Abnormal discharge detection method, abnormal discharge detection device, product and equipment

Abstract

The embodiment of the invention relates to an abnormal discharge detection method, an abnormal discharge detection device, a computer program product and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: determining a to-be-detected biomedical signal of a detected object, inputting the to-be-detected biomedical signal into a first abnormal discharge detection sub-model, and performing first abnormal discharge detection on the to-be-detected biomedical signal; performing form transformation on the to-be-detected biomedical signal of the detected object to obtain image-like biomedical signal data corresponding to the to-be-detected biomedical signal; inputting the image-like biomedical signal data into a second abnormal discharge detection sub-model, and performing second abnormal discharge detection on the image-like biomedical signal data; and fusing the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result of the detected object. According to the invention, the efficiency and accuracy of abnormal discharge detection and identification can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to an abnormal discharge detection method, an abnormal discharge detection device, a computer program product, and an electronic device. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims, and no description herein is admitted to be prior art by inclusion in this section.

[0003] Electroencephalogram (EEG) is an important basis for judging whether a patient's brain function is abnormal, and is of great value for clinical diagnosis and treatment, and assessment of the severity of the disease. The rapid development of artificial intelligence technology has made it possible to realize automatic EEG analysis, especially neural network technology, which has shown good application potential in detecting abnormal EEG discharges. Summary of the invention

[0004] However, the detection accuracy and reliability of the automatic EEG abnormality detection methods in the related art are insufficient, making it difficult to achieve truly independent EEG signal abnormality detection.

[0005] Therefore, an abnormal discharge detection method is highly needed to improve the accuracy and reliability of automatic detection of EEG abnormalities.

[0006] In this context, embodiments of the present invention are intended to provide an abnormal discharge detection method, an abnormal discharge detection device, a computer-readable storage medium, a computer program product, and an electronic device.

[0007] According to a first aspect of the embodiments of the present disclosure, there is provided an abnormal discharge detection method, comprising: determining a biomedical signal to be detected of a subject, inputting the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model; performing a form transformation on the biomedical signal to be detected of the subject to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; The image-like biomedical signal data is input into a second abnormal discharge detection submodel in a pre-trained abnormal discharge detection model, and a second abnormal discharge detection is performed on the image-like biomedical signal data according to the second abnormal discharge detection submodel; the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection are fused to obtain an abnormal discharge detection result of the detected object.

[0008] Optionally, determining the biomedical signal to be detected of the subject includes: acquiring collected biomedical signals of the subject; acquiring the biomedical signals of the subject in segments according to preset time lengths, and determining at least one biomedical signal to be detected of the subject.

[0009] Optionally, the fusing the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain the abnormal discharge detection result of the object under test includes: fusing the first abnormal discharge detection result and the second abnormal discharge detection result to obtain the abnormal discharge detection result of the biomedical signal to be detected; marking the biomedical signal to be detected when the abnormal discharge detection result of the biomedical signal to be detected is abnormal discharge; and obtaining the abnormal discharge detection result of the object under test according to the marked biomedical signal to be detected.

[0010] Optionally, the first abnormal discharge detection submodel includes a first multi-head attention submodel, a first deep convolutional neural network submodel and a first fully connected layer; the biomedical signal to be detected is input into the first abnormal discharge detection submodel in the pre-trained abnormal discharge detection model, and the first abnormal discharge detection is performed on the biomedical signal to be detected according to the first abnormal discharge detection submodel; including: inputting the biomedical signal to be detected into the first multi-head attention submodel, and obtaining a first feature of the biomedical signal to be detected according to the output of the first multi-head attention submodel; inputting the first feature into the first deep convolutional neural network submodel, and obtaining a second feature according to the output of the first deep convolutional neural network submodel; inputting the second feature into the first fully connected layer, and obtaining a first fully connected feature according to the output of the first fully connected layer; processing the first fully connected feature by a preset activation function, and obtaining a first abnormal discharge detection result of the biomedical signal to be detected according to the processing result.

[0011] Optionally, the first abnormal discharge detection submodel includes a second deep convolutional neural network submodel and a second fully connected layer; the image-like biomedical signal data is input into the second abnormal discharge detection submodel in a pre-trained abnormal discharge detection model, and a second abnormal discharge detection is performed on the image-like biomedical signal data according to the second abnormal discharge detection submodel, including: inputting the image-like biomedical signal data into the second deep convolutional neural network submodel, and obtaining a third feature according to the output of the second deep convolutional neural network submodel; inputting the third feature into the second fully connected layer, and obtaining a second fully connected feature according to the output of the second fully connected layer; processing the second fully connected feature by a preset activation function, and obtaining a second abnormal discharge detection result of the biomedical signal to be detected according to the processing result.

[0012] Optionally, the biomedical signal to be detected includes a first matrix, which corresponds to a first matrix dimension. The biomedical signal to be detected of the object under test is transformed in form to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; the first matrix is ​​deformed to obtain a second matrix, which corresponds to a second matrix dimension, and the difference between the number of rows and the number of columns of the second matrix dimension is less than a preset value; and the image-like biomedical signal data is determined according to the second matrix.

[0013] Optionally, any of the deep convolutional neural network sub-models includes any one of a deep dilated convolutional network sub-model and a multi-layer convolutional neural network sub-model.

[0014] According to a second aspect of an embodiment of the present disclosure, an abnormal discharge detection device is provided, comprising: a first detection module, configured to determine a biomedical signal to be detected of a test object, input the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and perform a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model; a signal preprocessing module, configured to perform a form transformation on the biomedical signal to be detected of the test object, and obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; a second detection module, configured to input the image-like biomedical signal data into a second abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and perform a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection sub-model; and a fusion module, configured to fuse the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection, and obtain an abnormal discharge detection result of the test object.

[0015] According to a third aspect of the present disclosure, a computer program product comprising instructions is provided. When the computer program product is run on a computer, the computer is enabled to execute the steps of the abnormal discharge detection method as described in the first aspect.

[0016] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the abnormal discharge detection method as described in the first aspect of the above embodiment is implemented.

[0017] According to the fifth aspect of the embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the abnormal discharge detection method as described in the first aspect of the above embodiment.

