A method and device for identifying psoriasis case features based on machine vision

Abstract

This invention provides a method and device for machine vision-based psoriasis case feature recognition, belonging to the field of artificial intelligence technology, for accurately identifying psoriasis conditions. The method includes: an electronic device acquiring a skin surface image of a subject, the skin surface image containing the subject's psoriasis-affected area; and performing a three-dimensional surface-and-section fusion analysis of the skin surface image and a preset psoriasis skin cross-section image using a deep neural network model to obtain an analysis result for the subject, which indicates the subject's psoriasis level.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for identifying psoriasis case features based on machine vision. Background Art

[0002] Currently, the diagnosis of psoriasis is still primarily based on clinical observation, relying on the physician's experience and visual judgment. However, psoriasis symptoms are diverse, with different patients exhibiting varying lesion area, morphology, and degree of scaling, making accurate diagnosis difficult. Furthermore, there is a lack of unified standards for assessing the severity of psoriasis. Traditional scoring methods, such as the Psoriasis Area and Severity Index (PASI), often rely on manual measurement, which is time-consuming, labor-intensive, and highly subjective, hindering long-term disease tracking and data analysis.

[0003] With the development of machine vision and deep learning technologies, automated analysis of medical images is becoming increasingly feasible. Image recognition and machine learning technologies have demonstrated significant advantages in assisting the diagnosis of a variety of diseases. For example, they have achieved high accuracy and efficiency in early screening for conditions such as cancer and diabetic retinopathy. The future trend is to incorporate these advanced image processing and analysis methods into the diagnosis of skin diseases, particularly for feature recognition and disease tracking of psoriasis, to enhance the objectivity and standardization of diagnosis.

[0004] Although machine vision and deep learning technologies are widely used in other medical imaging fields, there are still many challenges in the feature recognition of psoriasis: Accuracy and consistency: The morphology of psoriasis lesions is complex and variable, and is greatly affected by skin type, lighting conditions, and lesion location. Traditional image processing methods have difficulty dealing with these interferences, often resulting in insufficient recognition accuracy. Lack of standardized data: The training of deep learning models relies on a large amount of labeled data, but in the field of psoriasis, due to limited labeled data resources and the complexity of psoriasis lesion types, the model's generalization ability is not high and its stability is poor in practical applications. Difficulty in quantitative analysis: Traditional diagnostic methods are mostly qualitative descriptions and lack quantitative indicators. It is difficult for doctors to comprehensively evaluate characteristics such as lesion area and lesion thickness, which hinders the objective tracking of psoriasis disease progression and efficacy.

[0005] Therefore, the current research question is how to achieve accurate psoriasis condition identification through machine vision. Summary of the Invention

[0006] The embodiments of the present invention provide a method and device for identifying psoriasis case features based on machine vision, so as to achieve accurate identification of psoriasis conditions.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, a method for identifying psoriasis case features based on machine vision is provided, which is applied to an electronic device. The method includes: the electronic device obtains a skin surface image of an object, where the skin surface image includes a psoriasis-affected area of ​​the object; the electronic device performs a three-dimensional fusion analysis of the surface and the cross-section of the skin surface image and a preset psoriasis skin cross-section image through a deep neural network model to obtain an analysis result of the object, where the analysis result of the object indicates the psoriasis level of the object.

[0009] Optionally, the electronic device performs a three-dimensional fusion analysis of the surface and the cross-section of the skin surface image and the preset psoriasis skin cross-section image through a deep neural network model to obtain an analysis result of the object, including: the electronic device convolves the skin surface image through the first convolution layer of the deep neural network model to obtain a first feature vector set; the electronic device convolves the psoriasis skin cross-section image through the second convolution layer of the deep neural network model to obtain a second feature vector set; the electronic device fuses the first feature vector set and the second feature vector set through the feature fusion layer of the deep neural network model to obtain a fused feature vector set; the electronic device processes the fused feature vector set through the feature processing layer of the deep neural network model to obtain the analysis result of the object.

