Deep learning based psoriasis area and severity index system

Abstract

The application discloses a psoriasis lesion area evaluation system based on deep learning, which comprises an image acquisition module, a psoriasis lesion image preprocessing module, a psoriasis lesion image optimization module, a lesion area evaluation model design module and a psoriasis lesion area evaluation module. The application belongs to the field of image processing and specifically refers to a psoriasis lesion area evaluation system based on deep learning. According to the scheme, the inter-channel interaction weight mechanism is adopted, the channel area sensitive factor is introduced, and the complementarity of scales and erythema features is strengthened. Small scales are less likely to be missed due to the global information of erythema, and the boundary of erythema is clearer due to the reference of scale texture. By introducing the boundary sensitivity weight, the boundary error is directly related to the area error. The quadratic term of the area ratio is introduced and standardized to extract the lesion area features, thereby greatly improving the distinguishing accuracy of the boundary level. A loss function combining the gentle probability and the punishment weight is constructed, and then the psoriasis lesion area evaluation effect is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing, in particular to a psoriasis lesion area assessment system based on deep learning. BACKGROUND

[0002] The psoriasis lesion area assessment system generally labels the psoriasis lesion image and extracts the lesion feature of the image, and outputs the evaluation result through a specific model. However, the general psoriasis lesion area assessment system has the problems of scale feature capture imbalance leading to blurred erythema boundary, spatial feature misplacement and regional fracture, and insufficient boundary accuracy, which further leads to low reliability of the final lesion area assessment; the general psoriasis lesion area assessment system has the problems of fuzzy lesion grade boundary, weak lesion boundary grade distinction leading to misjudgment, and large exclusion class interference, which further leads to poor lesion area assessment effect. SUMMARY

[0003] In view of the above problems, in order to overcome the defects of the prior art, the present application provides a psoriasis lesion area assessment system based on deep learning, which aims at the problem of scale feature capture imbalance of the general psoriasis lesion area assessment system leading to blurred erythema boundary, spatial feature misplacement and regional fracture, and insufficient boundary accuracy, which further leads to low reliability of the final lesion area assessment. The present application introduces a channel area sensitive factor through an inter-channel interaction weight mechanism, and strengthens the complementarity of scales and erythema features. Small scales reduce missed detection due to the integration of global information of erythema, and erythema has a clearer boundary due to the reference of scale texture. By introducing a boundary sensitivity weight, the boundary error is directly related to the area error, thereby improving the reliability of lesion area assessment. For the problem of fuzzy lesion grade boundary of the general psoriasis lesion area assessment system, weak lesion boundary grade distinction leading to misjudgment, and large exclusion class interference, which further leads to poor lesion area assessment effect, the present application avoids cross-grade misjudgment through multi-value marking creation. The quadratic term of area ratio is introduced and standardized for lesion area feature extraction, which greatly improves the distinction accuracy of boundary grade. A loss function combining gentle probability and punishment weight is constructed to focus on the accuracy of the selected grade and avoid misjudgment caused by extreme probability, thereby improving the lesion area assessment effect.

[0004] The technical scheme adopted by the present application is as follows: the present application provides a psoriasis lesion area assessment system based on deep learning, which comprises an image acquisition module, a psoriasis lesion image preprocessing module, a psoriasis lesion image optimization module, a lesion area assessment model design module and a psoriasis lesion area assessment module.

[0005] The image acquisition module acquires historical psoriasis lesion images and performs image labeling.

[0006] The psoriasis lesion image preprocessing module performs skin color correction on the acquired historical psoriasis lesion images and performs normalization processing.

[0007] The psoriasis lesion image optimization module designs a hierarchical coding structure, introduces a channel area sensitive factor, and adopts a boundary weighted IoU loss to realize psoriasis lesion image optimization.

[0008] The psoriasis lesion area evaluation model design module extracts lesion spatial and statistical features and linearly transforms them based on the optimized psoriasis lesion image to train a total loss containing a gentle coefficient and a penalty coefficient, and establishes a psoriasis lesion area evaluation model.

[0009] The psoriasis lesion area evaluation module evaluates the lesion area of the real-time psoriasis lesion image.

[0010] Further, the image acquisition module acquires historical psoriasis lesion images; and performs image labeling, including pixel-level binary mask and lesion area grade true value.