[0018] According to the abnormal discharge detection method, abnormal discharge detection device, computer-readable storage medium, computer program product and electronic device of the embodiments of the present disclosure, a first abnormal discharge detection is performed on the original biomedical signal to be detected through a first abnormal discharge detection sub-model, and a second abnormal discharge detection is performed on the image-like biomedical signal data corresponding to the original biomedical signal to be detected through a second abnormal discharge detection sub-model, and then, the detection conditions of the first discharge detection and the second abnormal discharge detection are fused to obtain an abnormal discharge detection result. On the one hand, the present invention can retain the time information in the original biomedical signal to be detected by performing abnormal discharge detection on the original biomedical signal to be detected. By performing abnormal discharge detection on the image-like biomedical signal data, the feature extraction advantage of the neural network can be brought into play in the image-like biomedical signal data to extract deeper biomedical signal features. The combination of the two can not only retain the time information of the biomedical signal to be detected, but also extract richer biomedical signal features, which can improve the accuracy and reliability of abnormal discharge detection of the biomedical signal to be detected; on the other hand, the abnormal discharge detection result obtained according to the method of the present invention can provide doctors with more accurate reference information, so that doctors do not need to observe all the data in detail, but only need to roughly browse some key information, and then combine the abnormal discharge detection result to quickly and accurately determine the diagnosis result of the patient, saving the workload of the doctor and facilitating wide application in clinical practice; on the other hand, the present invention can realize automatic detection and recognition of abnormal discharge of biomedical signals based on the abnormal discharge detection model, thereby improving the efficiency of abnormal discharge detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic diagram showing an exemplary system architecture to which embodiments of the present disclosure may be applied; Figure 2 A schematic flow chart showing an abnormal discharge detection method in an exemplary embodiment of the present disclosure; Figure 3 A schematic flow chart showing a method for acquiring a biomedical signal to be detected in an exemplary embodiment of the present disclosure; Figure 4 A schematic diagram showing a model structure of a pre-trained abnormal discharge detection model in an exemplary embodiment of the present disclosure; Figure 5A schematic flow chart showing a method for performing first abnormal discharge detection in an exemplary embodiment of the present disclosure; Figure 6 A schematic flow chart showing a method for performing second abnormal discharge detection in an exemplary embodiment of the present disclosure; Figure 7 A schematic flow chart showing a method for obtaining abnormal discharge detection results of a tested object in an exemplary embodiment of the present disclosure; Figure 8 A schematic diagram showing the composition of an abnormal discharge detection device in an exemplary embodiment of the present disclosure; Fig. 9 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown.

[0020] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0021] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0022] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, medium, method or computer program product. Therefore, the present invention may be implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0023] According to an embodiment of the present invention, an abnormal discharge detection method, an abnormal discharge detection device, a computer-readable storage medium, a computer program product, and an electronic device are provided.

[0024] In this document, any number of elements in the drawings is used for illustration rather than limitation, and any naming is used only for distinction and does not have any limiting meaning.

[0025] The principle and spirit of the present invention are described in detail below with reference to several representative embodiments of the present invention. SUMMARY OF THE INVENTION

[0027] The inventors of the present disclosure have found that the abnormal discharge detection method in the related art has the problem of low accuracy and reliability in detecting abnormal discharge of biomedical signals such as EEG.

[0028] In view of the above content, the basic idea of ​​the present disclosure is to provide an abnormal discharge detection method, an abnormal discharge detection device, a computer-readable storage medium, a computer program product and an electronic device, perform a first abnormal discharge detection on the original biomedical signal to be detected through a first abnormal discharge detection sub-model, and perform a second abnormal discharge detection on the image-like biomedical signal data corresponding to the original biomedical signal to be detected through a second abnormal discharge detection sub-model, and then, fuse the detection conditions of the first discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result. On the one hand, the present invention can retain the time information in the original biomedical signal to be detected by performing abnormal discharge detection on the original biomedical signal to be detected. By performing abnormal discharge detection on the image-like biomedical signal data, the feature extraction advantage of the neural network can be brought into play in the image-like biomedical signal data to extract deeper biomedical signal features. The combination of the two can not only retain the time information of the biomedical signal to be detected, but also extract richer biomedical signal features, which can improve the accuracy and reliability of abnormal discharge detection of the biomedical signal to be detected; on the other hand, the abnormal discharge detection result obtained according to the method of the present invention can provide doctors with more accurate reference information, so that doctors do not need to observe all the data in detail, but only need to roughly browse some key information, and then combine the abnormal discharge detection result to quickly and accurately determine the diagnosis result of the patient, saving the workload of the doctor and facilitating wide application in clinical practice; on the other hand, the present invention can realize automatic detection and recognition of abnormal discharge of biomedical signals based on the abnormal discharge detection model, thereby improving the efficiency of abnormal discharge detection.

[0029] After introducing the basic principles of the present invention, various non-limiting embodiments of the present invention are described in detail below.

[0030] Application Scenario Overview It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present invention, and the embodiments of the present invention are not limited in this respect. On the contrary, the embodiments of the present invention can be applied to any applicable scenario.

[0031] The embodiments of the present disclosure can be applied to the abnormal discharge detection scenario of the human brain. For example, when the patient feels discomfort in the head, such as headache, the brain electrical signal of the patient can be collected, and then the collected original brain electrical signal can be converted into the corresponding image-like brain electrical signal, and the original brain electrical signal is input into the first abnormal discharge detection sub-model, and the image-like brain electrical signal is input into the second abnormal discharge detection sub-model, and the first abnormal discharge detection result and the second abnormal discharge detection result are respectively obtained. Then, the first abnormal discharge detection result and the second abnormal discharge detection result are fused, and the abnormal discharge detection result of the patient's brain is obtained according to the fusion result. The abnormal discharge detection result of the patient can be fed back to the doctor, such as sending the abnormal discharge detection result and the corresponding patient identification to the client logged in by the doctor, so as to assist the doctor to make a clinical diagnosis of the patient quickly and accurately according to the abnormal discharge detection result combined with other key indicator data, reduce the workload of the doctor, and improve the work efficiency of the doctor.

[0032] Exemplary System Architecture First, refer to Figure 1 The system architecture of an exemplary application environment of the present disclosure is described.

[0033] like Figure 1 As shown, the system architecture 100 may include a terminal device 110 and a server 120. The terminal device 110 may be a terminal device such as a smart phone, a tablet computer, a desktop computer, a laptop computer, a smart wearable device, etc. The server 120 generally refers to a background system that provides services related to the abnormal discharge detection method in this exemplary embodiment, and may be a server or a cluster formed by multiple servers. The terminal device 110 and the server 120 may be connected via a wired or wireless communication link to exchange data.

[0034] In an exemplary embodiment, the above abnormal discharge detection method can be performed by the server 120. Accordingly, the abnormal discharge detection device can be set in the server 120 to realize the corresponding module function. For example, the biomedical signal of the subject is collected by the electroencephalogram machine, and the collected biomedical signal is sent to the server 120. The server 120 performs segmentation processing on the received biomedical signal to obtain the biomedical signal to be detected, copies the biomedical signal to be detected, and transforms the copied biomedical signal to be detected to obtain image-like biomedical signal data. Then, the biomedical signal to be detected is input into the first abnormal discharge detection sub-model, and the image-like biomedical signal data is input into the second abnormal discharge detection sub-model. The first abnormal discharge detection result is obtained according to the first abnormal discharge detection sub-model, and the second abnormal discharge detection result is obtained according to the output of the second abnormal discharge detection sub-model. The first abnormal discharge detection result and the second abnormal discharge detection result are fused to obtain the final abnormal discharge detection result. The server 120 can send the final abnormal discharge detection result to the terminal device 110, and display the final abnormal discharge detection result in the graphical user interface of the terminal device 110.