[0010] Optionally, the skin surface image includes a first end and a second end of a corresponding pair, and a third end and a fourth end of a corresponding pair, and the electronic device convolves the skin surface image through a first convolution layer of a deep neural network model to obtain a first feature vector set, including: the convolution kernel of the first convolution layer is initially located at the first end of the skin surface image, the electronic device uses the convolution kernel of the first convolution layer to convolve the skin surface image once along the first direction and from the third end to the fourth end of the skin surface image to obtain a feature vector sequence; thereafter, the electronic device steps the convolution kernel along the second direction by a preset step size, and uses the convolution kernel to continue to convolve along the first direction and from the skin surface image The skin surface image is convolved again from the first end to the second end of the image to obtain a feature vector sequence; and so on, until the electronic device steps the convolution kernel along the second direction to the second end, and then uses the convolution kernel to continue to convolve the skin surface image along the first direction and from the first end to the second end of the skin surface image to obtain a feature vector sequence, until the first convolution layer obtains a total of multiple feature vector sequences through convolution, the first feature vector set includes multiple feature vector sequences, and the number of the multiple feature vector sequences is the number of times the convolution kernel steps plus one; wherein the first direction is the direction of the psoriasis skin section, and the second direction is perpendicular to the first direction.

[0011] Optionally, the electronic device fuses the first feature vector set and the second feature vector set through the feature fusion layer of the deep neural network model to obtain a fused feature vector set, including: the electronic device determines, through the feature fusion layer, a partial feature vector sequence in the first feature vector set that can be used for fusion; the electronic device fuses the partial feature vector sequence with the second feature vector set through the feature fusion layer to obtain a fused feature vector set.

[0012] Optionally, the electronic device determines, through the feature fusion layer, a partial feature vector sequence in the first feature vector set that can be used for fusion, including: the second feature vector set includes a continuous feature vector sequence, and the electronic device determines, through the feature fusion layer, a degree of correlation between each of the multiple feature vector sequences and the continuous feature vector sequence; the electronic device determines, through the feature fusion layer, K feature vector sequences with the largest K correlations from the multiple feature vector sequences, the K feature vector sequences are partial feature vector sequences that can be used for fusion, and K is an integer greater than 1; or; the electronic device selects, through the feature fusion layer, a feature vector sequence as a partial feature vector sequence that can be used for fusion at intervals of a preset number of feature vector sequences, and sequentially selects K feature vector sequences that can be used for fusion from the multiple feature vector sequences.

[0013] Optionally, the degree of correlation between any one of the multiple feature vector sequences and the continuous feature vector sequence satisfies the following relationship:

[0014]

[0015] Wherein, μ represents the degree of correlation, l represents any feature vector sequence in multiple feature vector sequences, L represents a continuous feature vector sequence, and α is a preset parameter.

[0016] Optionally, the electronic device fuses part of the feature vector sequence with the second feature vector set through a feature fusion layer to obtain a fused feature vector set, including: for the i-th feature vector sequence in the K feature vector sequences, i is any integer ranging from 1 to K; the electronic device divides the continuous feature vector sequence into M feature vector sequences through the feature fusion layer, where M is an integer greater than 1; the electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in the M feature vector sequences through the feature fusion layer to obtain a fused feature vector sequence, and when i traverses from 1 to K, K fused feature vector sequences are obtained, and the fused feature vector set includes the K fused feature vector sequences;

[0017] Optionally, the electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in M ​​feature vector sequences through a feature fusion layer to obtain a fused feature vector sequence, including: the electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in M ​​feature vector sequences through a feature fusion layer to obtain an initial feature vector sequence; the electronic device adds a connection parameter between the i-th feature vector sequence and each feature vector sequence in the M feature vectors in the initial feature vector sequence through a feature fusion layer to obtain a fused feature vector sequence, and the vector value of the connection parameter is between the i-th feature vector sequence and each feature vector sequence in the M feature vectors.

[0018] Optionally, the method also includes: the electronic device pads the length of each feature vector sequence not used for fusion in the first feature vector set to the same as the fused feature vector sequence through the feature fusion layer, thereby obtaining a padded feature vector sequence, and the fused feature vector set also includes the padded feature vector sequence.