[0011] Further, the psoriasis lesion image preprocessing module performs skin color correction on the acquired historical psoriasis lesion images, adopts YCbCr color space conversion; and performs hair removal, adopts morphological opening operation and threshold screening; finally performs image standardization and illumination normalization; and obtains a psoriasis lesion image set.

[0012] Further, the psoriasis lesion image optimization module specifically includes:

[0013] The hierarchical coding structure design unit; for the psoriasis lesion image, the feature extraction is split according to the lesion scale level, the first layer uses a convolutional neural network, and the 2-5 layers use a convolutional neural network + transformation neural network in parallel to extract features;

[0014] The psoriasis lesion feature channel interaction weight mechanism design unit; first, the psoriasis lesion channel feature compression is performed, the lesion feature mean value of each channel is calculated, the bidirectional channel attention is generated, and the channel area sensitive factor is introduced; the correlation matrix construction between the psoriasis lesion channels is performed, the bidirectional feature projection is performed, and finally the residual feature fusion is performed;

[0015] The psoriasis lesion spatial dimension feature intersection integration unit; first, the perception field is adapted, and then the fusion feature splicing is performed;

[0016] The psoriasis lesion segmentation decoder design unit; transpose convolution, each layer enlarges the feature map size by 2 times, the step = 2, and the padding = 1; skip connection fusion, after each layer is upsampled, the channel splicing is performed, and then the double convolution block is used to fuse the multi-scale lesion features; the output layer generates a binary mask;

[0017] The loss function is based on the IoU loss and introduces a boundary sensitivity weight.

[0018] Further, the psoriasis lesion area evaluation model design module specifically comprises the following contents:

[0019] Multi-value label creation; the psoriasis lesion area grading is a ordinal label, a double-branch tree area grade label conversion is performed, each area grade is mapped to a binary coding sequence; a range-inclusion label is generated for each binary tree node, and a target sequence is right-shifted to generate a decoding target sequence;

[0020] Area grade label embedding; the label bit is associated with the label value to generate a unique identifier, which is then converted into a vector with the same dimension as the psoriasis lesion feature through an embedding layer to serve as the input of the decoder;

[0021] Psoriasis lesion area feature extraction; global average pooling is performed on the final output feature map to obtain a spatial feature vector; a statistical feature vector is constructed based on the area proportion; the spatial feature and the statistical feature are spliced, and a linear transformation layer is used for mapping to obtain the final area feature;

[0022] Area grade sequence decoder design; the area grade binary coding sequence is predicted, and a mask is introduced to determine the probability contribution of the excluded area grade, focusing on the current selected grade; a group of original predicted values is output; a mask is generated based on the range-inclusion label of the previous moment, and the Sigmoid probability is weighted; the mean probability is calculated and compared, and the complete binary coding sequence is obtained after 3 iterations;

[0023] Area grade loss function design; a gentle coefficient is constructed, a penalty coefficient is introduced to suppress the exclusion grade loss, and a penalty coefficient is constructed; a single-time loss is constructed to obtain the total loss.

[0024] Further, the psoriasis lesion area evaluation module acquires a psoriasis lesion image, processes the image through a psoriasis lesion image preprocessing module and a psoriasis lesion image optimization module in sequence, and inputs the processed image into the psoriasis lesion area evaluation model, so that the area grade of the lesion output by the model is taken as the evaluation result of the psoriasis lesion area; if the area grade of the lesion is 4 or 5, the management personnel are warned.

[0025] The beneficial effects achieved by the present application using the above-mentioned scheme are as follows:

[0026] (1) For the problem that the general psoriasis lesion area evaluation system has scale feature capture imbalance, leading to blurred erythema boundary, spatial feature misplacement and regional fracture, and insufficient boundary accuracy, and further leading to low reliability of the final lesion area evaluation, the present scheme introduces a channel area sensitive factor through an inter-channel interaction weight mechanism, strengthens the complementarity of scales and erythema features, reduces the missed detection of small scales due to the integration of global information of erythema, and makes the boundary of erythema clearer due to the reference of scale texture; the boundary error is directly associated with the area error by introducing a boundary sensitivity weight; and the reliability of the lesion area evaluation is improved.