[0035] In another exemplary embodiment, the abnormal discharge detection method described above can also be performed by the terminal device 110. Accordingly, the abnormal discharge detection device can be set in the terminal device 110 to implement the corresponding module functions. For example, the user uploads the collected biomedical signal of the object under test to the terminal device 110, and the terminal device 110 first segments the collected biomedical signal according to the pre-configured algorithm logic to obtain the biomedical signal to be detected, and then copies the biomedical signal to be detected, and performs a form transformation on the copied biomedical signal to be detected to obtain image-like biomedical signal data, and then, the biomedical signal to be detected is input into the first abnormal discharge detection sub-model pre-configured in the terminal device 110, and the image-like biomedical signal data is input into the second abnormal discharge detection sub-model pre-configured in the terminal device 110, and the first discharge detection result is obtained according to the output of the first abnormal discharge detection sub-model, and the second abnormal discharge detection result is obtained according to the output of the second abnormal discharge detection sub-model, and the terminal device 110 can fuse the first abnormal discharge detection result and the second abnormal discharge detection result according to the pre-configured algorithm, and obtain the abnormal discharge detection result of the object under test according to the fusion result.

[0036] It should be understood that Figure 1The number of terminal devices and servers in the example is only illustrative. Any number of terminal devices and servers may be provided as required. For example, the server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0037] It is easy for those skilled in the art to understand that the above application scenarios are only used as examples and are not limited to the present exemplary embodiment.

[0038] Exemplary Methods Figure 2 A flow chart showing an abnormal discharge detection method in an exemplary embodiment of the present disclosure is shown. Figure 2 , the method comprising: Step S210, determining a biomedical signal to be detected of the subject, inputting the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model; Step S220, transforming the biomedical signal to be detected of the subject to be detected to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; Step S230, inputting the image-like biomedical signal data into a second abnormal discharge detection submodel in a pre-trained abnormal discharge detection model, and performing a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection submodel; Step S240: integrating the detection results of the first abnormal discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result of the detected object.

[0039] Below, first, the specific implementation method of "step S210, determining a biomedical signal to be detected of the subject, inputting the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model" is described in detail.

[0040] In an exemplary embodiment, the biomedical signal is an active signal spontaneously generated by the physiological process of a living body, which can more accurately reflect the physiological state or physical state of a person. Therefore, the biomedical signal can be used to determine whether the living body is abnormal. The living body in the present disclosure may include any living body, such as a human body, an animal body, etc., and this exemplary embodiment does not specifically limit this.

[0041] Exemplarily, the above-mentioned biomedical signals may include any one or more of the following: physiological signals such as electrocardiogram signals, electroencephalogram signals, electromyography signals, electrooculography signals and electrogastric signals, or may also include non-electrical signals such as body temperature, blood pressure, pulse, respiration, etc., which can be set according to actual conditions, and the present disclosure does not make any special limitations on this.

[0042] Among them, the ECG signal can be an electrocardiogram collected by a multi-channel electrocardiogram machine. An electrocardiogram (ECG) refers to a graph of various forms of potential changes drawn from the body surface by an electrocardiograph during each cardiac cycle, with the pacemaker, atrium, and ventricle being excited successively, accompanied by changes in the electrocardiogram bioelectricity. The electrocardiogram is an objective indicator of the occurrence, propagation, and recovery process of cardiac excitement.

[0043] EEG signals can be electroencephalograms collected by multi-channel electroencephalogram machines. Electroencephalograms (EEGs) are graphs obtained by amplifying and recording the spontaneous bioelectric potential of the cerebral cortex from the scalp through sophisticated instruments. They are spontaneous and rhythmic electrical activities of brain cell groups recorded by electrodes. This electrical activity is a plane diagram of the relationship between the potential and time, with the potential as the vertical axis and time as the horizontal axis. The frequency (period), amplitude and phase of brain waves constitute the basic characteristics of EEGs.

[0044] Electromyography (EMG) is the temporal and spatial superposition of action potentials of motor units in numerous muscle fibers, which can be obtained by sticking electromyography sensors on the skin.

[0045] Electrooculogram (EOG) is a bioelectric signal caused by the potential difference between the cornea and retina of the eye. It is very easy to collect and can be completed with a small number of electrodes.

[0046] Electrogastrogram (EGG) is an electrical signal generated by the contraction of stomach muscles, which can be collected on the surface of the abdominal skin using electrodes.

[0047] In an optional embodiment, the subjects may include patients who seek medical treatment for epilepsy or epilepsy-like symptoms, and the subjects may also include people who seek medical treatment for other brain discomfort, such as people with brain pain, etc. This exemplary embodiment does not specifically limit this.

[0048] For example, Figure 3 A schematic diagram of a method for acquiring a biomedical signal to be detected in an exemplary embodiment of the present disclosure is shown. Figure 3 , the method may include steps S310 to S320. Wherein: In step S310, the collected biomedical signals of the subject are acquired.

[0049] For example, for each subject, a long-term biomedical signal can be collected, such as a 10-minute biomedical signal. Since abnormal discharge is not continuous, the biomedical signal of the subject can be processed in segments to obtain the biomedical signal to be detected, and whether the subject has abnormal discharge can be determined based on the biomedical signal to be detected, thereby improving the efficiency and accuracy of abnormal discharge detection.

[0050] In step S320, biomedical signals of the subject are acquired in segments according to preset time lengths, and at least one biomedical signal to be detected of the subject is determined.

[0051] Taking the preset time length of 4 seconds as an example, the biomedical signal collected in step S210 can be segmented into 4-second units, and each 4-second segmented signal is used as a biomedical signal to be detected. In this way, 15 biomedical signals to be detected can be obtained in 1 minute, and 150 biomedical signals to be detected can be obtained in 10 minutes.

[0052] In another exemplary embodiment, the biomedical signal collected by the biomedical signal device can also be directly used as the biomedical signal to be detected without segmenting it. For example, the biomedical signal for 1 minute can be directly collected as needed and the biomedical signal collected for 1 minute can be used as the biomedical signal to be detected. This exemplary embodiment does not make any special limitation on this.

[0053] For example, the biomedical signal acquisition equipment directly acquires the biomedical signal digital sequence. For example, a multi-channel electrocardiograph, a multi-channel electroencephalogram, or a multi-channel electromyogram can be used to acquire the corresponding biomedical signal at a preset acquisition frequency, such as 500 Hz, and the obtained biomedical signal numerical sequence is obtained.

[0054] Taking EEG signals as an example, the EEG signals collected by an EEG machine can be a sequence of EEG signal values ​​as shown in the following formula (1).

[0055] x_t=(x_t1,x_t2,x_t3,x_t4,…,x_tn) (1) In formula (1), x_t is the EEG signal numerical sequence. x_t1, x_t2, x_t3, x_t4, …, x_tn represent the signal values ​​of the EEG signal at different sampling times. For example, x_t1 represents the signal value at the first sampling time in the EEG signal numerical sequence x_t, and x_tn represents the signal value at the nth sampling time in the EEG signal numerical sequence x_t.