[0019] In a second aspect, a psoriasis case feature recognition device based on machine vision is provided, which is configured as follows: the device obtains a skin surface image of an object, where the skin surface image includes the psoriasis-affected area of ​​the object; the device performs a three-dimensional fusion analysis of the surface and the cross-section of the skin surface image and a preset psoriasis skin cross-section image through a deep neural network model to obtain an analysis result of the object, where the analysis result of the object indicates the psoriasis level of the object.

[0020] The device is specifically configured to perform the functions of the method described in the first aspect above. Please refer to the method described in the first aspect above for specific understanding, and will not be repeated here.

[0021] In a third aspect, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are run on a computer, the computer is caused to execute the method described in the first aspect.

[0022] In a fourth aspect, a computer program product is provided, comprising a computer program or instructions, which, when executed on a computer, causes the computer to execute the method described in the first aspect.

[0023] In summary, the above method and system have the following technical effects:

[0024] When the electronic device obtains a skin surface image of a psoriasis-affected area of ​​an object, the electronic device performs a three-dimensional fusion analysis of the skin surface image and a preset psoriasis skin section image through a deep neural network model, i.e., spatially integrates the surface and depth for analysis, which has better robustness and can obtain an analysis object result that accurately indicates the psoriasis level of the object, i.e., achieves accurate psoriasis condition identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of a process for identifying psoriasis case features based on machine vision provided in an embodiment of the present application;

[0026] Figure 2A 、 Figure 2B 、 Figure 2C and Figure 2D A schematic diagram of a skin surface image in the method for identifying psoriasis case features based on machine vision provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of a deep neural network model in the method for identifying psoriasis case features based on machine vision provided in an embodiment of the present application;

[0028] Figure 4A and Figure 4B A schematic diagram of a psoriasis skin cross-section image in the psoriasis case feature recognition method based on machine vision provided in an embodiment of the present application;

[0029] Figure 5A and Figure 5B A schematic diagram of convolution in the method for identifying psoriasis case features based on machine vision provided in an embodiment of the present application;

[0030] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The present invention will present various aspects, embodiments, or features in the context of systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the figures. Furthermore, combinations of these aspects may also be used.

[0032] In the embodiment of the present invention, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information (such as the first indication information, the second indication information, or the third indication information below) is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, where there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can be achieved by means of the arrangement order of each piece of information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each piece of information can be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0033] In addition, the specific indication method can also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can refer to the existing technology and will not be repeated in this article. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, there may be a situation where the indication methods for different information are different. In the specific implementation process, the required indication method can be selected according to specific needs. The embodiment of the present invention does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present invention should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0034] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending timing of these sub-information can be the same or different. The specific sending method is not limited by the embodiment of the present invention. The sending period and / or sending timing of these sub-information can be predefined, for example, predefined according to a protocol, or can be configured by the transmitting device through sending configuration information to the receiving device.

[0035] "Pre-definition" or "pre-configuration" can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device, and the embodiments of the present invention do not limit the specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, which is not limited by the embodiments of the present invention.

[0036] The "protocol" involved in the embodiments of the present invention may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems, and the embodiments of the present invention do not specifically limit this.

[0037] In the embodiments of the present invention, descriptions such as "when...", "in the case of...", "if", and "if" all mean that the device will perform corresponding processing under certain objective circumstances. They do not limit the time, nor do they require the device to perform judgment actions during implementation, nor do they mean the existence of other limitations.

[0038] In the description of the embodiments of the present invention, unless otherwise specified, " / " indicates that the objects associated with each other are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b and c, or at least one of a, b or c, can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. At the same time, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0039] For example, Figure 1 The present invention provides a flowchart of a method for identifying psoriasis case features based on machine vision. The method can be applied to electronic devices.

[0040] like Figure 1 As shown, the process of the psoriasis case feature recognition method based on machine vision is as follows:

[0041] S101, an electronic device obtains a skin surface image of an object.

