A method and system for determining the location deviation of melanoma lesions

Abstract

This invention relates to the field of medical image processing technology, and discloses a method and system for determining the location offset of melanoma lesions. The method includes: determining a first positioning reference point by extracting blood vessels and melanoma from a first skin image, and determining the original location of the melanoma in the first skin image based on the first positioning reference point; extracting blood vessels and melanoma from a second skin image after a preset time interval to determine a second positioning reference point, and determining the changed location of the melanoma in the second skin image based on the second positioning reference point; thus, the distance between the original location and the changed location of the melanoma in the first image can be determined; and the location offset of the melanoma lesion is determined based on the distance between the original location and the changed location of the melanoma. This invention solves the problem of low accuracy in existing methods for determining the location offset of melanoma lesions.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and in particular to a method and system for determining the location deviation of melanoma lesions. Background Technology

[0002] Melanoma is a highly malignant tumor originating from melanoma, primarily occurring in the skin, but also in mucous membranes and internal organs. Cutaneous malignant melanoma ranks third among malignant skin tumors. Because melanoma predominantly occurs on the epidermis and possesses certain color and morphological characteristics, the use of machine learning technology for early diagnosis of melanoma has attracted widespread attention from scholars both domestically and internationally. For example, invention application CN 108830853 A discloses an artificial intelligence-based melanoma-assisted diagnostic method, which uses machine learning to extract tumor images from the skin surface and then determine whether they are melanomas. However, this judgment is based solely on a static method, while melanomas actually develop gradually, and changes in size, shape, and location over time are all related to whether they eventually develop into melanoma. Size and shape can be obtained through image segmentation after taking a picture, but because people's weight varies at different times, it is impossible to accurately identify whether the location has changed, resulting in a low accuracy rate for current melanoma diagnosis. Therefore, existing methods for judging the location deviation of melanoma lesions suffer from low accuracy. Summary of the Invention

[0003] This invention provides a method and system for determining the location offset of melanoma lesions, in order to solve the problem of low accuracy in existing methods for determining the location offset of melanoma lesions.

[0004] To achieve the above objectives, the present invention employs the following technical solution:

[0005] In a first aspect, the present invention provides a method for determining the location deviation of melanoma lesions, comprising:

[0006] Obtain a first skin image containing melanoma lesions, and extract blood vessels and melanoma from the first skin image;

[0007] The first positioning reference point is determined based on the blood vessels on the first skin image, and the original location of the melanoma in the first skin image is determined based on the first positioning reference point.

[0008] After a preset time interval, a second skin image containing the melanoma lesion in the first skin image is acquired, and blood vessels and melanoma are extracted from the second skin image.

[0009] The second positioning reference point is determined based on the blood vessels on the second skin image, and the location of the melanoma change in the second skin image is determined based on the second positioning reference point.

[0010] Based on the first positioning reference point and the second positioning reference point, the changed location of the melanoma is mapped onto the first skin image, and the distance between the original location of the melanoma and the changed location of the melanoma is determined in the first image;

[0011] The location shift of the melanoma lesion is determined based on the distance between the original location of the melanoma and the changed location of the melanoma.

[0012] Optional, such as Figure 2 As shown, the process of extracting blood vessels from a skin image includes:

[0013] The skin containing melanoma lesions was irradiated with infrared light, and digital image information of the reflected infrared light was collected as a skin image.

[0014] The skin image is enhanced by RGB channel enhancement to obtain an enhanced image, and the blood vessels on the skin image are extracted after noise reduction preprocessing of the enhanced image.

[0015] Optionally, melanoma can be extracted from skin images, including:

[0016] We constructed ResNet101 and Vit-Transformer neural network models and obtained training and validation datasets for melanoma through manual annotation.

[0017] A melanoma recognition model was constructed by combining the ResNet101 neural network model and the Vit-Transformer neural network model. The constructed melanoma recognition model was then trained using the training dataset and the validation dataset to obtain the trained melanoma recognition model.