[0056] From formula (1), it can be seen that the original biomedical signal collected by the biomedical signal can be regarded as a one-dimensional or multi-dimensional long matrix. For example, if the number of channels of the multi-channel EEG signal is 29 and the signal is sampled 2000 times in 4 seconds, the biomedical signal to be detected is a 29-by-2000-dimensional long matrix. The abnormal discharge detection model is usually a neural network model. The neural network model, especially the convolutional neural network, has a natural processing advantage for image signals. When processing image signals, it can extract deeper feature expressions of image signals. Most image signals are multi-row and multi-column matrices with basically the same or similar number of rows and columns, such as 256 by 256, 512 by 512, etc. In other words, the original biomedical signal is similar to a rectangular input, while the image signal is similar to a square input. The two are quite different in form, which makes it impossible for neural networks, especially convolutional neural networks, to fully utilize the advantages of feature extraction in abnormal discharge detection.

[0057] That is to say, only when the form of the biomedical signal input to the abnormal discharge detection model is similar to that of the image signal, can the advantages of neural networks, especially convolutional neural networks, in feature extraction be fully applied to the field of abnormal discharge detection, extract deeper biomedical signal features, and improve the accuracy of biomedical signal detection.

[0058] However, biomedical signals are related to time. As mentioned above, they are time series. When they are converted into image signals, the time information will be lost. However, the time information is also an important feature for abnormal discharge detection.

[0059] Based on this, in the present disclosure, the original biomedical signal to be detected is processed by the first abnormal discharge detection sub-model to perform the first abnormal discharge detection. In this way, the time information of the biomedical signal to be detected is retained in the first abnormal discharge detection. At the same time, the image-like biomedical signal data is processed by the second abnormal discharge detection sub-model, so as to extract deeper biomedical signal features by utilizing the natural advantages of the neural network model in image data processing, and perform the second abnormal discharge detection. Then, the first abnormal discharge detection situation and the second abnormal discharge detection situation are fused to obtain the abnormal discharge detection result of the object under test. Obviously, the fusion result not only retains the time information of the biomedical signal to be detected, but also obtains richer and deeper biomedical signal features through the image-like biomedical signal data, thereby improving the accuracy and reliability of abnormal discharge detection of biomedical signals.

[0060] In an exemplary embodiment, the pre-trained abnormal discharge detection model includes a first abnormal discharge detection sub-model and a second abnormal discharge detection sub-model, wherein the first abnormal discharge detection sub-model is used to process the original biomedical signal, and the second abnormal discharge detection sub-model is used to process the image-like biomedical signal corresponding to the original biomedical signal.

[0061] For example, biomedical signals can be collected from the bodies of different subjects, and then doctors can annotate the collected biomedical signals to see if there is abnormal discharge, thereby obtaining a labeled training data set. An initial abnormal discharge detection model is trained in a supervised manner based on the labeled training data set. For example, based on the binary cross entropy loss between the prediction results of the initial abnormal discharge detection model and the labels, iterative training is performed in the direction of reducing the binary cross entropy loss, and model parameters are updated. When the binary cross entropy loss is less than a preset value or the number of iterations reaches a certain threshold, the training is stopped, thereby obtaining a pre-trained abnormal discharge detection model.

[0062] Among them, the initial abnormal discharge detection model includes an initial first abnormal discharge detection sub-model and an initial second abnormal discharge detection sub-model, the input of the initial first abnormal discharge detection sub-model is the original biomedical signal in the training data set, and the output is the first abnormal discharge detection result, the input of the initial second abnormal discharge detection sub-model is the image-like biomedical data corresponding to the original biomedical signal in the training data set, and the output is the second abnormal discharge detection result, and the output of the initial abnormal discharge detection model is the fusion result of the first abnormal discharge detection result and the second abnormal discharge detection result. In this way, the final pre-trained abnormal discharge detection model includes the first abnormal discharge detection sub-model and the second abnormal discharge detection sub-model.

[0063] In an exemplary embodiment, the pre-trained abnormal discharge detection model is determined according to a convolutional neural network. For example, the first abnormal discharge detection sub-model includes a first convolutional neural network, and the second abnormal discharge detection sub-model includes a second convolutional neural network.

[0064] For example, the model structure of the pre-trained abnormal discharge detection model in the present disclosure can be as follows: Figure 4 Reference Figure 4 , the pre-trained abnormal discharge detection model includes a first abnormal discharge detection sub-model 41 and a second abnormal discharge detection sub-model 42. Among them, the first abnormal discharge detection sub-model 41 may include a first multi-head attention sub-model 411, a first deep convolutional neural network sub-model 412, a first fully connected layer 413 and a first activation layer 414. The second abnormal discharge detection sub-model 42 may include a second deep convolutional neural network sub-model 421, a second fully connected layer 422 and a second activation layer 423. Among them, the first activation layer and the second activation layer can both be preset activation functions.

[0065] For example, Figure 5 A schematic flow chart of a method for performing first abnormal discharge detection in an exemplary embodiment of the present disclosure is shown. Figure 5 , the method may include steps S510 to S540. Wherein: In step S510, the biomedical signal to be detected is input into the first multi-head attention sub-model, and the first feature of the biomedical signal to be detected is obtained according to the output of the first multi-head attention sub-model.

[0066] In an exemplary embodiment, the QKV of the first multi-head attention sub-model is the same, that is, they are all original signals of the biomedical signal to be detected. Q, K, and V correspond to the query, key, and value matrices in the multi-head attention model, respectively.

[0067] The specific structure of the first multi-head attention sub-model in the present disclosure can refer to the structure of the existing multi-head attention model in the field of natural language processing, and will not be repeated here.

[0068] After the original signal of the biomedical signal to be detected passes through the first multi-head attention sub-model, the time information characteristics of the biomedical signal to be detected can be extracted through the first multi-head attention sub-model. However, the first feature output by the first multi-head attention sub-model is a shallow biomedical signal understanding feature. This shallow biomedical signal feature cannot represent the deeper signal meaning of the biomedical signal. Therefore, in the present disclosure, inspired by the field of computer vision, the shallow features are input into the deep convolutional neural network again to extract deeper features of the biomedical signal, thereby improving the accuracy of abnormal discharge detection.

[0069] In step S520, the first feature is input into the first deep convolutional neural network sub-model, and the second feature is obtained according to the output of the first deep convolutional neural network sub-model.

[0070] In an exemplary embodiment, the first deep convolutional neural network sub-model may include any one of a first deep dilated convolutional network sub-model and a first multi-level convolutional neural network sub-model.

[0071] In the case where the first deep convolutional neural network submodel is the first deep expanded convolutional network submodel, since the original biomedical signal, such as the above-mentioned 29 times 2000 EEG signal, is not very sensitive to convolution, the convolution expansion rate of each layer in the first deep expanded convolutional network submodel can be the same, such as all 1, that is, the first deep expanded convolutional network submodel can be an ordinary multi-layer convolutional neural network submodel, so that the processing efficiency of the model can be improved while ensuring the processing effect. Of course, the expansion rate of each layer of the first deep expanded convolutional network submodel can also be different, such as the first deep expanded convolutional network submodel and the second deep expanded convolutional network submodel described below have the same model structure, and this exemplary embodiment does not make any special limitations on this.

