteristic information, the problem of low accuracy in the evaluation of bleeding risk caused by manual analysis in the prior art is solved, and more efficient and accurate bleeding risk is achieved Evaluate.
Patent Information
- Application Number
- CN202411223645.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-12-20
AI Technical Summary
In the prior art, medical staff manually analyze medical images for bleeding risk assessment is energy-consuming and can easily lead to operational errors, resulting in reduced accuracy of bleeding risk assessment.
By scanning the target body area of the patient, bleeding characteristic information is extracted, and bleeding risk assessment is performed based on these characteristic information, the bleeding risk level is determined, and the error of manual analysis is avoided.
It improves the accuracy of bleeding risk assessment, reduces errors in manual analysis by medical staff, and improves the efficiency and reliability of assessment.
Smart Images
Figure CN119170272A_ABST
Abstract
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 computer-readable storage medium for assessing bleeding risk. 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. At present, the bleeding risk assessment of tissues and organs through imaging examinations requires medical staff to manually analyze medical images, which takes a lot of effort and is prone to operational errors, resulting in reduced accuracy of bleeding risk assessment. Summary of the invention
[0003] The embodiments of the present application provide a bleeding risk assessment method, apparatus, device and computer-readable storage medium, which can improve the accuracy of bleeding risk assessment.
[0004] In a first aspect, an embodiment of the present application provides a method for assessing bleeding risk, the method comprising:
[0005] Performing an imaging scan on a target body area of a patient to obtain a target medical image;
[0006] Extracting bleeding characteristic information corresponding to the target medical image;
[0007] A bleeding risk assessment is performed on the patient based on the bleeding characteristic information to determine the bleeding risk level.
[0008] Optionally, extracting the bleeding characteristic information corresponding to the target medical image includes:
[0009] Inputting the target medical image into a pre-created bleeding area recognition model, and determining the bleeding area based on the target medical image by using the bleeding area recognition model;
[0010] A bleeding region image is segmented from the target medical image, and bleeding feature information corresponding to the bleeding region image is extracted.
[0011] Optionally, segmenting the target medical image to obtain a bleeding area image includes:
[0012] Determine the tissue organ to which the target medical image belongs, and determine a target image segmentation model in a preset image segmentation model set based on the tissue organ;
[0013] The target medical image is segmented based on the target image segmentation model to obtain a bleeding area image.
[0014] Optionally, the extracting bleeding feature information corresponding to the bleeding area image includes:
[0015] Acquire the morphological features corresponding to the image of the bleeding area, and acquire the pixel density change corresponding to the change of the image of the bleeding area over time;
[0016] The bleeding feature information corresponding to the bleeding area image is determined according to the morphological feature and the pixel density change.
[0017] Optionally, the bleeding characteristic information includes bleeding speed, bleeding volume, number of bleeding points and bleeding point locations, and the bleeding risk assessment of the patient based on the bleeding characteristic information to determine the bleeding risk level includes:
[0018] At least one of the bleeding speed, the bleeding volume, the number of bleeding points and the location of the bleeding points is input into a pre-created evaluation model to determine the bleeding risk level.
[0019] Optionally, inputting at least one of the bleeding speed, the bleeding volume, the number of bleeding points and the location of the bleeding points into a pre-created assessment model to determine the bleeding risk level comprises:
[0020] Inputting at least one of the bleeding speed, the bleeding volume, the number of bleeding points, and the location of the bleeding points into a pre-created evaluation model to obtain a bleeding evaluation value;
[0021] If there are bleeding assessment values in at least two dimensions, determining the bleeding risk level according to the bleeding assessment values and their corresponding preset weight values;
[0022] If there is only one dimensional bleeding assessment value, the bleeding risk level is determined based on the bleeding assessment value.
[0023] Optionally, the performing bleeding risk assessment on the patient based on the bleeding characteristic information and determining the bleeding risk level comprises:
[0024] According to the bleeding risk level and the preset mapping relationship between the risk level and the diagnosis and treatment method, the target diagnosis and treatment method corresponding to the bleeding risk level is determined.