[0018] The skin image is input into the trained melanoma recognition model, and the trained melanoma recognition model is used to extract melanoma from the skin image.

[0019] Optionally, determining the first positioning reference point based on blood vessels in the first skin image includes:

[0020] The position of each blood vessel is determined in the first skin image. Based on the position of each blood vessel, the blood vessels that intersect are identified, and the intersection of the intersecting blood vessels is used as the first positioning reference point. The first positioning reference point in the first skin image contains at least three points.

[0021] The determination of the second positioning reference point based on blood vessels in the second skin image includes:

[0022] The position of each blood vessel is determined in the second skin image. Based on the position of each blood vessel, the intersecting blood vessels are identified, and the intersection of the intersecting blood vessels is used as the second positioning reference point. The second positioning reference point in the second skin image contains at least three points.

[0023] Optionally, determining the original location of the melanoma in the first skin image based on the first positioning reference point includes:

[0024] A first planar coordinate system is constructed using the first positioning reference point, a first positional mapping relationship is established between the first skin image and the first planar coordinate system, and the position of the melanoma in the first skin image is determined.

[0025] The position of the melanoma in the first skin image is mapped to the first planar coordinate system using the first mapping relationship to obtain the position of the melanoma in the first planar coordinate system, and the position of the melanoma in the first planar coordinate system is taken as the original position of the melanoma.

[0026] Determining the location of melanoma changes in the second skin image based on the second positioning reference point includes:

[0027] A second planar coordinate system is constructed using the second positioning reference point, a second positional mapping relationship is established between the second skin image and the second planar coordinate system, and the position of the melanoma in the second skin image is determined.

[0028] The location of the melanoma in the second skin image is mapped to the second planar coordinate system using the second mapping relationship to obtain the location of the melanoma in the second planar coordinate system, and the location of the melanoma in the second planar coordinate system is used as the change location of the melanoma.

[0029] Optionally, mapping the location of the melanoma change onto the first skin image based on the first and second positioning reference points includes:

[0030] Determine whether the first positioning reference point in the first plane coordinate system and the second positioning reference point in the second plane coordinate system are intersections of the same blood vessel. If not, reconstruct the first plane coordinate system and / or the second plane coordinate system until the first positioning reference point in the first plane coordinate system and the second positioning reference point in the second plane coordinate system are intersections of the same blood vessel. Then, redetermine the original location and the changed location of the melanoma. If yes, map the changed location of the melanoma in the second plane coordinate system to the first plane coordinate system to obtain the changed location of the melanoma in the first plane coordinate system.

[0031] Optionally, methods for determining whether the first positioning reference point in the first planar coordinate system and the second positioning reference point in the second planar coordinate system are intersections of the same blood vessel include:

[0032] Extract the first shape information of the blood vessel corresponding to the first positioning reference point used to construct the first planar coordinate system, and extract the second shape information of the blood vessel corresponding to the second positioning reference point used to construct the second planar coordinate system;

[0033] The first shape information is compared with the second shape information to determine whether the first shape information and the second shape information match. If they match, the first positioning reference point for constructing the first planar coordinate system and the second positioning reference point for constructing the second planar coordinate system are determined to be the same blood vessel. If they do not match, the first positioning reference point for constructing the first planar coordinate system and the second positioning reference point for constructing the second planar coordinate system are determined to be different blood vessels.

[0034] The process of comparing the first shape information with the second shape information includes enlarging, reducing, or rotating the first shape information and / or the second shape information.

[0035] Optionally, determining the distance between the original location of the melanoma and the changed location of the melanoma in the first image includes:

[0036] The position of the changed location of the melanoma in the first plane coordinate system is compared with the original position of the melanoma to obtain the first distance information, and the first distance information is used as the distance between the original position of the melanoma and the changed location of the melanoma.