[0072] The number of layers of the first deep dilated convolutional network sub-model and the dilation rate of each layer can be determined according to requirements or experimental results. For example, experimental results show that when the number of layers is 3 and the dilation rate of each layer is 1, the training result is best. In this case, the number of layers of the first deep dilated convolutional network sub-model can be 3, and the dilation rate of each layer can be 1.

[0073] In the case where the first deep convolutional neural network submodel is a first multi-level convolutional neural network submodel, the convolution kernels of each layer of the first multi-level convolutional neural network submodel may be the same, but the number of convolution kernels of each layer is different. The convolution kernels of each layer of the first multi-level convolutional neural network submodel may also be different, and this exemplary embodiment does not specifically limit this.

[0074] In step S530, the second feature is input into the first fully connected layer, and the first fully connected feature is obtained according to the output of the first fully connected layer.

[0075] For example, the second feature may be input into the first fully connected layer, and the second feature may be subjected to dimensionality reduction processing by the first fully connected layer to obtain a feature after dimensionality reduction.

[0076] In step S540, the first fully connected feature is processed by a preset activation function, and a first abnormal discharge detection result of the biomedical signal to be detected is obtained according to the processing result.

[0077] In an exemplary implementation, the preset activation function may include a binary activation function, such as a sigmoid activation function. Of course, the preset activation function may also include a multi-classification activation function, such as a softmax activation function.

[0078] Taking the binary classification activation function as an example, the above-mentioned reduced-dimensional features can be mapped through the binary classification activation function, and the reduced-dimensional features are mapped to probability values ​​between 0 and 1 to obtain a first abnormal probability value, and the first abnormal probability value is used as the first abnormal discharge detection result.

[0079] Of course, the first multi-head attention sub-model may not be used, such as directly inputting the original biomedical signal to be detected into the first deep convolutional neural network sub-model, and performing the first abnormal discharge detection according to the first deep convolutional neural network sub-model. For example, the original biomedical signal to be detected is first input into the first deep convolutional neural network sub-model to obtain output 1, and then the output 1 is input into the first fully connected layer to obtain output 2, and then the output 2 is input into the preset activation function, and the first abnormal probability value is obtained according to the output of the preset activation function.

[0080] The deep convolutional neural network sub-model in the present disclosure may also be other convolutional neural network structures, and this exemplary embodiment does not specifically limit this.

[0081] Through the above steps S510 to S540, the first abnormal discharge detection sub-model can be used to perform abnormal discharge detection on the original biomedical signal to be detected to obtain a first abnormal discharge detection result.

[0082] The specific implementation of "step S220, transforming the form of the biomedical signal to be detected of the subject to be detected to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected" is described in detail below.

[0083] In an exemplary embodiment, the biomedical signal to be detected includes a first matrix, and the first matrix corresponds to a first matrix dimension. In other words, the biomedical signal to be detected can be represented by the first matrix, and the first matrix can be a matrix of N rows and M columns, such as the above-mentioned matrix of 29 rows and 2000 columns. N represents the number of channels of the biomedical signal, and 2000 represents the number of samples of each channel of the biomedical signal to be detected.

[0084] Based on this, exemplarily, an implementation of step S220 may include: performing matrix deformation on the first matrix to obtain a second matrix, the second matrix corresponds to a second matrix dimension, and the difference between the number of rows and the number of columns of the second matrix dimension is less than a preset value; and determining image-like biomedical signal data based on the second matrix.

[0085] For example, a matrix transformation function, such as a reshape function, can be used to transform a first matrix into a second matrix of K rows and L columns, wherein the absolute value of the difference between K and L is less than a preset value, and the preset value can be customized according to the needs, such as 0, 50, 100, etc. The preset value cannot be set too large, otherwise the difference between the form of the transformed matrix and the image data matrix will still be large. The purpose of setting the preset value is to make the transformed matrix more suitable for convolution operations. For example, the above-mentioned first matrix of 29 times 2000 is transformed into a second matrix of 290 times 200. In this way, it can be ensured that the form of the second matrix is ​​similar to that of the image signal, and the second matrix is ​​used as the image-like biomedical signal data of the biomedical signal to be detected.

[0086] It should be noted that in the process of converting from the first matrix to the second matrix, only the row and column dimensions of the matrix change, while the elements in the matrix do not change at all.

[0087] Below, the specific implementation method of "step S230, inputting the image-like biomedical signal data into the second abnormal discharge detection sub-model in the pre-trained abnormal discharge detection model, and performing a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection sub-model" is described in detail.

[0088] In an exemplary embodiment, as described above Figure 4 As shown, the second abnormal discharge detection submodel includes a second deep convolutional neural network submodel and a second fully connected layer.

[0089] Next, combine Figure 6 The specific implementation of step S230 is described. For example, Figure 6 A flow chart showing a method for performing a second abnormal discharge detection in an exemplary embodiment of the present disclosure is shown. Figure 6, the method may include steps S610 to S630. Wherein: In step S610, the image-like biomedical signal data is input into the second deep convolutional neural network sub-model, and the third feature is obtained according to the output of the second deep convolutional neural network sub-model.

[0090] In an exemplary embodiment, the second deep convolutional neural network sub-model may include a second deep dilated convolutional network sub-model and a second deep multi-level convolutional neural network sub-model.

[0091] In the case where the second deep convolutional neural network sub-model is a second deep dilated convolutional network sub-model, the second deep dilated convolutional network sub-model may be a multi-layer dilated convolutional neural network with different dilation rates for each layer, such as a 3-layer dilated convolutional network with dilation rates of 1, 2, and 3. In this way, through the second deep dilated convolutional network sub-model, deep feature extraction can be performed on image-like biomedical signal data to obtain richer biomedical signal features.

[0092] In the case where the second deep convolutional neural network sub-model is a second multi-level convolutional neural network sub-model, the convolution kernels of each layer of the second multi-level convolutional neural network sub-model may be different, such as the first layer includes three convolution kernels 1, the second layer includes two convolution kernels 2, and the third layer includes one convolution kernel 3, wherein convolution kernel 1, convolution kernel 2 and convolution kernel 3 are different, and this exemplary embodiment does not make any special limitation on this.

[0093] In step S620, the third feature is input into the second fully connected layer, and the second fully connected feature is obtained according to the output of the second fully connected layer.

[0094] For example, the third feature can be input into the second fully connected layer, and the third feature can be reduced in dimension by the second fully connected layer to obtain the feature after dimension reduction, that is, the second fully connected feature.

[0095] In step S630, the second fully connected feature is processed by a preset activation function, and a second abnormal discharge detection result of the biomedical signal to be detected is obtained according to the processing result.