[0025] In a second aspect, an embodiment of the present application provides a bleeding risk assessment device, the bleeding risk assessment device comprising:
[0026] A scanning unit, used for performing an image scan on a target body area of a patient to obtain a target medical image;
[0027] An extraction unit, used for extracting bleeding characteristic information corresponding to the target medical image;
[0028] A determination unit is used to perform a bleeding risk assessment on the patient based on the bleeding characteristic information and determine a target bleeding risk level.
[0029] In a third aspect, an embodiment of the present application also provides a bleeding risk assessment device, comprising a memory storing a computer program; a processor loads the computer program from the memory to execute the steps of any bleeding risk assessment method provided in the embodiment of the present application.
[0030] 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 a processor to load to execute the steps of any one of the bleeding risk assessment methods provided in the embodiments of the present application.
[0031] 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 bleeding risk assessment methods provided in the embodiments of the present application.
[0032] By adopting the scheme of the embodiment of the application, the target body area of the patient is scanned to obtain the target medical image; the bleeding characteristic information corresponding to the target medical image is extracted; the bleeding risk of the patient is assessed based on the bleeding characteristic information to determine the bleeding risk level. By assessing the bleeding risk of the patient based on the bleeding characteristic information corresponding to the medical image to determine the bleeding risk level, it is avoided that the manual analysis of the medical image by medical staff may easily lead to operational errors, thereby improving the accuracy of the bleeding risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] 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.
[0034] Figure 1 This is a schematic diagram of the first embodiment of the bleeding risk assessment method provided by the present application;
[0035] Figure 2 This is a flow chart of a second embodiment of the bleeding risk assessment method provided by the present application;
[0036] Figure 3 This is a schematic flow chart of a third embodiment of the bleeding risk assessment method provided by the present application;
[0037] Figure 4 is a schematic diagram of the structure of a bleeding risk assessment device provided in an embodiment of the present application;
[0038] Figure 5 It is a structural schematic diagram of the bleeding risk assessment device provided in the embodiments of the present application. DETAILED DESCRIPTION
[0039] 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.
[0040] Embodiments of the present application provide a bleeding risk assessment method, apparatus, device, and computer-readable storage medium.
[0041] Specifically, this embodiment will be described from the perspective of a bleeding risk assessment device, which can be integrated into a bleeding risk assessment apparatus, that is, the bleeding risk assessment method of the embodiment of the present application can be executed by the bleeding risk assessment device.
[0042] The bleeding risk assessment method provided in the embodiment of the present application can be applied to a bleeding risk assessment device, which can be a smart terminal, a PC terminal, a mobile terminal, or other device.
[0043] The following is a detailed description in conjunction with the accompanying drawings. In this embodiment, the execution subject is an example of a bleeding risk assessment 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.
[0044] Please refer to Figure 1 , a first embodiment of the bleeding risk assessment method is proposed, and the first embodiment includes the following steps:
[0045] Step 101, performing an image scan on a target body area of a patient to obtain a target medical image;
[0046] Step 102, extracting bleeding characteristic information corresponding to the target medical image;
[0047] Step 103: Perform a bleeding risk assessment on the patient based on the bleeding characteristic information to determine the bleeding risk level.
[0048] In this embodiment, when it is necessary to evaluate the blood risk level of the target body area of the patient, the bleeding risk evaluation device performs an image scan on the target body area of the patient to obtain the target medical image, extracts the bleeding characteristic information corresponding to the target medical image, and evaluates the bleeding risk of the patient based on the bleeding characteristic information to determine the bleeding risk level. Then, the target diagnosis and treatment method of the patient is determined according to the bleeding risk level.
[0049] It should be noted that the target body area can be the liver, kidney, stomach, small intestine and large intestine, etc.; illustratively, when patients with gastrointestinal discomfort seek emergency medical treatment, they usually undergo imaging tests on the stomach and intestines. Through imaging tests, the target medical images corresponding to the stomach and intestines are obtained, and the gastrointestinal bleeding area is identified using the gastrointestinal bleeding recognition model to obtain the bleeding characteristic information such as the location, volume (amount of bleeding), and morphology of the bleeding area. Based on the bleeding characteristic information, the patient's gastrointestinal bleeding risk is assessed to determine the bleeding risk level. According to the patient's bleeding risk level, the patient's target diagnosis and treatment method is determined. For example, if the bleeding risk level is severe, immediate surgery is required. If the bleeding risk level is moderate, you can stay in the hospital for observation. If the bleeding risk level is mild, you can take medicine and go home to rest.