[0027] (2) For the general psoriasis lesion area evaluation system, the lesion grade boundary is fuzzy, the lesion boundary grade is weak, which leads to misjudgment, and the exclusion interference is large, which further leads to poor psoriasis lesion area evaluation effect. The present scheme avoids cross-grade misjudgment through multi-value marking creation; the quadratic term of area ratio is introduced and standardized for lesion area feature extraction, which greatly improves the discrimination accuracy of boundary grade; a loss function combining gentle probability and punishment weight is constructed to focus on the accuracy of the selected grade and avoid misjudgment caused by extreme probability; and the lesion area evaluation effect is improved. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 A process schematic diagram of the psoriasis lesion area evaluation system based on deep learning provided by the present application is provided.

[0029] Figure 2 A process schematic diagram of the psoriasis lesion area evaluation model design module is provided.

[0030] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0032] In the description of the present application, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0033] Embodiment one, refer to Figure 1 The psoriasis lesion area evaluation system based on deep learning provided by the present application comprises an image acquisition module, a psoriasis lesion image preprocessing module, a psoriasis lesion image optimization module, a psoriasis lesion area evaluation model design module and a psoriasis lesion area evaluation module.

[0034] The image acquisition module acquires historical psoriasis lesion images and performs image labeling; and sends data to the psoriasis lesion image preprocessing module.

[0035] The psoriasis lesion image preprocessing module performs skin color correction on the collected historical psoriasis lesion images and performs normalization processing; and sends the data to the psoriasis lesion image optimization module;

[0036] The psoriasis lesion image optimization module designs a hierarchical coding structure, introduces a channel area sensitive factor, and adopts a boundary weighted IoU loss to realize psoriasis lesion image optimization; and sends the data to the psoriasis lesion area evaluation model design module;

[0037] The psoriasis lesion area evaluation model design module extracts lesion spatial and statistical features and linearly transforms them based on the optimized psoriasis lesion images to train a total loss containing a gentle coefficient and a penalty coefficient, and establishes a lesion area evaluation model; and sends the data to the psoriasis lesion area evaluation module;

[0038] The psoriasis lesion area evaluation module evaluates the lesion area of real-time psoriasis lesion images.

[0039] Example two, refer to Figure 1 This example is based on the above example, the image acquisition module acquires historical psoriasis lesion images, which are RGB images covering different parts, severity and skin color; and performs image annotation, including pixel-level binary mask and lesion area grade true value, 1 in the pixel-level binary mask is the lesion area, 0 is normal skin, hair or background; the lesion area is divided into grades: the lesion area ratio is calculated , and mapped to ordinal category labels, represented as: ; wherein, is the lesion area grading.

[0040] Example three, refer to Figure 1 This example is based on the above example, the psoriasis lesion image preprocessing module performs skin color correction on the collected historical psoriasis lesion images, converts the RGB image to YCbCr space using YCbCr color space conversion, represented as: ; ; Where Y is the luminance component in the YCbCr space; Cb and Cr are the blue and red components in the YCbCr space, respectively; R, G, and B are the red, green, and blue components of each pixel in the psoriatic lesion image, respectively. Hair removal is performed using morphological opening operations and thresholding. First, hair and lesions are initially separated by opening operations of 1×5 vertical structuring elements. Then, based on the large gray-level difference of hair pixels, Sobel edge detection is used to filter hair areas. Finally, the hair areas are filled by interpolation of surrounding normal skin pixels to avoid hair being misjudged as scales. Finally, image standardization is performed to unify the image size to 512×512, and illumination normalization is performed. CLAHE is used to enhance contrast within 8×8 local blocks to avoid large areas of dark lesions being missed due to insufficient illumination. A set of psoriatic lesion images is obtained.