[0096] Exemplarily, the preset activation function in step S630 and the preset activation function in step S540 may be the same. Continuing with the binary classification activation function as an example, the reduced-dimensional features obtained in the above step S620 may be mapped by the binary classification activation function, and the reduced-dimensional features may be mapped to probability values ​​between 0 and 1 to obtain a second abnormal probability value, and the second abnormal probability value may be used as the second abnormal discharge detection result.

[0097] For example, the image-like biomedical signal data is first input into the second deep convolutional neural network sub-model to obtain output 11, and then the output 11 is input into the second fully connected layer to obtain output 21, and then the output 21 is input into the preset activation function, and the second abnormality probability value is obtained according to the output of the preset activation function.

[0098] Through the above steps S610 to S630, abnormal discharge detection can be performed on the image-like biomedical signal data corresponding to the original biomedical signal to be detected by the second abnormal discharge detection sub-model to obtain a second abnormal discharge detection result.

[0099] The specific implementation of "step S240, integrating the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain the abnormal discharge detection result of the detected object" is described in detail below.

[0100] Exemplary, combined Figure 7 An exemplary implementation of step S240 is described. Figure 7 A flow chart showing a method for obtaining abnormal discharge detection results of a tested object in an exemplary embodiment of the present disclosure is shown. Figure 7 The method may include steps S710 to S730. Wherein: In step S710, the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection are integrated to obtain the abnormal discharge detection result of the biomedical signal to be detected.

[0101] For example, the first abnormal discharge detection result and the second abnormal discharge detection result may be combined, such as Figure 4 As shown, the first abnormal probability value and the second abnormal probability value mentioned above can be fused to obtain a fused probability value. When the fused probability value is greater than or equal to the probability threshold, it is determined that abnormal discharge exists in the biomedical signal to be detected. Otherwise, it is determined that abnormal discharge does not exist in the biomedical signal to be detected, thereby obtaining an abnormal discharge detection result of the biomedical signal to be detected.

[0102] Exemplarily, the first abnormal discharge detection and the second abnormal discharge detection may also include: fusing the output features of the first fully connected layer and the output features of the second fully connected layer to obtain a fused fully connected feature, and then inputting the fused fully connected feature into a preset activation function, and obtaining the abnormal discharge detection result of the biomedical signal to be detected according to the probability value output by the preset activation function. If the probability value is greater than or equal to the probability threshold, it is determined that an abnormal discharge exists; otherwise, it is determined that an abnormal discharge does not exist.

[0103] Of course, the second feature and the third feature mentioned above can also be fused to obtain a fused feature, and then the fused feature is reduced in dimension through a fully connected layer to obtain the reduced fused feature, and the reduced fused feature is input into a preset activation function. The abnormal discharge detection result of the biomedical signal to be detected is obtained according to the probability value output by the preset activation function. If the probability value is greater than or equal to the probability threshold, it is determined that abnormal discharge exists; otherwise, it is determined that abnormal discharge does not exist.

[0104] In step S720, when the abnormal discharge detection result of the biomedical signal to be detected is abnormal discharge, the biomedical signal to be detected is marked.

[0105] For example, when there is abnormal discharge in the biomedical signal to be detected, an abnormal mark, such as the first mark, can be added to the biomedical signal to be detected. Since the biomedical signal to be detected is acquired in segments, the abnormal mark can be used to locate the time period in which the abnormal discharge occurs in the subject, which is convenient for the doctor to make subsequent diagnosis and confirmation.

[0106] Exemplarily, when the abnormal discharge detection result of the biomedical signal to be detected is normal discharge, no mark may be added to it, or a normal mark, such as the second mark, may be added to it.

[0107] In step S730, the abnormal discharge detection result of the detected object is obtained according to the marked biomedical signal to be detected.

[0108] Exemplarily, the time periods corresponding to the marked biomedical signals to be detected can be summarized to obtain the time periods in which the subject has abnormal discharges, and then the time periods in which the subject has abnormal discharges are used as abnormal discharge detection results and fed back to the client where the doctor is located. The doctor can quickly and accurately locate the time period in which abnormal discharges may exist based on the abnormal discharge detection results, and study the biomedical signal images in the time period in which abnormal discharges may exist to confirm whether abnormal discharges are really occurring. In this way, the doctor does not need to study the entire biomedical signal image as a whole, but only needs to confirm the abnormality of the biomedical signal images in the abnormal time period summarized in the detection results, thereby improving the doctor's work efficiency.

[0109] On the one hand, the present invention can retain the time information in the original biomedical signal to be detected by performing abnormal discharge detection on the original biomedical signal to be detected. By performing abnormal discharge detection on the image-like biomedical signal data, the feature extraction advantage of the neural network can be brought into play in the image-like biomedical signal data to extract deeper biomedical signal features. The combination of the two can not only retain the time information of the biomedical signal to be detected, but also extract richer biomedical signal features, which can improve the accuracy and reliability of abnormal discharge detection of the biomedical signal to be detected; on the other hand, the abnormal discharge detection result obtained according to the method of the present invention can provide doctors with more accurate reference information, so that doctors do not need to observe all the data in detail, but only need to roughly browse some key information, and then combine the abnormal discharge detection result to quickly and accurately determine the diagnosis result of the patient, saving the workload of the doctor and facilitating wide application in clinical practice; on the other hand, the present invention can realize automatic detection and recognition of abnormal discharge of biomedical signals based on the abnormal discharge detection model, thereby improving the efficiency of abnormal discharge detection.

[0110] In addition, it should be noted that the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0111] Exemplary Devices The exemplary embodiment of the present disclosure also provides an abnormal discharge detection device. Figure 8 As shown, the abnormal discharge detection device 800 may include the following program modules: a first detection module 810, configured to determine a biomedical signal to be detected of the detected object, input the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and perform a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model; a signal preprocessing module 820, configured to perform a form transformation on the biomedical signal to be detected of the detected object, and obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; a second detection module 830, configured to input the image-like biomedical signal data into a second abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and perform a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection sub-model; a fusion module 840, configured to fuse the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result of the detected object.

[0112] In an exemplary embodiment, determining the biomedical signals to be detected of the subject includes: acquiring the collected biomedical signals of the subject; acquiring the biomedical signals of the subject in segments according to preset time lengths, and determining at least one biomedical signal to be detected of the subject.

[0113] In an exemplary embodiment, the fusion of the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain the abnormal discharge detection result of the object under test includes: fusing the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain the abnormal discharge detection result of the biomedical signal to be detected; marking the biomedical signal to be detected when the abnormal discharge detection result of the biomedical signal to be detected is abnormal discharge; and obtaining the abnormal discharge detection result of the object under test based on the marked biomedical signal to be detected.