[0042] The skin surface image includes the affected area of ​​psoriasis of the subject. The subject may be a patient with psoriasis. The skin surface image may be obtained by photographing the affected area on the skin of the patient with psoriasis using a photographing device (such as a camera). For example, an example of a skin surface image may be as follows: Figure 2A 、 Figure 2B 、 Figure 2C and Figure 2DAs shown, the affected area of ​​psoriasis is usually in the form of blocks or spots. The photographing device can send the photographed skin surface image to the electronic device.

[0043] S102, the electronic device performs a three-dimensional fusion analysis of the skin surface image and the preset psoriasis skin cross-section image through a deep neural network model to obtain an analysis result of the object.

[0044] like Figure 3 As shown, the deep neural network model may include a first convolutional layer, a second convolutional layer, a feature fusion layer and a feature processing layer. The first convolutional layer and the second convolutional layer are connected to the feature fusion layer, and the feature fusion layer is connected to the feature processing layer. The first convolutional layer and the second convolutional layer can be existing convolutional layer structures. The embodiment of the present application does not improve the structure. The difference is that the deep neural network model is dual-channel, that is, the skin surface image and the psoriasis skin cross-section image are input at the same time. The input skin surface image is input to the first convolutional layer for processing, and the psoriasis skin cross-section image is input to the second convolutional layer for processing. The feature fusion layer is used to fuse the features output by the first convolutional layer with the features output by the second convolutional layer. For specific implementation, please refer to the relevant introduction below. The feature processing layer may include a pooling layer, a fully connected layer and an output layer, which can be specifically implemented using existing technologies.

[0045] The psoriasis skin section image can be a preset image, that is, an image preset in the electronic device. The psoriasis skin section image is obtained by photographing a psoriasis skin section through a microscope. The psoriasis skin section can be a sample section, not from the above patient. An example of a psoriasis skin section image can be as follows: Figure 4A and Figure 4B shown.

[0046] On this basis, S102 includes the following steps:

[0047] S1: The electronic device may convolve the skin surface image through the first convolutional layer of the deep neural network model to obtain a first feature vector set.

[0048] like Figure 5A As shown, Figure 2ATaking an image as an example, the skin surface image includes the first and second ends of the corresponding pair, and the third and fourth ends of the corresponding pair. The convolution kernel of the first convolution layer is initially located at the first end of the skin surface image. The electronic device uses the convolution kernel of the first convolution layer to convolve the skin surface image once along the first direction and from the third end to the fourth end of the skin surface image to obtain a feature vector sequence. Afterwards, the electronic device steps the convolution kernel along the second direction by a preset step size, and uses the convolution kernel to continue to convolve the skin surface image along the first direction from the first end to the second end of the skin surface image again to obtain a feature vector sequence; and so on, until the electronic device steps the convolution kernel along the second direction to the second end, and then uses the convolution kernel to continue to convolve the skin surface image along the first direction from the first end to the second end of the skin surface image again to obtain a feature vector sequence, until the first convolution layer obtains a total of multiple feature vector sequences through convolution, and the first feature vector set includes multiple feature vector sequences, and the number of multiple feature vector sequences is the number of times the convolution kernel steps plus one. Wherein, the first direction is the direction of the psoriatic skin section, and the second direction is perpendicular to the first direction. That is to say, if Figure 5B As shown, the convolution kernel can first move from top to bottom for convolution, then step to the left with a preset step size, and then move from top to bottom for convolution until the convolution is completed, that is, it moves to the lower right corner of the image, that is, Figure 5A The position of the convolution kernel when the convolution is completed.

[0049] The above convolution method is to ensure that each feature vector sequence can be convolved with the psoriasis skin section image to obtain a feature vector sequence that is consistent in spatial dimension, that is, the direction of the psoriasis skin section, so that subsequent feature fusion analysis can be performed.

[0050] S2: The electronic device convolves the psoriasis skin section image through the second convolutional layer of the deep neural network model to obtain a second set of feature vectors.

[0051] The above S2 can be implemented using existing technologies without limitation.

[0052] S3: The electronic device fuses the first feature vector set and the second feature vector set through a feature fusion layer of the deep neural network model to obtain a fused feature vector set.