[0041] Example 4, see Figure 1 This embodiment is based on the above embodiment, and the psoriasis lesion image optimization module specifically includes:

[0042] A hierarchical coding structure design unit is used to address the issue that psoriatic lesions exhibit both small-scale details, including punctate scaling, and large-scale distributions, such as extensive erythema on the trunk. A hierarchical encoder is designed to extract features from psoriatic lesion images by splitting them into layers according to lesion scale. The first layer uses a convolutional neural network (CNN) to lay the foundation for local details. Layers 2-5 simultaneously use a CNN and a transform neural network (VLT) for parallel extraction, ensuring that scaling details and global erythema features are generated synchronously at each scale level, providing multi-scale lesion feature support for subsequent fusion. The CNN backbone uses ResNet18, and the VLT backbone uses ViT-Base. The hierarchical feature extraction process is as follows: Layer 1 (input layer) uses only ResNet18's Conv1+MaxPool to convert the preprocessed image into a 128×128×64 basic local feature map, capturing the initial edges of the lesions. Layers 2-5 (multi-scale layers) simultaneously execute a ResNet18 block (outputting CNN features) and a ViT-Base block (outputting VLT features).

[0043] The encoder layer number and feature map size correspond to the scale of psoriatic skin lesions. Convolutional neural networks emphasize this aspect, while transform neural networks emphasize this aspect.

[0044] The second layer consists of 64×64 small scales with scale edge texture and clustered distribution of small scales.

[0045] Layer 3, 32×32 medium-sized plaque, plaque boundary details, association between plaque and surrounding skin lesions;

[0046] Layer 4: 16×16 large area of ​​erythema, internal infiltration texture of erythema, global extent of erythema;

[0047] Layer 5, 8×8 full-map skin lesion distribution, core lesion area features, and correlation of skin lesions in multiple locations;

[0048] Design unit for the interaction weighting mechanism between channels of psoriatic skin lesions; The channel features of psoriatic skin lesions exhibit significant differences. Through channel compression, bidirectional attention, feature projection, and residual connection feature integration, the scaling channel of the convolutional neural network and the erythema channel of the transform neural network are bidirectionally associated, screening highly correlated features, strengthening the complementarity of local details and global context, and avoiding missed detection of small scaling and blurred erythema boundaries; First, the channel features of psoriatic skin lesions are compressed, and the mean value of the lesion features in each channel is calculated to avoid interference from single pixel noise, represented as: ; Where P is the original lesion feature map extracted from the psoriasis lesion image by the convolutional neural network; V is the original lesion feature map extracted by the transform neural network. It is a channel-level average pooling function; and This is the result of average pooling; bidirectional channel attention generation allows the scaling channel of the convolutional neural network to perceive the dimension of the erythema channel of the neural network, and vice versa, generating attention weights that can filter highly relevant channels, and introducing a channel area sensitivity factor. For each channel, the average area ratio of its corresponding lesion in the training set is statistically analyzed as a sensitivity factor, expressed as: ; ; ; ;in, and These are the channel attention weight vectors on the convolutional neural network side and the transform neural network side, respectively; and These are the sensitivity factors on the convolutional neural network side and the transform neural network side, respectively. and These are the average areas of the skin lesions corresponding to the convolutional channel p and the transform channel v, respectively. It is the Sigmoid activation function; and These are the weight matrices for increasing and decreasing the dimensionality of the convolutional neural network, respectively. It is the ReLU activation function; and These are the weight matrices for dimensionality increase and dimensionality reduction on the neural network side, respectively; and a correlation matrix between channels in psoriatic lesions is constructed to quantify the correlation between the scaling channel and the erythematous channel, expressed as: Bidirectional feature projection integrates convolutional neural network features with global erythema information to avoid missing scales at the erythema edge, and transform neural network features with detailed scale information to avoid blurring of erythema boundaries. This is represented as: ; Finally, residual feature fusion is performed, which is represented as: ; Where Q is the inter-channel correlation matrix; It is the projection result of the features of the convolutional neural network onto the channel space of the transform neural network; The spatial dimension of P is preserved by marking; It is the Softmax normalization function; It is the projection result of the transformed neural network features onto the channel space of the convolutional neural network; The spatial dimension of V is preserved; and These are the fused convolutional neural network feature maps and transform neural network feature maps, respectively.