[0050] The bleeding risk assessment device of this embodiment performs bleeding risk assessment on the patient based on the bleeding characteristic information corresponding to the medical image to determine the bleeding risk level, thereby avoiding manual analysis of medical images by medical staff that may easily lead to operational errors and improving the accuracy of bleeding risk assessment.
[0051] Specifically, each step is described in detail below:
[0052] Step 101 , performing an image scan on a target body area of a patient to obtain a target medical image.
[0053] In this step, when it is necessary to evaluate the blood risk level of the target body area of the patient, the bleeding risk assessment device performs an image scan on the target body area of the patient to obtain a target medical image. Specifically, the bleeding risk assessment device scans the target body area of the patient (CT, MR, 4D ultrasound, etc.) to obtain a medical image of the target body area. The physiological tissue of the target medical image is segmented using a pre-trained physiological tissue segmentation model, and the target medical image is extracted.
[0054] Exemplarily, the bleeding risk assessment device scans the patient's abdominal area (CT, MR, 4D ultrasound, etc.) to obtain medical images of the abdominal area. The stomach and intestines in the medical images of the abdominal area are segmented using the pre-trained stomach tissue segmentation model and the intestinal tissue segmentation model, and the stomach medical image and the intestinal medical image are extracted.
[0055] Step 102, extracting bleeding characteristic information corresponding to the target medical image;
[0056] In this step, after obtaining the target medical image, the bleeding risk assessment device identifies the target medical image and extracts the bleeding feature information corresponding to the target medical image. Specifically, the bleeding risk assessment device includes a plurality of feature recognition models, and the bleeding risk assessment device uses the corresponding feature recognition model to extract the bleeding feature information corresponding to the target medical image according to the type of physiological tissue in the target medical image.
[0057] Exemplarily, the bleeding risk assessment device obtains a gastric medical image, and extracts bleeding feature information corresponding to the gastric medical image based on a gastric bleeding feature recognition model. The bleeding feature information includes bleeding rate, bleeding amount, number of bleeding points, and location of bleeding points.
[0058] Step 103: Perform a bleeding risk assessment on the patient based on the bleeding characteristic information to determine the bleeding risk level.
[0059] In this step, the bleeding risk assessment device performs a bleeding risk assessment on the patient based on the bleeding characteristic information to determine the bleeding risk level. Optionally, the bleeding risk assessment device inputs all the bleeding characteristic information into a pre-created bleeding risk level assessment model and outputs the bleeding risk level. Optionally, the bleeding risk assessment device inputs part of the bleeding characteristic information into a pre-created bleeding risk level assessment model and outputs the bleeding risk level.
[0060] The bleeding risk assessment device of this embodiment performs an image scan on the target body area of the patient to obtain a target medical image; extracts bleeding characteristic information corresponding to the target medical image; and performs a bleeding risk assessment on the patient based on the bleeding characteristic information to determine the bleeding risk level. By performing a bleeding risk assessment on the patient based on the bleeding characteristic information corresponding to the medical image to determine the bleeding risk level, it is possible to avoid manual analysis of medical images by medical staff, which may easily lead to operational errors, and improve the accuracy of bleeding risk assessment.
[0061] Further, refer to Figure 2 A second embodiment of the bleeding risk assessment method is proposed. The difference between the second embodiment and the first embodiment is that the extraction of bleeding feature information corresponding to the target medical image includes:
[0062] Step 1021, inputting the target medical image into a pre-created bleeding area recognition model, and determining the bleeding area based on the target medical image by using the bleeding area recognition model;
[0063] In this step, the bleeding risk assessment device inputs the target medical image into a pre-created bleeding area recognition model, and determines the bleeding area based on the target medical image through the bleeding area recognition model; it should be noted that the target medical image may include a bleeding area or may not include a bleeding area, and the bleeding risk assessment device inputs the target medical image into the bleeding area recognition model, and determines whether there is a bleeding area in the tissue or organ in the target medical image through the bleeding area recognition model. When there is a bleeding area in the tissue or organ in the target medical image, the bleeding area recognition model outputs the bleeding area corresponding to the tissue or organ in the target medical image, and when there is no bleeding area in the tissue or organ in the target medical image, the bleeding area recognition model outputs a prompt message that there is no bleeding area in the tissue or organ in the target medical image.