[0053] The electronic device can determine the partial feature vector sequences that can be used for fusion in the first feature vector set through the feature fusion layer. For example, the second feature vector set includes a continuous feature vector sequence, and the electronic device determines the degree of correlation between each of the multiple feature vector sequences and the continuous feature vector sequence through the feature fusion layer. The electronic device determines the K feature vector sequences with the largest correlation from the multiple feature vector sequences through the feature fusion layer, and the K feature vector sequences are partial feature vector sequences that can be used for fusion, where K is an integer greater than 1. Alternatively, the electronic device selects a feature vector sequence as a partial feature vector sequence that can be used for fusion every preset number (such as 1 or 2) of feature vector sequences through the feature fusion layer, and sequentially selects K feature vector sequences that can be used for fusion from the multiple feature vector sequences. In this way, it can be ensured that the K feature vector sequences selected for fusion also include sequences with a high degree of correlation with the continuous feature vector sequence.

[0054] The correlation degree between any one of the multiple feature vector sequences and the continuous feature vector sequence satisfies the following equation (1):

[0055]

[0056] Among them, μ represents the degree of correlation, L represents any feature vector sequence in multiple feature vector sequences, L represents a continuous feature vector sequence, and α is a preset parameter. The specific value can be set according to the actual situation. The setting of α is to avoid distortion of the calculation results.

[0057] The electronic device can fuse some feature vector sequences with the second feature vector set through a feature fusion layer to obtain a fused feature vector set. For example, for the i-th feature vector sequence in K feature vector sequences, i is any integer ranging from 1 to K. The electronic device can use the feature fusion layer to evenly divide the continuous feature vector sequence into M feature vector sequences, where M is an integer greater than 1 and the value of M can be preset. The larger the value of M, the higher the coupling degree of the fused features, the greater the computational overhead, but also the more robust the result. Conversely, the smaller the value of M, the lower the coupling degree of the fused features, the lower the computational overhead, but also the correspondingly lower robustness of the result. M can be reasonably set to 4 or 6 to balance overhead and robustness. The electronic device can use the feature fusion layer to embed the i-th feature vector sequence between every two adjacent feature vector sequences in the M feature vector sequences to obtain a fused feature vector sequence. When i is traversed from 1 to K, K fused feature vector sequences are obtained, and the fused feature vector set includes the K fused feature vector sequences.

[0058] Specifically, the electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in the M feature vector sequences through the feature fusion layer to obtain an initial feature vector sequence; the electronic device adds a connection parameter between the i-th feature vector sequence and each feature vector sequence in the M feature vectors in the initial feature vector sequence through the feature fusion layer to obtain a fused feature vector sequence, and the vector value of the connection parameter (such as including multiple vectors, the values ​​of these multiple vectors) is between the i-th feature vector sequence and each feature vector sequence in the M feature vectors, that is, the value of an endpoint vector of the i-th feature vector sequence gradually approaches the value of an endpoint vector of an adjacent feature vector sequence, which can increase the smoothness of the sequence and thus improve the robustness of the processing.

[0059] The M feature vector sequences include sequence #1 (L1, L2, L3, L4), sequence #2 (L5, L6, L7, L8), and sequence #3 (L9, L10, L11, L12). The i-th feature vector sequence is x1, x2, x3, x4...xN, where N is an integer greater than 4. The fused feature vector sequence is as follows:

[0060] L1,L2,L3,L4,y1,y2,y3,x1,x2,x3,x4...xN,y4,y5,L5,L6,L7,L8,y6,y7,y8,x1,x2,x3,x4...xN,y9,y10,L9,L10,L11,L12.

[0061] Among them, L, y, and x all represent vectors, y1 to y10 are connection parameters, the vector values ​​of y1, y2, and y3 gradually approach the vector value of y1 from the vector value of L4, and the vector values ​​of y4 and y5 gradually approach the vector value of L5 from the vector value of xN. The same applies to the others, which will not be repeated here.