[0049] A unit for integrating spatial features of psoriatic lesions; the spatial distribution of psoriatic lesions exhibits local-global misalignment. Through receptive field adaptation, iterative fusion, and parameter control, the spatial features of scaling from the convolutional neural network are aligned with the spatial features of erythema from the transform neural network, ensuring the continuity of the lesion region and providing a complete and unbroken lesion mask for area statistics; firstly, receptive field adaptation is performed, represented as: ; Subsequently, feature fusion and stitching are performed to enhance the commonly identified lesion areas, represented as follows: ;in, and These are the fused convolutional neural network feature maps and the transformed neural network feature maps, respectively. It is a two-dimensional convolution operation; and It is a convolution kernel; This is the final output feature map; It is feature splicing;

[0050] The design unit for the psoriasis lesion segmentation decoder is as follows: The boundary accuracy of psoriasis lesions directly affects area assessment. A U-Net-like architecture of transposed convolution + double convolution is adopted, combined with skip connections in the spatial dimension feature fusion unit of psoriasis lesions, to fuse multi-scale lesion features and ultimately generate a binary segmentation mask of the same size as the input image. Transposed convolution enlarges the feature map size by a factor of 2 in each layer, with a stride of 2 and padding of 1, ensuring accurate lesion size recovery. Skip connection fusion, after upsampling in each layer, is combined with... Channel concatenation is performed, followed by a double convolutional block of 3×3 convolution + ReLU + 3×3 convolution + ReLU to fuse multi-scale skin lesion features; the output layer generates a binary mask, represented as: ;in, It is the value of the final output binary segmentation mask at pixel (x,y), where 1 indicates that the pixel belongs to the psoriasis lesion area and 0 indicates that the pixel does not belong to the psoriasis lesion area; It is a 1×1 convolution kernel; First to Perform convolution to obtain a single-channel feature map, then apply the sigmoid function to this single-channel feature map to obtain a probability map of each pixel belonging to skin lesions. This represents the pixel value corresponding to the coordinate in the probability graph;

[0051] The loss function is based on IoU loss and introduces boundary sensitivity weights. This links the segmentation loss of the boundary region with the area error, strengthening the impact of the boundary on area assessment, as shown below: ; ;in, It is a boundary-weighted loss; It is an IoU loss; It is a truly labeled binary segmentation mask; It is the boundary enhancement coefficient; It is an erosion operation; training uses the AdamW optimizer, and the learning rate scheduling strategy uses cosine annealing.

[0052] By performing the above operations, this solution addresses the problems of unbalanced scale feature capture leading to blurred erythema boundaries, spatial feature misalignment and regional fragmentation, and insufficient boundary accuracy in general psoriasis lesion area assessment systems, resulting in low reliability of the final lesion area assessment. This solution introduces a channel area-sensitive factor through an inter-channel interactive weighting mechanism, enhancing the complementarity of scale and erythema features. Small scales are less likely to be missed due to the integration of global erythema information, while erythema boundaries are clearer by referencing scale texture. By introducing boundary sensitivity weights, boundary errors are directly correlated with area errors, thereby improving the reliability of lesion area assessment.

[0053] Example 5, see Figure 1 and Figure 2 This embodiment is based on the above embodiment, and the skin lesion area assessment model design module specifically includes the following:

[0054] Multi-value marker creation; lesion area grading These are ordinal labels. Direct prediction can lead to misjudgments due to blurred boundaries between levels. Therefore, a binary tree area level label conversion is performed. Assuming the binary tree height is d=3, each area level is mapped to a bi-state encoded sequence, represented as: ; represents the path from the root node to the leaf node, where 0 in binary indicates the left branch and 1 indicates the right branch. Each leaf node uniquely corresponds to a skin lesion area level; generates a range label for each binary tree node, indicating the positive class included / excluded negative class of the current node, represented as: The target sequence is then shifted right, starting with the initial query marker 's', to generate the decoded target sequence. , is represented as: ;in, It is a bi-state encoded sequence label at the area level; It is the multi-hot vector at time t, where 0 corresponds to the left branch and 1 corresponds to the right branch, and t∈{1,2,3}; The scope includes the tag; It is the multi-heat vector at time t, which is a binary vector of length 6. Each time corresponds to a level, and 1 indicates that the current level node contains the level of skin lesion area.