[0064] Exemplarily, the target medical image is a gastric medical image, and the stomach is usually divided into four regions, namely the cardia, body, antrum, and pylorus. The bleeding risk assessment device inputs the gastric medical image into a pre-created bleeding region recognition model. If there is bleeding in the body of the stomach, the bleeding region recognition model outputs that the corresponding bleeding region of the stomach in the gastric medical image is the body; if there is bleeding in the cardia and antrum of the stomach, the bleeding region recognition model outputs that the corresponding bleeding region of the stomach in the gastric medical image is the cardia and antrum; if there is no bleeding in the cardia, body, antrum, and pylorus of the stomach, the bleeding region recognition model outputs a prompt message that there is no bleeding region in the stomach in the gastric medical image.
[0065] Step 1022: Segment the target medical image to obtain a bleeding region image, and extract bleeding feature information corresponding to the bleeding region image.
[0066] In this step, after determining the bleeding area corresponding to the tissue organ in the target medical image, the bleeding risk assessment device segments the target medical image through an image segmentation model and extracts the bleeding area image therefrom; the bleeding risk assessment device then performs feature analysis on the bleeding area image and extracts the bleeding feature information corresponding to the bleeding area image.
[0067] Specifically, segmenting the target medical image to obtain a bleeding area image includes:
[0068] Step 10221, determining the tissue organ to which the target medical image belongs, and determining a target image segmentation model in a preset image segmentation model set based on the tissue organ;
[0069] In this step, the bleeding risk assessment device determines the tissue and organ to which the target medical image belongs, and determines the target image segmentation model in a preset image segmentation model set based on the tissue and organ; specifically, the preset image segmentation model set in the bleeding risk assessment device includes image segmentation models corresponding to a variety of tissues and organs, and each image segmentation model is bound to its corresponding tissue and organ type and stored in the bleeding risk assessment device. The bleeding risk assessment device selects an image segmentation model bound to the corresponding tissue and organ type from the preset image segmentation model set as the target image segmentation model according to the tissue and organ to which the target medical image belongs.
[0070] Step 10222: Segment the target medical image based on the target image segmentation model to obtain a bleeding area image.
[0071] In this step, the bleeding risk assessment device segments the target medical image based on the target image segmentation model to obtain a bleeding area image; exemplarily, the target medical image is a stomach medical image, and the corresponding target image segmentation model is a stomach image segmentation model. The bleeding risk assessment device inputs the stomach medical image into the stomach image segmentation model, and the stomach image segmentation model segments the stomach medical image into a cardia medical image, a stomach body medical image, a gastric antrum medical image, and a gastric pylorus medical image; the bleeding risk assessment device determines the bleeding area image in the cardia medical image, the gastric body medical image, the gastric antrum medical image, and the gastric pylorus medical image according to the bleeding area of the stomach determined by the above analysis. For example: if there is bleeding in the gastric antrum of the stomach, at this time, the corresponding bleeding area of the stomach is the gastric antrum, and the bleeding risk assessment device determines the gastric antrum medical image as the bleeding area image; if there is bleeding in the cardia and gastric antrum of the stomach, at this time, the corresponding bleeding areas of the stomach are the cardia and gastric antrum, and the bleeding risk assessment device determines the cardia medical image and the gastric antrum medical image as the bleeding area images.
[0072] Specifically, extracting the bleeding feature information corresponding to the bleeding area image includes:
[0073] Step 10223, obtaining the morphological features corresponding to the bleeding area image, and obtaining the pixel density change corresponding to the bleeding area image changing over time;
[0074] In this step, the bleeding risk assessment device obtains the morphological features corresponding to the bleeding area image, and obtains the pixel density change corresponding to the bleeding area image over time. Specifically, the morphology of the bleeding area image can provide important clues, such as the shape, size and boundary of the bleeding location. Bleeding may have an irregular shape with blurred or clear boundaries; the pixel density change corresponding to the bleeding area image over time can reflect the area with abnormal density in the image caused by bleeding.
[0075] Step 10224: Determine the bleeding feature information corresponding to the bleeding area image according to the morphological features and the pixel density variation.
