A method, system and electronic device for determining event probability

Abstract

The present application discloses an event probability determination method, system and electronic device. Through the above method, the category to which the to-be-processed image data belongs can be directly determined by an unsupervised clustering network, and then according to the correspondence between the category and the event probability, the probability of anastomotic complications occurring in the to-be-processed image data can be further determined, thus avoiding the problems of low accuracy and efficiency caused by manual determination.

Description

Technical Field

[0001] This application relates to the field of electronic technologies, and particularly to a method, a system, and an electronic device for determining an event probability. Background Art

[0002] Currently, many diseases can be treated through surgeries. Although surgical techniques and postoperative care have been greatly improved, anastomotic complications may occur at the anastomotic site due to various reasons during the surgery.

[0003] One of the reasons for anastomotic complications is poor perfusion at the anastomotic site. Therefore, due to differences in vascular structures, resection and anastomosis in a poorly perfused colon area may lead to insufficient postoperative colon perfusion. Acute insufficient perfusion at the anastomotic site can cause anastomotic leakage or colon necrosis. Since it is subjective, lacks objective criteria, and it is difficult to detect minor changes in the microcirculation of the colon wall, visually observing the color change of the intestine may not be reliable. However, due to differences in vascular structures and blood flow pathways in the collateral circulation, the indocyanine green (ICG) curve morphology of each patient is different, reflecting different perfusion states. ICG images are also affected by factors such as infrared light intensity, camera exposure time, and shooting distance. Therefore, the current efficiency and accuracy of detecting and analyzing the anastomotic site are relatively low. Summary of the Invention

[0004] This application provides a method, a system, and an electronic device for determining an event probability, so as to avoid the problems of low accuracy and low efficiency caused by manual determination.

[0005] In a first aspect, this application provides a method for determining an event probability, and the method includes:

[0006] Obtain image data to be processed;

[0007] Import the image data to be processed into an unsupervised clustering network to determine the current data category to which the image data to be processed belongs;

[0008] Determine the current event probability corresponding to the current data category according to the correspondence between the data category and the event probability.

[0009] Through the above method, the category to which the image data to be processed belongs can be directly determined through the unsupervised clustering network, and then according to the correspondence between the category and the event probability, the probability of anastomotic complications occurring in the image data to be processed can be further determined, thus avoiding the problems of low accuracy and low efficiency caused by manual determination.

[0010] In an optional embodiment, before obtaining the image data to be processed, the method further includes:

[0011] Obtain a set number of training data, where the training data contains the fluorescence intensity change curve information of each image data;

[0012] Import the set number of training data into the unsupervised clustering network for training to obtain multiple data categories.

[0013] In an optional embodiment, the obtaining the set number of training data includes:

[0014] Each piece of training data in the set number of training data is obtained according to the following method:

[0015] Determine two regions of interest (ROIs) in the reference image, and obtain the first average fluorescence intensity curve corresponding to the first ROI region and the second average fluorescence intensity curve corresponding to the second ROI region among the two ROI regions;

[0016] Plot the first average fluorescence intensity region and the second average fluorescence intensity curve in the same coordinate system to obtain one piece of the training data.

[0017] In an optional embodiment, the determining two ROI regions in the reference image includes:

[0018] Select temporary ROI regions with equal distance from the anastomosis and the same area at both ends of the anastomosis in the reference image;

[0019] Connect the center points of the two temporary ROI regions, and respectively determine one ROI region on both sides of the connection line to obtain two ROI regions.

[0020] In an optional embodiment, the obtaining the first average fluorescence intensity curve corresponding to the first ROI region and the second average fluorescence intensity curve corresponding to the second ROI region among the two ROI regions includes:

[0021] Track the first ROI region according to the target tracking algorithm to obtain the first average fluorescence intensity curve of the first ROI region within a set time period;

[0022] When it is monitored that the fluorescence intensity of the second ROI region reaches the fluorescence intensity of the first ROI region, obtain the second average fluorescence intensity curve of the second ROI region within the set time period before reaching the fluorescence intensity.

[0023] In a second aspect, the present application provides an event probability determination system, and the system includes:

[0024] An acquisition module, configured to acquire image data to be processed;

[0025] A processing module, configured to import the to-be-processed image data into an unsupervised clustering network, determine the current data category to which the to-be-processed image data belongs; and determine the current event probability corresponding to the current data category according to the correspondence between the data category and the event probability.

[0026] In an optional embodiment, the obtaining module is further configured to obtain a set number of training data, where the training data includes fluorescence intensity change curve information of each image data;

[0027] The processing module is further configured to import the set number of training data into the unsupervised clustering network for training to obtain multiple data categories.