[0062] The method further includes:

[0063] The electronic device uses the feature fusion layer to pad the length of each feature vector sequence not used for fusion in the first feature vector set to the same as the fused feature vector sequence, thereby obtaining a padded feature vector sequence. For example, a 0 vector is added at the end of each feature vector sequence not used for fusion. The fused feature vector set also includes the padded feature vector sequence to ensure format consistency and facilitate subsequent processing.

[0064] S4: The electronic device processes the fused feature vector set through the feature processing layer of the deep neural network model to obtain the analysis result of the object.

[0065] The analysis result of the subject indicates the psoriasis level of the subject, such as 10 levels from mild to severe, and the analysis result may indicate any one of the levels.

[0066] It can be understood that the above is the application process of the model. For the training process, the difference between the analysis result of the object and the actual level of the object can be used to regress the feature processing layer until the model converges.

[0067] In summary, when the electronic device obtains a skin surface image of the psoriasis-affected area of ​​the object, the electronic device performs a three-dimensional fusion analysis of the surface and section of the skin surface image and the preset psoriasis skin section image through a deep neural network model, that is, spatially integrating the surface and depth for analysis, which has better robustness and can obtain an analysis object result that accurately indicates the psoriasis level of the object, thereby achieving accurate psoriasis condition identification.

[0068] The above description, combined with FIG2 , details a psoriasis case feature identification method based on machine vision provided by an embodiment of the present invention. The following details a psoriasis case feature identification device based on machine vision provided by an embodiment of the present invention. The device is configured to: acquire a skin surface image of a subject, the skin surface image including the subject's psoriasis-affected area; and perform a three-dimensional surface and cross-section fusion analysis of the skin surface image and a preset psoriasis skin cross-section image using a deep neural network model to obtain an analysis result of the subject, which indicates the subject's psoriasis level.

[0069] The device is specifically configured to perform the above Figure 1 The function of the method shown is specifically referred to above Figure 1 The method shown in the figure can be understood and will not be described in detail here.

[0070] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. For example, the electronic device may be a terminal device, or a chip (system) or other component or assembly that can be set in the terminal device. Figure 6 As shown, electronic device 400 may include a processor 401. Optionally, electronic device 400 may further include a memory 402 and / or a transceiver 403. Processor 401 is coupled to memory 402 and transceiver 403, for example, via a communication bus. Furthermore, electronic device 400 may be a chip, such as one including processor 401. In this case, the transceiver may be the chip's input / output interface.

[0071] The following combination Figure 6 The components of the electronic device 400 are described in detail below:

[0072] The processor 401 is the control center of the electronic device 400 and can be a single processor or a collective term for multiple processing elements. For example, the processor 401 can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement an embodiment of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0073] Optionally, the processor 401 can execute various functions of the electronic device 400 by running or executing software programs stored in the memory 402 and calling data stored in the memory 402, such as executing the dynamic update method of the radar control software shown in Figure 2 above.

[0074] In a specific implementation, as an embodiment, the processor 401 may include one or more CPUs, such as Figure 6 CPU0 and CPU1 are shown in FIG.

[0075] In a specific implementation, as an embodiment, the electronic device 400 may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer programs or instructions).

[0076] The memory 402 is used to store the software program for executing the solution of the present invention, and is controlled by the processor 401 to execute the software program. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0077] Alternatively, the memory 402 may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store 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 may be integrated with the processor 401 or exist independently and accessed through the interface circuit ( Figure 6 (not shown) is coupled to the processor 401, which is not specifically limited in this embodiment of the present invention.

[0078] Transceiver 403 is used for communication with other electronic devices. For example, if electronic device 400 is a terminal device, transceiver 403 can be used to communicate with a network device or another terminal device. For another example, if electronic device 400 is a network device, transceiver 403 can be used to communicate with a terminal device or another network device.

[0079] Optionally, the transceiver 403 may include a receiver and a transmitter ( Figure 6 (not shown separately in the figure). The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0080] Optionally, the transceiver 403 may be integrated with the processor 401 or may exist independently and communicate with the electronic device 400 through an interface circuit ( Figure 6 (not shown) is coupled to the processor 401, which is not specifically limited in this embodiment of the present invention.