[0076] In this step, the bleeding risk assessment device determines the bleeding characteristic information corresponding to the bleeding area image according to the morphological characteristics and the pixel density change. Specifically, the bleeding characteristic information includes bleeding speed, bleeding amount, number of bleeding points and bleeding point positions. The bleeding risk assessment device determines the number of bleeding points and bleeding point positions in the bleeding area image according to the morphological characteristics, and determines the bleeding speed and bleeding amount in the bleeding area image according to the pixel density change.
[0077] Specifically, the morphological features can reflect the shape, size and boundaries of the bleeding location. The bleeding risk assessment device determines the number and locations of bleeding points in the bleeding area image based on the shape, size and boundaries of the bleeding location. The pixel density change reflects the area in the image with abnormal density caused by bleeding. The bleeding risk assessment device determines the pixel density change based on the pixel density of the bleeding location in multiple consecutive frames of bleeding area images. The amount of bleeding in the bleeding area image can be calculated based on the pixel density change. The bleeding speed in the bleeding area image can be calculated based on the pixel density change and the time of multiple consecutive frames of bleeding area images.
[0078] Exemplarily, the pixel density of the bleeding area image in the initial frame is 100PPI, and the pixel density of the bleeding area image in the final frame is 1000PPI. At this time, the pixel density change is 900PPI. The bleeding risk assessment device determines the bleeding amount based on the preset mapping relationship between the pixel density change and the bleeding amount. The time difference between the bleeding area image in the initial frame and the bleeding area image in the final frame is 3 seconds. The bleeding risk assessment device calculates the ratio of the pixel density change and the time difference as 900PPI / 3 seconds, and obtains a changing speed of the pixel density change of 300PPI / second. The bleeding risk assessment device determines the bleeding speed based on the preset mapping relationship between the changing speed of the pixel density change and the bleeding speed.
[0079] The bleeding risk assessment device of this embodiment inputs the target medical image into a pre-created bleeding area recognition model, determines the bleeding area based on the target medical image through the bleeding area recognition model; segments the bleeding area image from the target medical image, and extracts the bleeding feature information corresponding to the bleeding area image; the accuracy of extracting the bleeding feature information can be improved, thereby helping to improve the accuracy of subsequent bleeding risk assessment.
[0080] Further, refer to Figure 3, a third embodiment of the bleeding risk assessment method is proposed. The difference between the third embodiment and the first embodiment and the second embodiment is that the bleeding characteristic information includes bleeding speed, bleeding amount, number of bleeding points and bleeding point locations. The bleeding risk assessment of the patient based on the bleeding characteristic information to determine the bleeding risk level includes:
[0081] Step 1031, input at least one of the bleeding speed, the bleeding volume, the number of bleeding points and the location of the bleeding points into a pre-created evaluation model to determine the bleeding risk level.
[0082] In this step, the bleeding risk assessment device inputs at least one of the bleeding speed, bleeding volume, number of bleeding points and bleeding point locations into a pre-created assessment model to determine the bleeding risk level. Optionally, the bleeding risk assessment device inputs part of the bleeding characteristic information into a pre-created bleeding risk level assessment model to output the bleeding risk level. Preferably, the bleeding risk assessment device inputs all the bleeding characteristic information into a pre-created bleeding risk level assessment model to output the bleeding risk level.
[0083] Specifically, step 1031 includes:
[0084] Step 10311, inputting at least one of the bleeding speed, the bleeding volume, the number of bleeding points, and the position of the bleeding points into a pre-created evaluation model to obtain a bleeding evaluation value;
[0085] In this step, the bleeding risk assessment device inputs at least one of the bleeding speed, bleeding volume, number of bleeding points, and bleeding point location into a pre-created assessment model to obtain a bleeding assessment value. It is understandable that for each feature of the bleeding speed, bleeding volume, number of bleeding points, and bleeding point location, the assessment model will output a corresponding bleeding assessment value.