[0037] Optionally, determining the location shift of the melanoma lesion based on the distance between the original location of the melanoma and the changed location of the melanoma includes:

[0038] The first distance information is compared with a preset first threshold. If the first distance information is less than or equal to the preset first threshold, it is determined that the location of the melanoma lesion has not shifted. If the first distance information is greater than the preset first threshold, the second distance information between the original location of the melanoma and all the first positioning reference points is determined. At the same time, based on the position of the changed location of the melanoma in the first plane coordinate system, the third distance information between the changed location of the melanoma and all the first positioning reference points is determined. The difference between the second distance information and the third distance information is calculated. If the difference is less than or equal to the preset second threshold, it is determined that the location of the melanoma lesion has not shifted. If the difference is greater than the preset second threshold, it is determined that the location of the melanoma lesion has shifted.

[0039] Secondly, embodiments of this application provide a melanoma lesion location offset determination system, including a processor and a memory;

[0040] Memory, used to store computer programs;

[0041] When a processor executes a program stored in memory, it implements any of the steps of the method described in the first aspect.

[0042] Beneficial effects:

[0043] The method for determining the location deviation of melanoma lesions provided by this invention determines a first positioning reference point by extracting blood vessels and melanoma from a first skin image, and determines the original location of the melanoma in the first skin image based on the first positioning reference point; after a preset time interval, extracting blood vessels and melanoma from a second skin image to determine a second positioning reference point, and determining the changed location of the melanoma in the second skin image based on the second positioning reference point; thus, the distance between the original location and the changed location of the melanoma can be determined in the first image; thereby locating the location of the melanoma and determining whether there is a location deviation. Since blood vessels are usually stationary, using blood vessels as a reference greatly improves the accuracy of melanoma diagnosis. Attached Figure Description

[0044] Figure 1 This is a flowchart of a preferred embodiment of the melanoma lesion location offset determination method of the present invention;

[0045] Figure 2 This is a schematic diagram illustrating the extraction of blood vessels from a skin image according to a preferred embodiment of the present invention.

[0046] Figure 3 This is a schematic diagram of the structure of a melanoma recognition model according to a preferred embodiment of the present invention. Detailed Implementation

[0047] The technical solution of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms "an" or "a" and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms "connected" or "linked" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship also changes accordingly.

[0049] Please see Figure 1 This application provides a method for determining the location deviation of melanoma lesions, including:

[0050] Obtain a first skin image containing melanoma lesions, and extract blood vessels and melanoma from the first skin image;

[0051] The first positioning reference point is determined based on the blood vessels on the first skin image, and the original location of the melanoma in the first skin image is determined based on the first positioning reference point.

[0052] After a preset time interval, a second skin image containing the melanoma lesion in the first skin image is acquired, and blood vessels and melanoma are extracted from the second skin image.

[0053] The second positioning reference point is determined based on the blood vessels on the second skin image, and the location of the melanoma change in the second skin image is determined based on the second positioning reference point.

[0054] Based on the first positioning reference point and the second positioning reference point, the changed location of the melanoma is mapped onto the first skin image, and the distance between the original location of the melanoma and the changed location of the melanoma is determined in the first image;

[0055] The location shift of the melanoma lesion is determined based on the distance between the original location of the melanoma and the changed location of the melanoma.

[0056] In this embodiment, a first positioning reference point is determined by extracting blood vessels and melanoma from a first skin image, and the original position of the melanoma in the first skin image is determined based on the first positioning reference point. After a preset time interval, blood vessels and melanoma are extracted from a second skin image to determine a second positioning reference point, and the changed position of the melanoma in the second skin image is determined based on the second positioning reference point. The distance between the original position and the changed position of the melanoma in the first image can then be determined, thereby locating the position of the melanoma and determining whether there is a positional shift. Since blood vessels are usually stationary, using blood vessels as a reference greatly improves the accuracy of melanoma diagnosis.