[0055] Area rank label embedding; binary labels at different levels have ambiguous meanings, so the label position is associated with the label value to generate a unique identifier, which is then transformed into a vector of the same dimension as the skin lesion features through an embedding layer, and used as the input to the decoder; the unique identifier is represented as: Decoder input Represented as: ;in, This is the position-value association encoding function for the area marker; k is the position index of the element in the target sequence, where k=0 corresponds to the initial marker s, and k=1 corresponds to... ; It is the value of the element at the k-th position in the target sequence; It is an embedded layer for area markers;

[0056] Skin lesion area feature extraction; for Perform global average pooling to obtain spatial feature vectors. Constructing statistical feature vectors based on area proportion This includes the percentage and the quadratic term, improving the differentiation of boundary levels, and is expressed as: Spatial and statistical features are combined, and the final area feature is obtained through a linear transformation layer mapping. , is represented as: ;in, and These are all samples in the training set. The mean and variance; It is a linear transformation layer mapping;

[0057] Design of area-level sequence decoder; Inputting skin lesion features, with As the label embedding input, predict the area level bi-state encoded sequence, and simultaneously introduce a mask decision to suppress the probability contribution of the already eliminated area levels, focusing on the current candidate level; let the decoder input at time t be... During training During testing, the embedding of the predicted label from the previous time step is used; after processing with multi-head self-attention and cross-attention, a set of original predicted values ​​is output. , is represented as: ;Based on the range containing the label in the previous time step Generate a mask, suppress the weights of excluded categories, and weight the Sigmoid probability, represented as: ; ;in, It is an area-level sequence decoder; It is the mask vector at time t. It is a vector element; It is a suppressor factor; The range at time t-1 includes the label; Let i be the label of level i in the multi-hot vector at time t-1; let the area level ranges of the left and right subtrees at level t of the binary tree be [l,m] and [m+1,r], respectively. Calculate the mean probability and compare them, expressed as: ; ; The complete two-state encoding sequence is obtained by iterating 3 times. ;in, and These are the mean probabilities of the left and right branches, respectively; l, m, and r are boundary parameters; It is the mask-weighted probability of level i at time t; It is the decision result at time t; , and These are the decision results at three different moments;

[0058] Area-level loss function design; constructing a smoothing coefficient to avoid probability extremes, expressed as: A penalty coefficient is introduced to suppress the loss caused by excluding certain levels, prioritizing the prediction accuracy of candidate levels, and constructing a penalty coefficient system. , is represented as: Single-moment loss Represented as: The assessment of psoriasis area requires a step-by-step screening process at three different times, hence the total loss... Represented as: ;in, It is the smoothness coefficient at time t; T is the temperature range coefficient; It is the penalty coefficient; the AdamW optimizer is used, and the learning rate is dynamically adjusted using a cosine annealing strategy; after each round of training, the model is evaluated using a validation set, and the rank accuracy is used as the core indicator to judge the model performance.

[0059] By performing the above operations, this solution addresses the problems of general psoriasis lesion area assessment systems, such as blurred lesion grade boundaries, weak differentiation of lesion grade boundaries leading to misjudgments, and large exclusion of class interference, resulting in poor lesion area assessment performance. This solution avoids cross-grade misjudgments by creating multi-valued labels; it introduces a quadratic term of area proportion and standardizes it for lesion area feature extraction, significantly improving the accuracy of boundary grade differentiation; and it constructs a loss function combining smooth probability and punitive weights to focus on the accuracy of candidate grades, avoiding misjudgments caused by extreme probabilities. These improvements ultimately enhance the effectiveness of lesion area assessment.

[0060] Example 6, see Figure 1 This embodiment is based on the above embodiment. The psoriasis lesion area assessment module acquires psoriasis lesion images, which are then processed by the psoriasis lesion image preprocessing module and the psoriasis lesion image optimization module in sequence before being input into the lesion area assessment model. The lesion area level output by the model is used as the psoriasis lesion area assessment result. If the lesion area level is 4 or 5, an early warning is issued to the management personnel.

[0061] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

[0062] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A deep learning-based system for assessing the area of ​​psoriasis lesions, characterized in that: The system includes an image acquisition module, a psoriasis lesion image preprocessing module, a psoriasis lesion image optimization module, a lesion area assessment model design module, and a psoriasis lesion area assessment module. The image acquisition module acquires historical images of psoriasis lesions and annotates them; The psoriasis lesion image preprocessing module performs skin color correction and normalization on the acquired historical psoriasis lesion images; The psoriasis lesion image optimization module is designed with a hierarchical coding structure, introduces a channel area sensitive factor, and adopts boundary weighted IoU loss to achieve psoriasis lesion image optimization. The skin lesion area assessment model design module is based on the optimized psoriasis skin lesion image, extracts the spatial and statistical features of the skin lesion and performs linear transformation, and trains it with total loss containing smoothing coefficient and punishment coefficient to establish the skin lesion area assessment model. The psoriasis lesion area assessment module assesses the lesion area of ​​real-time psoriasis lesion images.