[0086] Step 10312: if there are bleeding assessment values of at least two dimensions, determine the bleeding risk level according to the bleeding assessment values and their corresponding preset weight values;
[0087] In this step, if the bleeding risk assessment device determines that the assessment model outputs bleeding assessment values of at least two dimensions, the bleeding risk level is determined according to the bleeding assessment values and their corresponding preset weight values; specifically, the bleeding rate, bleeding amount, number of bleeding points and bleeding point locations are ranked in order of importance based on clinical experience, medical guidelines and other standards, and the ranking is: bleeding rate> bleeding amount> number of bleeding points> bleeding point locations. Correspondingly, the greater the importance, the greater the corresponding preset weight value. The bleeding risk assessment device determines the corresponding preset weight value according to the characteristic information corresponding to the bleeding assessment value, and then determines the target bleeding assessment value according to the preset weight value and the bleeding assessment value, and then determines the bleeding risk level according to the target bleeding assessment value.
[0088] Exemplarily, the bleeding risk assessment device simultaneously inputs the bleeding rate, bleeding amount, number of bleeding points, and bleeding point locations into a pre-created assessment model to obtain a first bleeding assessment value corresponding to the bleeding rate, a second bleeding assessment value corresponding to the bleeding amount, a third bleeding assessment value corresponding to the number of bleeding points, and a fourth bleeding assessment value corresponding to the bleeding point locations. The bleeding risk assessment device determines a first preset weight value corresponding to the bleeding rate, a second preset weight value corresponding to the bleeding amount, a third preset weight value corresponding to the number of bleeding points, and a fourth preset weight value corresponding to the bleeding point locations; target bleeding assessment value = first bleeding assessment value * first preset weight value + second bleeding assessment value * second preset weight value + third bleeding assessment value * third preset weight value + fourth bleeding assessment value * fourth preset weight value; the bleeding risk assessment device determines the corresponding bleeding risk level based on the mapping relationship between the target bleeding assessment value, the preset bleeding assessment value, and the bleeding risk level.
[0089] Step 10313: If there is only one dimensional bleeding assessment value, determine the bleeding risk level based on the bleeding assessment value.
[0090] In this step, if the bleeding risk assessment device determines that the assessment model outputs a bleeding assessment value of one dimension, the mapping relationship between the bleeding assessment value and the preset bleeding assessment value and bleeding risk level is used to determine the corresponding bleeding risk level.
[0091] Furthermore, the step of performing a bleeding risk assessment on the patient based on the bleeding characteristic information and determining the bleeding risk level includes:
[0092] Step 104, determining a target diagnosis and treatment method corresponding to the bleeding risk level according to the bleeding risk level and a preset mapping relationship between the risk level and the diagnosis and treatment method.
[0093] In this step, the bleeding risk assessment device determines the target diagnosis and treatment method corresponding to the bleeding risk level according to the bleeding risk level and the preset mapping relationship between the risk level and the diagnosis and treatment method. For example: if the bleeding risk level is severe, surgery is required immediately. If the bleeding risk level is moderate, you can stay in the hospital for observation. If the bleeding risk level is mild, you can take medicine and go home to rest.
[0094] The bleeding risk assessment device in this embodiment inputs at least one of the bleeding speed, bleeding volume, number of bleeding points and bleeding point locations into a pre-created assessment model to determine the bleeding risk level, which can improve the accuracy of bleeding risk assessment.
[0095] This embodiment also provides a bleeding risk assessment device, which can be integrated into a bleeding risk assessment device such as a smart terminal, a PC terminal, a mobile terminal, etc. Figure 4 As shown, the bleeding risk assessment device may include:
[0096] The scanning unit 1001 is used to perform image scanning on a target body area of a patient to obtain a target medical image;
[0097] An extraction unit 1002 is used to extract bleeding characteristic information corresponding to the target medical image;
[0098] The determination unit 1003 is used to perform a bleeding risk assessment on the patient based on the bleeding characteristic information to determine a target bleeding risk level.
[0099] In an optional example, the extraction unit is further configured to:
[0100] Inputting the target medical image into a pre-created bleeding area recognition model, and determining the bleeding area based on the target medical image by using the bleeding area recognition model;
[0101] A bleeding region image is segmented from the target medical image, and bleeding feature information corresponding to the bleeding region image is extracted.
[0102] In an optional example, the extraction unit is further configured to:
[0103] Determine the tissue organ to which the target medical image belongs, and determine a target image segmentation model in a preset image segmentation model set based on the tissue organ;
[0104] The target medical image is segmented based on the target image segmentation model to obtain a bleeding area image.