[0057] The preset time intervals in the embodiments can be divided into two cases: 1. It is recommended to conduct a clinical assessment every 3 months after surgery; 2. For patients who have completed initial treatment, the recommended follow-up plan is once every 3 months in the first year, once every 4 months in the second year, once every 6 months from the third to the fifth year, and once a year thereafter. Therefore, according to the first case, the preset time interval can be set to 3 months, and according to the second case, the preset time interval can be set to 3 months in the first year, 4 months in the second year, 6 months from the third to the fifth year, and 12 months after five years.

[0058] Regarding the selection of the melanoma location in the embodiments, regardless of whether it is the original location of the melanoma or the location where the melanoma has changed, the centroid location of the corresponding melanoma can be selected as the melanoma location to facilitate the calculation.

[0059] Regarding the selection of positioning reference points, since the position of blood vessels will not change significantly under the influence of external forces, the position of blood vessels can be used as the selection criterion for reference points. Among these, the intersections between blood vessels are natural positioning points. Therefore, the intersections of blood vessels on the skin image can be used as positioning reference points to determine the position of the skin image.

[0060] Optionally, extract blood vessels from the skin image, including:

[0061] like Figure 2 As shown, infrared light was used to irradiate the skin containing melanoma lesions, and digital image information of the reflected infrared light was collected as a skin image.

[0062] The skin image is enhanced by RGB channel enhancement to obtain an enhanced image, and the blood vessels on the skin image are extracted after noise reduction preprocessing of the enhanced image.

[0063] Optionally, melanoma can be extracted from skin images, including:

[0064] We constructed ResNet101 and Vit-Transformer neural network models and obtained training and validation datasets for melanoma through manual annotation.

[0065] A melanoma recognition model was constructed by combining the ResNet101 neural network model and the Vit-Transformer neural network model. The constructed melanoma recognition model was then trained using the training dataset and the validation dataset to obtain the trained melanoma recognition model.

[0066] The skin image is input into the trained melanoma recognition model, and the trained melanoma recognition model is used to extract melanoma from the skin image.

[0067] In this embodiment, ResNet-101 is a deep convolutional neural network whose main feature is the use of residual blocks to solve the vanishing gradient problem in deep network training. In deep learning, the vanishing gradient problem becomes increasingly severe as the number of network layers increases, making it difficult for the network to converge. ResNet-101 uses residual blocks to construct the deep network, making the network easier to train and achieving excellent results in image recognition tasks.

[0068] The mathematical expression for the ResNet-101 model is as follows:

[0069] Input: X

[0070] Residual block: F(X)+X

[0071] Here, F(X) represents the mapping function of the residual block, and X represents the input data. The residual block can be viewed as a kind of skip connection, which allows the input data to be directly passed to the output layer, thereby avoiding the effects of the vanishing gradient problem.

[0072] The ResNet101 network structure diagram has 101 layers, with the first layer being a 7x7 convolutional layer, followed by 4 stages, each containing several residual blocks.

[0073] Finally, there is a layer of global average pooling and a fully connected layer.

[0074] Each residual block consists of two 3x3 convolutional layers, each followed by batch normalization and a ReLU activation function. There are also batch normalization and ReLU activation functions between residual blocks, but no convolutional layers between them. The first residual block of each stage uses a 1x1 convolutional layer to convert the number of input channels to the number of output channels for summation with subsequent residual blocks.

[0075] Vision Transformer (ViT) is a deep learning model based on the Transformer architecture for image recognition and computer vision tasks. Unlike traditional convolutional neural networks (CNNs), ViT directly treats the image as a sequential input and utilizes a self-attention mechanism to process the pixel relationships within the image.

[0076] ViT works by dividing an image into a series of patches and converting each patch into a vector representation as an input sequence. These vectors are then processed by a multi-layered Transformer encoder, which incorporates self-attention mechanisms and feedforward neural network layers. This captures the contextual dependencies at different locations within the image. Finally, specific visual tasks can be performed by classifying or regressing the output of the Transformer encoder.