[0114] In an exemplary embodiment, the first abnormal discharge detection submodel includes a first multi-head attention submodel, a first deep convolutional neural network submodel and a first fully connected layer; the biomedical signal to be detected is input into the first abnormal discharge detection submodel in the pre-trained abnormal discharge detection model, and the first abnormal discharge detection is performed on the biomedical signal to be detected according to the first abnormal discharge detection submodel, including: inputting the biomedical signal to be detected into the first multi-head attention submodel, and obtaining a first feature of the biomedical signal to be detected according to the output of the first multi-head attention submodel; inputting the first feature into the first deep convolutional neural network submodel, and obtaining a second feature according to the output of the first deep convolutional neural network submodel; inputting the second feature into the first fully connected layer, and obtaining a first fully connected feature according to the output of the first fully connected layer; processing the first fully connected feature by a preset activation function, and obtaining a first abnormal discharge detection result of the biomedical signal to be detected according to the processing result.

[0115] In an exemplary embodiment, the second abnormal discharge detection submodel includes a second deep convolutional neural network submodel and a second fully connected layer; the image-like biomedical signal data is input into the second abnormal discharge detection submodel in a pre-trained abnormal discharge detection model, and the second abnormal discharge detection is performed on the image-like biomedical signal data according to the second abnormal discharge detection submodel, including: inputting the image-like biomedical signal data into the second deep convolutional neural network submodel, and obtaining a third feature according to the output of the second deep convolutional neural network submodel; inputting the third feature into the second fully connected layer, and obtaining a second fully connected feature according to the output of the second fully connected layer; processing the second fully connected feature by a preset activation function, and obtaining a second abnormal discharge detection result of the biomedical signal to be detected according to the processing result.

[0116] In an exemplary embodiment, the biomedical signal to be detected includes a first matrix, which corresponds to a first matrix dimension. The biomedical signal to be detected of the object under test is transformed in form to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; the first matrix is ​​matrix deformed to obtain a second matrix, which corresponds to a second matrix dimension, and the difference between the number of rows and the number of columns of the second matrix dimension is less than a preset value; and the image-like biomedical signal data is determined according to the second matrix.

[0117] In an exemplary embodiment, any of the deep convolutional neural network sub-models includes any of a deep dilated convolutional network sub-model and a multi-layer convolutional neural network sub-model.

[0118] The specific details of each part of the above-mentioned device have been described in detail in the implementation of the corresponding method part above. The undisclosed details can be found in the implementation of the method part above, and will not be repeated here.

[0119] Exemplary Storage Media The storage medium according to the exemplary embodiment of the present invention is described below.

[0120] In this exemplary embodiment, the above method can be implemented by a program product, such as a portable compact disk read-only memory (CD-ROM) and including program code, and can be run on a device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device.

[0121] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0122] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0123] The program code contained on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RE, etc., or any suitable combination of the foregoing.

[0124] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0125] Exemplary computer program products The exemplary embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the abnormal discharge detection method described above is implemented.

[0126] In one embodiment, the computer program product may be a tangible product containing a computer program, such as a computer-readable storage medium storing a computer program. The readable storage medium may be a storage medium based on electrical, magnetic, optical, electromagnetic, infrared, or other signals, including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), mechanical hard disk (HDD), solid state drive (SSD), and the like. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing a computer program, such as a read-only memory, a NAND flash memory (Nand Flash), and the like.

[0127] In one embodiment, the computer program product may be an intangible product including a computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as a digital file storing an executable file, an installation package, etc. of the computer program.

[0128] The code of the computer program can be written in one or more programming languages. Programming languages ​​such as C language, Java, C++, Python, etc. The program code can be executed completely on the user computing device, or partially on the user computing device, or as a separate software package, or partially on the user computing device and partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through an Internet connection provided by an operator).

[0129] The computer program can be carried or transmitted through electrical, magnetic, optical, electromagnetic, infrared and other signals. The electronic device can convert the signal carrying the computer program into a digital signal, and then run the computer program. When the computer program is run on the electronic device, its code is used to enable the electronic device to execute (more specifically, the processor of the electronic device can execute) the method steps of various exemplary embodiments of the present disclosure, such as the abnormal discharge detection method described above, which includes the following steps: determining the biomedical signal to be detected of the object under test, inputting the biomedical signal to be detected into the first abnormal discharge detection submodel in the pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection submodel; performing a form transformation on the biomedical signal to be detected of the object under test to obtain the image-like biomedical signal data corresponding to the biomedical signal to be detected; inputting the image-like biomedical signal data into the second abnormal discharge detection submodel in the pre-trained abnormal discharge detection model, and performing a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection submodel; fusing the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain the abnormal discharge detection result of the object under test.

[0130] By executing the above method steps through a computer program, on the one hand, by performing abnormal discharge detection on the original biomedical signal to be detected, the time information in the original biomedical signal to be detected can be retained, and by performing abnormal discharge detection on the image-like biomedical signal data, the feature extraction advantage of the neural network can be brought into play in the image-like biomedical signal data, and deeper biomedical signal features can be extracted. The combination of the two can not only retain the time information of the biomedical signal to be detected, but also extract richer biomedical signal features, which can improve the accuracy and reliability of abnormal discharge detection of the biomedical signal to be detected; on the other hand, the abnormal discharge detection result obtained according to the method disclosed in the present invention can provide doctors with more accurate reference information, so that doctors do not need to observe all the data in detail, but only roughly browse some key information, and then combine the abnormal discharge detection result to quickly and accurately determine the diagnosis result of the patient, saving the workload of the doctor and facilitating wide application in clinical practice; on the other hand, based on the abnormal discharge detection model, automatic detection and identification of abnormal discharge of biomedical signals can be realized, and the efficiency of abnormal discharge detection can be improved.

[0131] Exemplary Electronic Devices refer to Fig. 9An electronic device of an exemplary embodiment of the present disclosure is described. The electronic device is the terminal device 110 or the server 120 mentioned above. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the method steps of various exemplary embodiments of the present disclosure by executing the executable instructions. In addition, the electronic device may also include a display for displaying a graphical user interface.

[0132] Reference below Fig. 9 , the electronic device is exemplified in the form of a general-purpose computing device. It should be understood that Fig. 9 The electronic device 900 shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0133] like Fig. 9 As shown, the electronic device 900 may include: a processor 910 , a memory 920 , a bus 930 , an I / O (input / output) interface 940 , a network adapter 950 , and a display 960 .

[0134] The memory 920 may include a volatile memory, such as a RAM 921, a cache unit 922, and may also include a non-volatile memory, such as a ROM 923. The memory 920 may also include one or more program modules 924, such program modules 924 include but are not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or a combination thereof may include the implementation of a network environment. For example, the program module 924 may include each module in the above-mentioned device.

[0135] The processor 910 may include one or more processing units. For example, the processor 910 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor and / or an NPU (Neural-Network Processing Unit), etc.

[0136] The processor 910 can be used to execute executable instructions stored in the memory 920, such as the above-mentioned abnormal discharge detection method, which includes the following steps: determining a biomedical signal to be detected of the object under test, inputting the biomedical signal to be detected into a first abnormal discharge detection submodel in a pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection submodel; performing a form transformation on the biomedical signal to be detected of the object under test to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected; inputting the image-like biomedical signal data into a second abnormal discharge detection submodel in a pre-trained abnormal discharge detection model, and performing a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection submodel; and fusing the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result of the object under test.