[0105] In an optional example, the extraction unit is further configured to:
[0106] Acquire the morphological features corresponding to the image of the bleeding area, and acquire the pixel density change corresponding to the change of the image of the bleeding area over time;
[0107] The bleeding feature information corresponding to the bleeding area image is determined according to the morphological feature and the pixel density change.
[0108] In an optional example, the determining unit is further configured to:
[0109] At least one of the bleeding speed, the bleeding volume, the number of bleeding points and the location of the bleeding points is input into a pre-created evaluation model to determine the bleeding risk level.
[0110] In an optional example, the determining unit is further configured to:
[0111] Inputting at least one of the bleeding speed, the bleeding volume, the number of bleeding points, and the location of the bleeding points into a pre-created evaluation model to obtain a bleeding evaluation value;
[0112] If there are bleeding assessment values in at least two dimensions, determining the bleeding risk level according to the bleeding assessment values and their corresponding preset weight values;
[0113] If there is only one dimensional bleeding assessment value, the bleeding risk level is determined based on the bleeding assessment value.
[0114] In an optional example, the determining unit is further configured to:
[0115] According to the bleeding risk level and the preset mapping relationship between the risk level and the diagnosis and treatment method, the target diagnosis and treatment method corresponding to the bleeding risk level is determined.
[0116] By adopting the scheme of this embodiment, the target body area of the patient is scanned to obtain the target medical image; the bleeding characteristic information corresponding to the target medical image is extracted; the bleeding risk of the patient is assessed based on the bleeding characteristic information to determine the bleeding risk level. By assessing the bleeding risk of the patient based on the bleeding characteristic information corresponding to the medical image to determine the bleeding risk level, it is avoided that the manual analysis of the medical image by medical staff may easily lead to operational errors, thereby improving the accuracy of the bleeding risk assessment.
[0117] Accordingly, the present application also provides a bleeding risk assessment device, such as Figure 5 As shown, Figure 5A schematic diagram of the structure of a bleeding risk assessment device provided in an embodiment of the present application. The bleeding risk assessment 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. It will be appreciated by those skilled in the art that the bleeding risk assessment device structure shown in the figure does not constitute a limitation on the bleeding risk assessment device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.
[0118] The processor 1101 is the control center of the bleeding risk assessment device 1100, and uses various interfaces and lines to connect various parts of the entire bleeding risk assessment device 1100, and executes various functions and processes data of the bleeding risk assessment 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 bleeding risk assessment 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.
[0119] In an embodiment of the present application, the processor 1101 in the bleeding risk assessment device 1100 will load the instructions corresponding to the processes of one or more applications into the memory 1102 according to the following steps, and the processor 1101 will run the application 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.
[0120] Optional, such as Figure 5 As shown, the bleeding risk assessment 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. Those skilled in the art can understand that Figure 5 The structure of the bleeding risk assessment device shown in the figure does not constitute a limitation on the bleeding risk assessment device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0121] The touch display screen 1103 can be used to display a graphical user interface and receive the operation instructions 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 to display the information input by the user or the information provided to the user and various graphical user interfaces of the bleeding risk assessment 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-EmittingDiode) and the like. The touch panel can be used to collect the touch operation of the user on or near it (such as the user uses any suitable object or attachment such as a finger, a stylus on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts of 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.
[0122] 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 bleeding risk assessment device through wireless communication, and to send and receive signals between the network device or other bleeding risk assessment device.
[0123] The audio circuit 1105 can be used to provide an audio interface between the user and the bleeding risk assessment 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 bleeding risk assessment 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 bleeding risk assessment device.
[0124] 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.
[0125] The power supply 1107 is used to supply power to various components of the bleeding risk assessment 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 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.
[0126] although Figure 5 Not shown, the bleeding risk assessment device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.
[0127] 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.
[0128] 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.
[0129] To this end, the present application embodiment provides a computer-readable storage medium, in which multiple computer programs are stored, and the computer program can be loaded by a processor to execute any one of the bleeding risk assessment methods provided in the present application embodiment. The computer program can execute the bleeding risk assessment method, and the specific implementation can be referred to the previous embodiment, which will not be repeated here.
[0130] 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.