[0077] like Figure 3 As shown, vit applies image patches to the transformer. CNNs use the sliding window concept to perform convolutions on the image using kernels to obtain feature maps. To make the image resemble the input sequence of NLP, we can first divide the image into patches, then flatten these patches before inputting them into the network (thus creating an image sequence), then extract features through the transformer, and finally classify these features using an MLP. Essentially, this can be understood as replacing the backbone with a transformer in traditional CNN classification tasks.

[0078] Optionally, determining the first positioning reference point based on blood vessels in the first skin image includes:

[0079] The position of each blood vessel is determined in the first skin image. Based on the position of each blood vessel, the blood vessels that intersect are identified, and the intersection of the intersecting blood vessels is used as the first positioning reference point. The first positioning reference point in the first skin image contains at least three points.

[0080] The determination of the second positioning reference point based on blood vessels in the second skin image includes:

[0081] The position of each blood vessel is determined in the second skin image. Based on the position of each blood vessel, the intersecting blood vessels are identified, and the intersection of the intersecting blood vessels is used as the second positioning reference point. The second positioning reference point in the second skin image contains at least three points.

[0082] Optionally, determining the original location of the melanoma in the first skin image based on the first positioning reference point includes:

[0083] A first planar coordinate system is constructed using the first positioning reference point, a first positional mapping relationship is established between the first skin image and the first planar coordinate system, and the position of the melanoma in the first skin image is determined.

[0084] The position of the melanoma in the first skin image is mapped to the first planar coordinate system using the first mapping relationship to obtain the position of the melanoma in the first planar coordinate system, and the position of the melanoma in the first planar coordinate system is taken as the original position of the melanoma.

[0085] Determining the location of melanoma changes in the second skin image based on the second positioning reference point includes:

[0086] A second planar coordinate system is constructed using the second positioning reference point, a second positional mapping relationship is established between the second skin image and the second planar coordinate system, and the position of the melanoma in the second skin image is determined.

[0087] The location of the melanoma in the second skin image is mapped to the second planar coordinate system using the second mapping relationship to obtain the location of the melanoma in the second planar coordinate system, and the location of the melanoma in the second planar coordinate system is used as the change location of the melanoma.

[0088] Optionally, mapping the location of the melanoma change onto the first skin image based on the first and second positioning reference points includes:

[0089] Determine whether the first positioning reference point in the first plane coordinate system and the second positioning reference point in the second plane coordinate system are intersections of the same blood vessel. If not, reconstruct the first plane coordinate system and / or the second plane coordinate system until the first positioning reference point in the first plane coordinate system and the second positioning reference point in the second plane coordinate system are intersections of the same blood vessel. Then, redetermine the original location and the changed location of the melanoma. If yes, map the changed location of the melanoma in the second plane coordinate system to the first plane coordinate system to obtain the changed location of the melanoma in the first plane coordinate system.

[0090] Optionally, methods for determining whether the first positioning reference point in the first planar coordinate system and the second positioning reference point in the second planar coordinate system are intersections of the same blood vessel include:

[0091] Extract the first shape information of the blood vessel corresponding to the first positioning reference point used to construct the first planar coordinate system, and extract the second shape information of the blood vessel corresponding to the second positioning reference point used to construct the second planar coordinate system;

[0092] The first shape information is compared with the second shape information to determine whether the first shape information and the second shape information match. If they match, the first positioning reference point for constructing the first planar coordinate system and the second positioning reference point for constructing the second planar coordinate system are determined to be the same blood vessel. If they do not match, the first positioning reference point for constructing the first planar coordinate system and the second positioning reference point for constructing the second planar coordinate system are determined to be different blood vessels.

[0093] The process of comparing the first shape information with the second shape information includes enlarging, reducing, or rotating the first shape information and / or the second shape information.

[0094] Optionally, determining the distance between the original location of the melanoma and the changed location of the melanoma in the first image includes:

[0095] The position of the changed location of the melanoma in the first plane coordinate system is compared with the original position of the melanoma to obtain the first distance information, and the first distance information is used as the distance between the original position of the melanoma and the changed location of the melanoma.