[0081] It is understandable that Figure 6 The structure of the electronic device 400 shown in the figure does not constitute a limitation on the electronic device. The actual electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0082] In addition, the technical effects of the electronic device 400 can refer to the technical effects of the methods described in the above method embodiments, and will not be repeated here.

[0083] It should be understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0084] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0085] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired connection (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0086] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0087] In this disclosure, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0088] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0089] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0090] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0092] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0093] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0094] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0095] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for identifying features of psoriasis cases based on machine vision, characterized in that: Applied to electronic equipment, the method includes: The electronic device acquires a skin surface image of the subject, wherein the skin surface image includes a psoriasis affected area of ​​the subject; The electronic device performs a three-dimensional fusion analysis of the skin surface image and the preset psoriasis skin section image using a deep neural network model to obtain an analysis result of the object, wherein the analysis result of the object indicates the psoriasis level of the object; The electronic device performs a three-dimensional fusion analysis of the surface and the cross-section of the skin surface image and the preset psoriasis skin cross-section image using a deep neural network model to obtain an analysis result of the object, including: The electronic device convolves the skin surface image through the first convolutional layer of the deep neural network model to obtain a first feature vector set; The electronic device convolves the psoriasis skin section image through the second convolutional layer of the deep neural network model to obtain a second feature vector set; The electronic device fuses the first feature vector set and the second feature vector set through a feature fusion layer of the deep neural network model to obtain a fused feature vector set; The electronic device processes the fused feature vector set through the feature processing layer of the deep neural network model to obtain an analysis result of the object; The skin surface image includes a corresponding pair of first and second ends, and a corresponding pair of third and fourth ends. The electronic device convolves the skin surface image through the first convolution layer of the deep neural network model to obtain a first feature vector set, including: The convolution kernel of the first convolution layer is initially located at the first end of the skin surface image, and the electronic device uses the convolution kernel of the first convolution layer to convolve the skin surface image once along a first direction and from the third end to the fourth end of the skin surface image to obtain a feature vector sequence; Afterwards, the electronic device steps the convolution kernel along the second direction by a preset step size, and uses the convolution kernel to continue to convolve the skin surface image again along the first direction and from the first end to the second end of the skin surface image, to obtain a feature vector sequence; This is continued in this manner until the electronic device steps the convolution kernel along the second direction to the second end, and then uses the convolution kernel to continue to convolve the skin surface image along the first direction from the first end to the second end of the skin surface image, to obtain a feature vector sequence, until the first convolution layer obtains a total of multiple feature vector sequences through convolution, the first feature vector set includes the multiple feature vector sequences, and the number of the multiple feature vector sequences is the number of times the convolution kernel steps plus one; The first direction is the direction of the psoriasis skin section, and the second direction is perpendicular to the first direction.

2. The method according to claim 1, characterized in that The electronic device fuses the first feature vector set and the second feature vector set through a feature fusion layer of the deep neural network model to obtain a fused feature vector set, including: The electronic device determines, through the feature fusion layer, a partial feature vector sequence in the first feature vector set that can be used for fusion; The electronic device fuses the partial feature vector sequence with the second feature vector set through the feature fusion layer to obtain the fused feature vector set.

3. The method according to claim 2, characterized in that The electronic device determines, through the feature fusion layer, a partial feature vector sequence in the first feature vector set that can be used for fusion, including: The second feature vector set includes a continuous feature vector sequence, and the electronic device determines, through the feature fusion layer, a degree of correlation between each of the multiple feature vector sequences and the continuous feature vector sequence; The electronic device determines, through the feature fusion layer, K feature vector sequences having the largest correlation levels from the multiple feature vector sequences, wherein the K feature vector sequences are the partial feature vector sequences that can be used for fusion, and K is an integer greater than 1; or; The electronic device selects K feature vector sequences that can be used for fusion from the multiple feature vector sequences in sequence by using the feature fusion layer, selecting a feature vector sequence as a partial feature vector sequence that can be used for fusion at intervals of a preset number of feature vector sequences.