[0028] In an optional embodiment, the obtaining module is specifically configured to obtain each of the set number of training data according to the following method:

[0029] Determine two regions of interest (ROIs) in a reference image, and obtain a first average fluorescence intensity curve corresponding to a first ROI and a second average fluorescence intensity curve corresponding to a second ROI in the two ROIs;

[0030] Plot the first average fluorescence intensity region and the second average fluorescence intensity curve in the same coordinate system to obtain one of the training data.

[0031] In a third aspect, the present application provides an electronic device, including:

[0032] A memory, configured to store a computer program;

[0033] A processor, configured to implement the steps of the above-mentioned event probability determination method when executing the computer program stored in the memory.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and the computer program, when executed by a processor, implements the steps of the above-mentioned event probability determination method.

[0035] For the various aspects in the above second to fourth aspects and the possible technical effects that each aspect may achieve, please refer to the description of the possible technical effects that can be achieved in the above first aspect or various possible solutions in the first aspect, and details will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flowchart of an event probability determination method provided by the present application;

[0037] Figure 2Schematic diagram for determining the ROI region in the reference image provided for this application;

[0038] Figure 3 Schematic structural diagram of an event probability determination system provided for this application;

[0039] Figure 4 Schematic structural diagram of an electronic device provided for this application. Detailed implementation manners

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The specific operation methods in the method embodiments can also be applied to the apparatus embodiments or system embodiments. It should be noted that in the description of this application, "a plurality of" is understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The connection between A and B can represent: A is directly connected to B and A is connected to B through C. In addition, in the description of this application, words such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying an order.

[0041] The following will describe the embodiments of this application in detail with reference to the accompanying drawings.

[0042] S1. Obtain the image data to be processed;

[0043] S2. Import the image data to be processed into an unsupervised clustering network to determine the current data category to which the image data to be processed belongs;

[0044] S3. Determine the current event probability corresponding to the current data category according to the correspondence between the data category and the event probability.

[0045] In the embodiments of this application, before processing the image data to be processed, it is first necessary to train the unsupervised clustering network, and a certain amount of training data is required for training the unsupervised clustering network. Therefore, in the embodiments of this application, the training samples can be obtained through the following method.

[0046] Specifically, the video recording is processed. Here, the processing can be denoising, filtering, etc. of the video recording, which can make the image data in the video recording more accurate. After the video recording is processed, a reference image is extracted from the video recording. In the reference image, the colorectal region is used as the reference region, and two temporary regions of interest (ROIs) with the same distance from the anastomosis and the same area are selected at both ends of the reference region of the anastomosis. The centers of these two temporary ROI regions are connected, and an ROI region is determined on each side of the connection line, resulting in two ROI regions.

[0047] For example, as Figure 2 shown is a frame image in the video recording. This image is the reference image. The anastomosis is determined in this reference image, and a temporary ROI region is selected at each end of the anastomosis. The two temporary ROI regions are equidistant from the anastomosis, and the areas of these two ROI regions are the same. In Figure 2 , the two temporary ROI regions are rectangles with the same area.

[0048] The centers of the two temporary ROI regions are connected. At this time, a connection line is obtained. Multiple parallel lines are generated on both the upper and lower sides of this connection line, and an ROI region is determined on each side of the parallel lines, so that two ROI regions can be obtained. These two ROI regions are used as the finally selected ROI regions.

[0049] After the ROI regions are determined, according to the object tracking algorithm (Tracking-Learning-Detection, TLD), in the two ROI regions, the ROI region near the perfusion end is tracked within a set time period (such as 30 s), and the first average fluorescence intensity curve that changes stably over time in this ROI region within the set time period is obtained.

[0050] After the first average fluorescence intensity curve corresponding to the first ROI region is determined, for the second ROI region far from the perfusion end, that is, the second ROI region on the other side of the anastomosis, the fluorescence intensity of the second ROI region is tracked in real time, and the time when the fluorescence intensity of the second ROI region approaches the first ROI region on the side near the perfusion segment is determined. Taking this time as the base point, the second average fluorescence intensity curve corresponding to the second ROI region within the set time period (such as 30 s) is also traced back using the TLD algorithm.

[0051] After the first average fluorescence intensity curve and the second average fluorescence intensity curve are determined, the first average fluorescence intensity curve and the second average fluorescence intensity curve are plotted on the same time axis, thereby generating a training data.

[0052] In the above manner, a corresponding training data can be generated for each frame image in the video recording. Therefore, in the embodiments of the present application, a set number of training data can be obtained in the above manner. For example, the training data can be defined as 10,000 copies.