[0096] Optionally, determining the location shift of the melanoma lesion based on the distance between the original location of the melanoma and the changed location of the melanoma includes:

[0097] The first distance information is compared with a preset first threshold. If the first distance information is less than or equal to the preset first threshold, it is determined that the location of the melanoma lesion has not shifted. If the first distance information is greater than the preset first threshold, the second distance information between the original location of the melanoma and all the first positioning reference points is determined. At the same time, based on the position of the changed location of the melanoma in the first plane coordinate system, the third distance information between the changed location of the melanoma and all the first positioning reference points is determined. The difference between the second distance information and the third distance information is calculated. If the difference is less than or equal to the preset second threshold, it is determined that the location of the melanoma lesion has not shifted. If the difference is greater than the preset second threshold, it is determined that the location of the melanoma lesion has shifted.

[0098] This application also provides a system for determining the location offset of melanoma lesions, including a processor and a memory;

[0099] Memory, used to store computer programs;

[0100] When a processor executes a program stored in memory, it implements any of the steps described in the method for determining the location offset of a melanoma lesion.

[0101] The melanoma lesion location offset determination system described above can realize various embodiments of the electro-melanoma lesion location offset determination method described above, and can achieve the same beneficial effects. Here, it will not be elaborated further.

[0102] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method for determining the location deviation of melanoma lesions, characterized in that, include: Obtain a first skin image containing melanoma lesions, and extract blood vessels and melanoma from the first skin image; The first positioning reference point is determined based on the blood vessels on the first skin image, and the original location of the melanoma in the first skin image is determined based on the first positioning reference point. After a preset time interval, a second skin image containing the melanoma lesion in the first skin image is acquired, and blood vessels and melanoma are extracted from the second skin image. The second positioning reference point is determined based on the blood vessels on the second skin image, and the location of the melanoma change in the second skin image is determined based on the second positioning reference point. Based on the first positioning reference point and the second positioning reference point, the changed location of the melanoma is mapped onto the first skin image, and the distance between the original location of the melanoma and the changed location of the melanoma is determined in the first skin image; The location shift of the melanoma lesion is determined based on the distance between the original location of the melanoma and the changed location of the melanoma.

2. The method for determining the location offset of melanoma lesions according to claim 1, characterized in that, Extracting blood vessels from skin images, including: The skin containing melanoma lesions was irradiated with infrared light, and digital image information of the reflected infrared light was collected as a skin image. The skin image is enhanced by RGB channel enhancement to obtain an enhanced image, and the blood vessels on the skin image are extracted after noise reduction preprocessing of the enhanced image.

3. The method for determining the location offset of melanoma lesions according to claim 1, characterized in that, Extracting melanoma from skin images, including: We constructed ResNet101 and Vit-Transformer neural network models and obtained training and validation datasets for melanoma through manual annotation. A melanoma recognition model was constructed by combining the ResNet101 neural network model and the Vit-Transformer neural network model. The constructed melanoma recognition model was then trained using the training dataset and the validation dataset to obtain the trained melanoma recognition model. The skin image is input into the trained melanoma recognition model, and the trained melanoma recognition model is used to extract melanoma from the skin image.

4. The method for determining the location offset of melanoma lesions according to claim 1, characterized in that, The determination of the first positioning reference point based on blood vessels in the first skin image includes: The position of each blood vessel is determined in the first skin image. Based on the position of each blood vessel, the blood vessels that intersect are identified, and the intersection of the intersecting blood vessels is used as the first positioning reference point. The first positioning reference point in the first skin image contains at least three points. The determination of the second positioning reference point based on blood vessels in the second skin image includes: The position of each blood vessel is determined in the second skin image. Based on the position of each blood vessel, the intersecting blood vessels are identified, and the intersection of the intersecting blood vessels is used as the second positioning reference point. The second positioning reference point in the second skin image contains at least three points.