4. The method according to claim 3, characterized in that The degree of correlation between any one of the plurality of feature vector sequences and the continuous feature vector sequence satisfies the following relationship: Wherein, μ represents the correlation degree, l represents any one of the multiple feature vector sequences, L represents the continuous feature vector sequence, and α is a preset parameter.

5. The method according to claim 3, characterized in that The electronic device fuses the partial feature vector sequence with the second feature vector set through the feature fusion layer to obtain the fused feature vector set, including: For the i-th feature vector sequence in the K feature vector sequences, i is any integer from 1 to K; The electronic device divides the continuous feature vector sequence into M feature vector sequences through the feature fusion layer, where M is an integer greater than 1; The electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in the M feature vector sequences through the feature fusion layer to obtain a fused feature vector sequence. When i traverses from 1 to K, K fused feature vector sequences are obtained, and the fused feature vector set includes the K fused feature vector sequences.

6. The method according to claim 5, characterized in that The electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in the M feature vector sequences through the feature fusion layer to obtain a fused feature vector sequence, including: The electronic device embeds the i-th feature vector sequence between every two adjacent feature vector sequences in the M feature vector sequences through the feature fusion layer to obtain an initial feature vector sequence; The electronic device adds a connection parameter between the i-th feature vector sequence and each feature vector sequence in the M feature vectors in the initial feature vector sequence through the feature fusion layer to obtain a fused feature vector sequence, and the vector value of the connection parameter is between the i-th feature vector sequence and each feature vector sequence in the M feature vectors.

7. The method according to claim 5 or 6, characterized in that The method further comprises: The electronic device uses the feature fusion layer to pad the length of each feature vector sequence in the first feature vector set that is not used for fusion to the same length as the fused feature vector sequence, thereby obtaining a padded feature vector sequence. The fused feature vector set also includes the padded feature vector sequence.

8. A device for identifying psoriasis case features based on machine vision, characterized in that: The apparatus is configured to: The device acquires a skin surface image of a subject, wherein the skin surface image includes a psoriasis affected area of ​​the subject; The device performs a three-dimensional fusion analysis of the surface and the cross-section of the skin surface image and the preset psoriasis skin cross-section image using a deep neural network model to obtain an analysis result of the object, wherein the analysis result of the object indicates the psoriasis level of the object; The electronic device performs a three-dimensional fusion analysis of the surface and the cross-section of the skin surface image and the preset psoriasis skin cross-section image through a deep neural network model to obtain an analysis result of the object, including: The electronic device convolves the skin surface image through the first convolution layer of the deep neural network model to obtain a first feature vector set; The electronic device convolves the psoriasis skin section image through the second convolutional layer of the deep neural network model to obtain a second feature vector set; The electronic device fuses the first feature vector set and the second feature vector set through a feature fusion layer of the deep neural network model to obtain a fused feature vector set; The electronic device processes the fused feature vector set through the feature processing layer of the deep neural network model to obtain an analysis result of the object; The skin surface image includes a corresponding pair of first and second ends, and a corresponding pair of third and fourth ends. The electronic device convolves the skin surface image through the first convolution layer of the deep neural network model to obtain a first feature vector set, including: The convolution kernel of the first convolution layer is initially located at the first end of the skin surface image, and the electronic device uses the convolution kernel of the first convolution layer to convolve the skin surface image once along a first direction and from the third end to the fourth end of the skin surface image to obtain a feature vector sequence; Afterwards, the electronic device steps the convolution kernel along the second direction by a preset step size, and uses the convolution kernel to continue to convolve the skin surface image again along the first direction and from the first end to the second end of the skin surface image, to obtain a feature vector sequence; This is continued in this manner until the electronic device steps the convolution kernel along the second direction to the second end, and then uses the convolution kernel to continue to convolve the skin surface image along the first direction from the first end to the second end of the skin surface image, to obtain a feature vector sequence, until the first convolution layer obtains a total of multiple feature vector sequences through convolution, the first feature vector set includes the multiple feature vector sequences, and the number of the multiple feature vector sequences is the number of times the convolution kernel steps plus one; The first direction is the direction of the psoriasis skin section, and the second direction is perpendicular to the first direction.

Images