2. The deep learning-based psoriasis lesion area assessment system according to claim 1, characterized in that: The psoriasis lesion image optimization module specifically includes: Hierarchical coding structure design unit; for psoriasis lesion images, feature extraction is performed by splitting the image into layers according to the lesion scale. The first layer uses a convolutional neural network, and layers 2-5 use a convolutional neural network and a transform neural network in parallel for extraction. Design unit for the interaction weighting mechanism between channels characteristic of psoriatic skin lesions; A unit for integrating spatial dimensional features of psoriatic lesions; first, receptive field adaptation is performed, followed by feature fusion splicing; Design unit for psoriasis lesion segmentation decoder; transposed convolution, each layer enlarges the feature map size by 2 times, stride=2, padding=1; skip connection fusion, after upsampling of each layer, channel splicing is performed, and then multi-scale lesion features are fused through double convolutional blocks; the output layer generates a binary mask; The loss function is based on IoU loss and introduces boundary sensitivity weights.

3. The deep learning-based psoriasis lesion area assessment system according to claim 2, characterized in that: The design unit for the interaction weighting mechanism between psoriasis lesion feature channels first compresses the psoriasis lesion channel features, calculates the mean value of the lesion features in each channel, generates bidirectional channel attention, and introduces a channel area sensitive factor. A correlation matrix between channels of psoriatic lesions was constructed, bidirectional feature projection was performed, and finally residual feature fusion was carried out.

4. The deep learning-based psoriasis lesion area assessment system according to claim 3, characterized in that: The skin lesion area assessment model design module specifically includes the following: Multi-value label creation; the lesion area grading is an ordinal label, and a two-branch tree area grade label conversion is performed, with each area grade mapped to a bi-state encoded sequence; a range-containing label is generated for each binary tree node, and the target sequence is right-shifted to generate the decoded target sequence; Area rank label embedding: The label position is associated with the label value to generate a unique identifier, which is then transformed into a vector of the same dimension as the skin lesion feature through the embedding layer and used as the input of the decoder; Skin lesion area feature extraction; Global average pooling is performed on the final output feature map to obtain a spatial feature vector; a statistical feature vector is constructed based on the area ratio; and the vectors are then concatenated. Spatial and statistical features are mapped through a linear transformation layer to obtain the final area features; Design of area-level sequence decoder; Design of area-level loss function.

5. The deep learning-based psoriasis lesion area assessment system according to claim 4, characterized in that: The area level sequence decoder design predicts the area level bi-state encoded sequence, while introducing a mask judgment to suppress the probability contribution of the eliminated area levels and focus on the current candidate level; outputs a set of original predicted values; generates a mask based on the range containing the label in the previous time step and weights the Sigmoid probability; calculates the mean probability and compares it, and iterates 3 times to obtain the complete bi-state encoded sequence.

6. The deep learning-based psoriasis lesion area assessment system according to claim 5, characterized in that: The area-level loss function design involves constructing a smoothing coefficient, introducing a penalty coefficient to suppress and eliminate level losses, constructing a penalty coefficient, constructing a single-time loss, and obtaining the total loss.

7. The deep learning-based psoriasis lesion area assessment system according to claim 6, characterized in that: The psoriasis lesion image preprocessing module performs skin color correction on the acquired historical psoriasis lesion images using YCbCr color space conversion; hair removal is performed using morphological opening operations and threshold filtering; finally, image standardization and illumination normalization are performed to obtain a set of psoriasis lesion images.

8. The deep learning-based psoriasis lesion area assessment system according to claim 7, characterized in that: The psoriasis lesion area assessment module acquires psoriasis lesion images, which are then processed by the psoriasis lesion image preprocessing module and the psoriasis lesion image optimization module before being input into the lesion area assessment model. The lesion area level output by the model is used as the psoriasis lesion area assessment result. If the lesion area level is 4 or 5, an early warning is issued to the management personnel.

Images