5. The method for determining the location offset of melanoma lesions according to claim 4, characterized in that, Determining the original location of the melanoma in the first skin image based on the first positioning reference point includes: A first planar coordinate system is constructed using the first positioning reference point, a first positional mapping relationship is established between the first skin image and the first planar coordinate system, and the position of the melanoma in the first skin image is determined. The position of the melanoma in the first skin image is mapped to the first planar coordinate system using the first mapping relationship to obtain the position of the melanoma in the first planar coordinate system, and the position of the melanoma in the first planar coordinate system is taken as the original position of the melanoma. Determining the location of melanoma changes in the second skin image based on the second positioning reference point includes: A second planar coordinate system is constructed using the second positioning reference point, a second positional mapping relationship is established between the second skin image and the second planar coordinate system, and the position of the melanoma in the second skin image is determined. The location of the melanoma in the second skin image is mapped to the second planar coordinate system using the second mapping relationship to obtain the location of the melanoma in the second planar coordinate system, and the location of the melanoma in the second planar coordinate system is used as the change location of the melanoma.

6. The method for determining the location offset of melanoma lesions according to claim 5, characterized in that, Mapping the location of the melanoma change onto the first skin image based on the first and second positioning reference points includes: Determine whether the first positioning reference point in the first plane coordinate system and the second positioning reference point in the second plane coordinate system are intersections of the same blood vessel. If not, reconstruct the first plane coordinate system and / or the second plane coordinate system until the first positioning reference point in the first plane coordinate system and the second positioning reference point in the second plane coordinate system are intersections of the same blood vessel. Then, redetermine the original location and the changed location of the melanoma. If yes, map the changed location of the melanoma in the second plane coordinate system to the first plane coordinate system to obtain the changed location of the melanoma in the first plane coordinate system.

7. The method for determining the location offset of melanoma lesions according to claim 6, characterized in that, Methods for determining whether the first positioning reference point in the first planar coordinate system and the second positioning reference point in the second planar coordinate system are intersection points of the same blood vessel include: Extract the first shape information of the blood vessel corresponding to the first positioning reference point used to construct the first planar coordinate system, and extract the second shape information of the blood vessel corresponding to the second positioning reference point used to construct the second planar coordinate system; The first shape information is compared with the second shape information to determine whether the first shape information and the second shape information match. If they match, the first positioning reference point for constructing the first planar coordinate system and the second positioning reference point for constructing the second planar coordinate system are determined to be the same blood vessel. If they do not match, the first positioning reference point for constructing the first planar coordinate system and the second positioning reference point for constructing the second planar coordinate system are determined to be different blood vessels. The process of comparing the first shape information with the second shape information includes enlarging, reducing, or rotating the first shape information and / or the second shape information.

8. The method for determining the location deviation of melanoma lesions according to claim 7, characterized in that, Determining the distance between the original location of the melanoma and the changed location of the melanoma in the first skin image includes: The position of the changed location of the melanoma in the first plane coordinate system is compared with the original position of the melanoma to obtain the first distance information, and the first distance information is used as the distance between the original position of the melanoma and the changed location of the melanoma.

9. The method for determining the location offset of melanoma lesions according to claim 8, characterized in that, Determining the location shift of a melanoma lesion based on the distance between the original location of the melanoma and the changed location of the melanoma includes: The first distance information is compared with a preset first threshold. If the first distance information is less than or equal to the preset first threshold, it is determined that the location of the melanoma lesion has not shifted. If the first distance information is greater than the preset first threshold, the second distance information between the original location of the melanoma and all the first positioning reference points is determined. At the same time, based on the position of the changed location of the melanoma in the first plane coordinate system, the third distance information between the changed location of the melanoma and all the first positioning reference points is determined. The difference between the second distance information and the third distance information is calculated. If the difference is less than or equal to the preset second threshold, it is determined that the location of the melanoma lesion has not shifted. If the difference is greater than the preset second threshold, it is determined that the location of the melanoma lesion has shifted.

10. A system for determining the location offset of melanoma lesions, characterized in that, Including processor and memory; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-9.

Images