[0137] The above method is implemented by a computer program. On the one hand, by performing abnormal discharge detection on the original biomedical signal to be detected, the time information in the original biomedical signal to be detected can be retained. By performing abnormal discharge detection on the image-like biomedical signal data, the feature extraction advantage of the neural network can be brought into play in the image-like biomedical signal data to extract deeper biomedical signal features. The combination of the two not only retains the time information of the biomedical signal to be detected, but also extracts richer biomedical signal features, which can improve the accuracy and reliability of abnormal discharge detection of the biomedical signal to be detected; on the other hand, the abnormal discharge detection result obtained according to the method disclosed in the present invention can provide doctors with more accurate reference information, so that doctors do not need to observe all the data in detail, but only roughly browse some key information, and then combine the abnormal discharge detection result to quickly and accurately determine the diagnosis result of the patient, saving the workload of the doctor and facilitating wide application in clinical practice; on the other hand, based on the abnormal discharge detection model, automatic detection and identification of abnormal discharge of biomedical signals can be realized, thereby improving the efficiency of abnormal discharge detection.

[0138] The bus 930 is used to realize the connection between different components of the electronic device 900, and may include a data bus, an address bus, and a control bus.

[0139] The electronic device 900 can communicate with one or more external devices 1000 (eg, a keyboard, a mouse, an external controller, etc.) through the I / O interface 940 .

[0140] The electronic device 900 can communicate with one or more networks through the network adapter 950. For example, the network adapter 950 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless LAN, Bluetooth, near field communication, etc. The network adapter 950 can communicate with other modules of the electronic device 900 through the bus 930.

[0141] The electronic device 900 may display a graphical user interface, such as a graphical user interface displaying abnormal discharge detection results, through the display 960 .

[0142] although Fig. 9 Not shown, other hardware and / or software modules may also be provided in the electronic device 900, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0143] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0144] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. Those skilled in the art will easily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are indicated by the claims, and any variations, uses or adaptive changes of the present disclosure should be covered, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not disclosed in the present disclosure.

Claims

1. A method for detecting abnormal discharge, characterized in that: include; Determining a biomedical signal to be detected of the subject, inputting the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model; Performing a formal transformation on a first matrix corresponding to the biomedical signal to be detected of the subject to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected, wherein the image-like biomedical signal data corresponds to a second matrix, the first matrix corresponds to a first matrix dimension, the second matrix corresponds to a second matrix dimension, and a difference between the number of rows and the number of columns of the second matrix dimension is less than a preset value; inputting the image-like biomedical signal data into a second abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection sub-model; The detection results of the first abnormal discharge detection and the second abnormal discharge detection are integrated to obtain an abnormal discharge detection result of the detected object.

2. The method according to claim 1, characterized in that Determining the biomedical signal to be detected from the subject includes: Acquiring the collected biomedical signals of the subject; The biomedical signals of the subject are acquired in segments according to a preset time length, and at least one biomedical signal to be detected of the subject is determined.

3. The method according to claim 1 or 2, characterized in that The fusing the detection results of the first abnormal discharge detection and the second abnormal discharge detection to obtain the abnormal discharge detection result of the detected object includes: fusing the detection results of the first abnormal discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result of the biomedical signal to be detected; When the abnormal discharge detection result of the biomedical signal to be detected is abnormal discharge, marking the biomedical signal to be detected; The abnormal discharge detection result of the detected object is obtained according to the marked biomedical signal to be detected.

4. The method according to claim 1, wherein The first abnormal discharge detection sub-model includes a first multi-head attention sub-model, a first deep convolutional neural network sub-model and a first fully connected layer; Inputting the to-be-detected biomedical signal into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a first abnormal discharge detection on the to-be-detected biomedical signal according to the first abnormal discharge detection sub-model, comprises: Inputting the biomedical signal to be detected into the first multi-head attention sub-model, and obtaining a first feature of the biomedical signal to be detected according to an output of the first multi-head attention sub-model; Inputting the first feature into the first deep convolutional neural network sub-model, and obtaining a second feature according to an output of the first deep convolutional neural network sub-model; Inputting the second feature into the first fully connected layer, and obtaining a first fully connected feature according to an output of the first fully connected layer; The first fully connected feature is processed by a preset activation function, and a first abnormal discharge detection result of the biomedical signal to be detected is obtained according to the processing result.

5. The method according to claim 1, characterized in that The second abnormal discharge detection sub-model includes a second deep convolutional neural network sub-model and a second fully connected layer; Inputting the image-like biomedical signal data into a second abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and performing a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection sub-model, comprises: Inputting the image-like biomedical signal data into the second deep convolutional neural network sub-model, and obtaining a third feature according to an output of the second deep convolutional neural network sub-model; Inputting the third feature into the second fully connected layer, and obtaining a second fully connected feature according to the output of the second fully connected layer; The second fully connected feature is processed by a preset activation function, and a second abnormal discharge detection result of the biomedical signal to be detected is obtained according to the processing result.

6. The method according to claim 1, wherein The first abnormal discharge detection result includes a first abnormal probability value, the second abnormal discharge detection result includes a second abnormal probability value, and the abnormal discharge detection result of the detected object obtained by fusing the detection conditions of the first abnormal discharge detection and the second abnormal discharge detection includes: Fusing the first abnormality probability value and the second abnormality probability value to obtain a fused probability value; An abnormal discharge detection result of the detected object is obtained according to the fusion probability value.

7. The method according to claim 4 or 5, characterized in that Any of the deep convolutional neural network sub-models includes any one of a deep dilated convolutional neural network sub-model and a multi-level convolutional neural network sub-model.

8. An abnormal discharge detection device, characterized in that: include; a first detection module configured to determine a biomedical signal to be detected of a subject, input the biomedical signal to be detected into a first abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and perform a first abnormal discharge detection on the biomedical signal to be detected according to the first abnormal discharge detection sub-model; a signal preprocessing module configured to perform a form transformation on a first matrix corresponding to the biomedical signal to be detected of the subject to obtain image-like biomedical signal data corresponding to the biomedical signal to be detected, wherein the image-like biomedical signal data corresponds to a second matrix, the first matrix corresponds to a first matrix dimension, the second matrix corresponds to a second matrix dimension, and a difference between the number of rows and the number of columns of the second matrix dimension is less than a preset value; a second detection module configured to input the image-like biomedical signal data into a second abnormal discharge detection sub-model in a pre-trained abnormal discharge detection model, and perform a second abnormal discharge detection on the image-like biomedical signal data according to the second abnormal discharge detection sub-model; The fusion module is configured to fuse the detection results of the first abnormal discharge detection and the second abnormal discharge detection to obtain an abnormal discharge detection result of the detected object.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, causes the one or more processors to implement the method according to any one of claims 1 to 7.

Images