[0053] After obtaining the set number of training data, the training data is imported into an unsupervised clustering network, and the unsupervised clustering network trains the imported training data, so as to obtain each clustering sample, and these clustering samples will be used as samples for determining the category to which the image data belongs subsequently.

[0054] After completing the above training, if the image data to be processed is obtained, at this time, the image data to be processed is imported into the unsupervised clustering network to determine the current data category to which the image data to be processed belongs.

[0055] Briefly speaking, after the image data to be processed is imported into the unsupervised clustering network, the data category of the image data to be processed can be determined through the unsupervised clustering network, that is, the category to which the anastomotic complication in the image belongs is determined. Then, further according to the corresponding relationship between the data category and the event probability, the current event probability corresponding to the current data category of the image data to be processed is determined. That is, the probability of anastomotic complication occurring.

[0056] Through the above method, the category to which the image data to be processed belongs can be directly determined through the unsupervised clustering network, and then according to the corresponding relationship between the category and the event probability, the probability of anastomotic complication occurring in the image data to be processed is further determined, thus avoiding the problems of low accuracy and low efficiency caused by manual determination.

[0057] Based on the same inventive concept, an event probability determination system is also provided in the embodiments of the present application, as Figure 3 shown in the structural schematic diagram of an event probability determination system provided by the embodiments of the present application. The system includes:

[0058] An acquisition module 301, configured to acquire image data to be processed;

[0059] A processing module 302, configured to import the image data to be processed into an unsupervised clustering network to determine the current data category to which the image data to be processed belongs; and determine the current event probability corresponding to the current data category according to the corresponding relationship between the data category and the event probability.

[0060] Further, in an optional embodiment, the acquisition module 301 is further configured to acquire a set number of training data, where the training data includes information on the fluorescence intensity change curves of each image data;

[0061] The processing module 302 is further configured to import a set number of training data into the unsupervised clustering network for training to obtain multiple data categories.

[0062] Further, in an alternative embodiment, the obtaining module 301 is specifically configured to obtain each of the set number of training data by the following method:

[0063] Determine two regions of interest (ROIs) in a reference image, and obtain a first average fluorescence intensity curve corresponding to a first ROI region and a second average fluorescence intensity curve corresponding to a second ROI region among the two ROI regions;

[0064] Plot the first average fluorescence intensity region and the second average fluorescence intensity curve in the same coordinate system to obtain one of the training data.

[0065] Further, in an alternative embodiment, the obtaining module 301 is specifically configured to track the first ROI region according to a target tracking algorithm to obtain the first average fluorescence intensity curve of the first ROI region within a set time period;

[0066] When it is monitored that the fluorescence intensity of the second ROI region reaches the fluorescence intensity of the first ROI region, obtain the second average fluorescence intensity curve of the second ROI region within the set time period before reaching the fluorescence intensity.

[0067] Based on the same inventive concept, an electronic device is further provided in an embodiment of the present application. The electronic device can implement the functions of the foregoing event probability determination system. Refer to Figure 4 , the electronic device includes:

[0068] At least one processor 401 and a memory 402 connected to at least one processor 401. In the embodiment of the present application, the specific connection medium between the processor 401 and the memory 402 is not limited. Figure 4 Taking the connection between the processor 401 and the memory 402 through the bus 400 as an example. The bus 400 is represented by a thick line in Figure 4 . The connection manners between other components are only for illustrative purposes and are not to be construed as limitations. The bus 400 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 4 only a thick line is used to represent it in , but it does not mean that there is only one bus or one type of bus. Alternatively, the processor 401 can also be referred to as a controller, and the name is not limited.

[0069] In an embodiment of the present application, the memory 402 stores instructions executable by at least one processor 401. By executing the instructions stored in the memory 402, the at least one processor 401 can execute an event probability determination method described above. The processor 401 can implement Figure 3 the functions of each module in the system shown.

[0070] Among them, the processor 401 is the control center of the device. It can connect various parts of the entire control device through various interfaces and lines. By running or executing the instructions stored in the memory 402 and calling the data stored in the memory 402, various functions of the device and process data, so as to monitor the device as a whole.

[0071] In a possible design, the processor 401 may include one or more processing units. The processor 401 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 401 either. In some embodiments, the processor 401 and the memory 402 can be implemented on the same chip. In some embodiments, they can also be implemented separately on independent chips.