[0131] Since the computer program stored in the computer-readable storage medium can execute any one of the bleeding risk assessment methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the bleeding risk assessment 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.
[0132] 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 bleeding risk assessment device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the bleeding risk assessment device performs the methods provided in various optional implementations in the above-mentioned embodiments.
[0133] In the above-mentioned bleeding risk assessment device, computer-readable storage medium, bleeding risk assessment equipment, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, refer to the relevant description 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 bleeding risk assessment device, computer-readable storage medium, computer program product, bleeding risk assessment equipment and its corresponding units described above can refer to the description of the bleeding risk assessment method in the above embodiment, and will not be repeated here.
[0134] The above is a detailed introduction to a bleeding risk assessment method, device, equipment, computer-readable storage medium, and computer program product provided in the embodiments of the present application. Specific examples are used herein 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 technicians in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for assessing bleeding risk, characterized in that: The bleeding risk assessment method includes: Performing an imaging scan on a target body area of a patient to obtain a target medical image; Extracting bleeding characteristic information corresponding to the target medical image; A bleeding risk assessment is performed on the patient based on the bleeding characteristic information to determine the bleeding risk level.
2. The method for assessing bleeding risk according to claim 1, characterized in that: The extracting bleeding characteristic information corresponding to the target medical image includes: Inputting the target medical image into a pre-created bleeding area recognition model, and determining the bleeding area based on the target medical image by using the bleeding area recognition model; A bleeding region image is segmented from the target medical image, and bleeding feature information corresponding to the bleeding region image is extracted.
3. The method for assessing bleeding risk according to claim 2, characterized in that: The step of segmenting the target medical image to obtain a bleeding area image comprises: Determine the tissue organ to which the target medical image belongs, and determine a target image segmentation model in a preset image segmentation model set based on the tissue organ; The target medical image is segmented based on the target image segmentation model to obtain a bleeding area image.
4. The method for assessing bleeding risk according to claim 2, characterized in that: The extracting bleeding feature information corresponding to the bleeding area image includes: Acquire the morphological features corresponding to the image of the bleeding area, and acquire the pixel density change corresponding to the change of the image of the bleeding area over time; The bleeding feature information corresponding to the bleeding area image is determined according to the morphological feature and the pixel density change.
5. The method for assessing bleeding risk according to claim 1, characterized in that: The bleeding characteristic information includes bleeding speed, bleeding volume, number of bleeding points and bleeding point locations. The bleeding risk assessment of the patient based on the bleeding characteristic information to determine the bleeding risk level includes: At least one of the bleeding speed, the bleeding volume, the number of bleeding points and the location of the bleeding points is input into a pre-created evaluation model to determine the bleeding risk level.
6. The method for assessing bleeding risk according to claim 5, characterized in that: The step of inputting at least one of the bleeding speed, the bleeding volume, the number of bleeding points and the location of the bleeding points into a pre-created assessment model to determine the bleeding risk level comprises: Inputting at least one of the bleeding speed, the bleeding volume, the number of bleeding points, and the location of the bleeding points into a pre-created evaluation model to obtain a bleeding evaluation value; If there are bleeding assessment values in at least two dimensions, determining the bleeding risk level according to the bleeding assessment values and their corresponding preset weight values; If there is only one dimensional bleeding assessment value, the bleeding risk level is determined based on the bleeding assessment value.
7. The method for assessing bleeding risk according to any one of claims 1 to 6, characterized in that: After the bleeding risk assessment of the patient based on the bleeding characteristic information and the bleeding risk level is determined, the method includes: According to the bleeding risk level and the preset mapping relationship between the risk level and the diagnosis and treatment method, the target diagnosis and treatment method corresponding to the bleeding risk level is determined.
8. A bleeding risk assessment device, characterized in that: The bleeding risk assessment device comprises: A scanning unit, used for performing an image scan on a target body area of a patient to obtain a target medical image; An extraction unit, used for extracting bleeding characteristic information corresponding to the target medical image; A determination unit is used to perform a bleeding risk assessment on the patient based on the bleeding characteristic information and determine a target bleeding risk level.
9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program; the processor loads the computer program from the memory to execute the steps of the bleeding risk assessment method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the bleeding risk assessment method according to any one of claims 1 to 7.