[0072] The processor 401 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of an event probability determination method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0073] The memory 402 serves as a non-volatile computer-readable storage medium and can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The memory 402 may include at least one type of storage medium. For example, it may include flash memory, hard disks, multimedia cards, card-type memories, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memories, magnetic disks, optical discs, and so on. The memory 402 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 402 in the embodiments of the present application may also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0074] By designing and programming the processor 401, the code corresponding to the event probability determination method introduced in the foregoing embodiments can be solidified into the chip, so that the chip can execute Figure 1 the steps of the event probability determination method of the embodiment shown. How to design and program the processor 401 is a well-known technology to those skilled in the art and will not be elaborated here.

[0075] Based on the same inventive concept, the embodiments of the present application also provide a storage medium storing computer instructions, which, when run on a computer, cause the computer to execute an event probability determination method described above.

[0076] In some possible implementation manners, various aspects of the event probability determination method provided in the present application may also be implemented in the form of a program product, which includes program code. When the program product runs on a device, the program code is used to cause the control device to execute the steps in the event probability determination method according to various exemplary embodiments of the present application described above in this specification.

[0077] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0078] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0079] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0081] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for determining event probability, characterized in that, The method includes: Obtain the image data to be processed; Import the image data to be processed into an unsupervised clustering network to determine the current data category to which the image data to be processed belongs; Determine the current event probability corresponding to the current data category according to the correspondence between the data category and the event probability; Before obtaining the image data to be processed, the method further includes: Obtain a set number of training data, where the training data contains the fluorescence intensity change curve information of each image data; Import the set number of training data into the unsupervised clustering network for training to obtain multiple data categories; The obtaining of the set number of training data includes: Each training data in the set number of training data is obtained according to the following method: Determine two ROI regions in the reference image, and obtain the first average fluorescence intensity curve corresponding to the first ROI region and the second average fluorescence intensity curve corresponding to the second ROI region in the two ROI regions; Plot the first average fluorescence intensity curve and the second average fluorescence intensity curve in the same coordinate system to obtain one piece of the training data; The determination of the two ROI regions in the reference image includes: Select temporary ROI regions with equal distance from and the same area as the anastomosis at both ends of the reference image; Connect the center points of the two temporary ROI regions, and respectively determine an ROI region on both sides of the connection line to obtain two ROI regions; The obtaining of the first average fluorescence intensity curve corresponding to the first ROI region and the second average fluorescence intensity curve corresponding to the second ROI region in the two ROI regions includes: Track the first ROI region according to the target tracking algorithm to obtain the first average fluorescence intensity curve of the first ROI region within a set time period; When it is monitored that the fluorescence intensity of the second ROI region reaches the fluorescence intensity of the first ROI region, obtain the second average fluorescence intensity curve of the second ROI region within the set time period before reaching the fluorescence intensity.

2. An event probability determination system, characterized in that, The system includes: An acquisition module for obtaining the image data to be processed; A processing module for importing the image data to be processed into an unsupervised clustering network to determine the current data category to which the image data to be processed belongs; determining the current event probability corresponding to the current data category according to the correspondence between the data category and the event probability; The acquisition module is further used to obtain a set number of training data, where the training data contains the fluorescence intensity change curve information of each image data; The processing module is further used to import the set number of training data into the unsupervised clustering network for training to obtain multiple data categories; The acquisition module is specifically used to obtain each training data in the set number of training data according to the following method: Two ROI regions are determined in the reference image, and the first average fluorescence intensity curve corresponding to the first ROI region and the second average fluorescence intensity curve corresponding to the second ROI region in the two ROI regions are obtained; The first average fluorescence intensity curve and the second average fluorescence intensity curve are plotted in the same coordinate system to obtain one piece of the training data; The determining two ROI regions in the reference image includes: Temporary ROI regions with equal distances from the anastomosis and the same area are selected at both ends of the anastomosis in the reference image; The centers of the two temporary ROI regions are connected, and one ROI region is determined on each side of the connection line to obtain two ROI regions; The obtaining the first average fluorescence intensity curve corresponding to the first ROI region and the second average fluorescence intensity curve corresponding to the second ROI region in the two ROI regions includes: According to the target tracking algorithm, the first ROI region is tracked to obtain the first average fluorescence intensity curve of the first ROI region within a set time period; When it is monitored that the fluorescence intensity of the second ROI region reaches the fluorescence intensity of the first ROI region, the second average fluorescence intensity curve of the second ROI region within the set time period before reaching the fluorescence intensity is obtained.

3. An electronic device, characterized in that, including: A memory for storing a computer program; A processor for implementing the method steps recited in claim 1 when executing the computer program stored on the memory.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method steps recited in claim 1 are implemented.

Images