An intelligent tumor image processing system

Abstract

The present invention discloses an intelligent tumor image processing system, including an image acquisition module, a tumor image enhancement module, a tumor image segmentation module, and a tumor image processing module. The present invention belongs to the field of image processing, specifically referring to an intelligent tumor image processing system. This solution introduces the attenuation effect and noise characteristics in the imaging process to enhance the repair ability of tumor images; introduces structural loss and boundary loss to enhance the boundary details of the tumor region. By alternately enhancing the global features and local features of the tumor region, the details of the tumor image are gradually optimized to improve the detection ability of the tumor region; through multi-scale feature enhancement and bilateral filtering, combined with multi-scale convolution and pooling, the edges of the tumor region are retained and background noise is removed. At the same time, through adjacent feature aggregation, the accuracy of the tumor region boundary is improved, and the interference of the fuzzy region is reduced; thereby restoring tumor details, enhancing boundary clarity, and improving the tumor image processing effect.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and specifically refers to an intelligent tumor image processing system. Background Art

[0002] The tumor image processing system is an image processing tool based on computer vision and artificial intelligence technologies, aiming to highlight the key areas of tumor images. However, general tumor image processing systems have problems such as easy loss of details and blurred boundaries when processing low-quality and noise-interfered tumor images, and poor processing accuracy due to the noise brought by imaging devices; for small-sized tumors, general tumor image processing systems are difficult to accurately capture the boundaries, and the effect of processing fuzzy and unobvious tumor areas is poor, resulting in poor tumor image processing effects. Summary of the Invention

[0003] In view of the above situation, to overcome the defects of the prior art, the present invention provides an intelligent tumor image processing system. Aiming at the problems that general tumor image processing systems are prone to detail loss and boundary blur when processing low-quality and noise-interfered tumor images, and the noise brought by imaging devices leads to poor processing accuracy, this solution uses structural loss and background light estimation to remove noise and restore details; introduces the attenuation effect and noise characteristics in the imaging process to enhance the repair ability of tumor images; introduces structural loss and boundary loss to enhance the boundary details of the tumor area and prevent artifacts and noise in the image from affecting subsequent processing; thereby improving the accuracy of tumor image processing. Aiming at the problems that general tumor image processing systems are difficult to accurately capture the boundaries for small-sized tumors, and the effect of processing fuzzy and unobvious tumor areas is poor, resulting in poor tumor image processing effects, this solution alternately enhances the global features and local features of the tumor area, gradually optimizes the details of the tumor image, and improves the detection ability of the tumor area; the global features are used to capture the overall shape of the tumor, while the local features focus on the detailed parts, especially the tumor boundary; through multi-scale feature enhancement and bilateral filtering, combined with multi-scale convolution and pooling, the edges of the tumor area are retained and background noise is removed, and at the same time, through adjacent feature aggregation, the accuracy of the tumor area boundary is improved, and the interference of fuzzy areas is reduced; thereby restoring tumor details, enhancing boundary clarity, and improving tumor image processing effects.

[0004] The technical solution adopted by the present invention is as follows: An intelligent tumor image processing system provided by the present invention includes an image acquisition module, a tumor image enhancement module, a tumor image segmentation module, and a tumor image processing module;

[0005] The image acquisition module acquires historical tumor image data;

[0006] The tumor image enhancement module enhances low-quality tumor images, simulates the degradation process, and generates high-quality tumor images;

[0007] The tumor image segmentation module segments the enhanced tumor images through progressive enhancement, feature aggregation, and degraded feature selection;

[0008] The tumor image processing module performs enhanced segmentation on real-time acquired tumor images, thereby realizing tumor image processing.

[0009] Furthermore, in the image acquisition module, the historical tumor image data includes low-quality tumor images and high-quality tumor images; and tumor regions are delimited for the historical tumor image data.

[0010] Furthermore, the tumor image enhancement module is based on a generative adversarial network, inputs a low-quality tumor image I, and outputs a high-quality tumor image J as the target image; specifically including the following:

[0011] Tumor image degradation simulation unit; introducing the attenuation effect suffered by the tumor image during the imaging process and the noise characteristics of the imaging device; the tumor image degradation simulation is expressed as: ; ; where T is the transmission map, used to describe the attenuation degree of the tumor image during the imaging process; A is the background light; is the noise of the imaging device; and are the weighting coefficients of the noise; is Gaussian noise; is salt-and-pepper noise; and are the noise probabilities;

[0012] Tumor image enhancement inversion unit; accurately estimating the background light according to the noise distribution of the tumor image; introducing low-frequency background noise by estimating the transmission map, and the background light estimation is expressed as: ; the transmission map estimation is expressed as: ; where, is the background light estimated during the enhancement process; GB(·) is Gaussian blur; is the transmission map estimated during the enhancement process; is the Sigmoid activation function; and are 7×7 convolution and 3×3 convolution respectively; and are adjustment parameters; is the low-frequency background noise;

[0013] Tumor image degradation estimation unit; the transmission map and background light estimations during the degradation process are respectively expressed as: ; ; where, and are the estimated transmission map and background light during the degradation process respectively; Max(·) is the max pooling operation; is the feature extracted from the high-quality tumor image J; is residual learning;

[0014] Loss function design unit; construct the adversarial loss, expressed as: ; ; construct the cycle consistency loss, expressed as: ; construct the structure loss, expressed as: ; ; construct the tumor boundary loss , expressed as: ; the final loss is expressed as: ; where, L1 and L2 are the adversarial losses of I and J respectively; D(·) is the discriminator; is the low-quality image enhanced by the generator; is the high-quality image processed by the degradation network; and are the images restored by enhancing the degradation process; is the L1 norm; and are the losses obtained by weighted averaging all the images in the low-quality tumor image and high-quality tumor image datasets respectively; and are the losses of the estimated transmission map and background light respectively; and are the estimated transmission maps during the enhancement process and the degradation process respectively; and are the estimated background lights during the enhancement process and the degradation process respectively; , , and are the loss weights; r is the pixel point index; is the gradient difference between I and J at the pixel point r.

[0015] Furthermore, the tumor image segmentation module processes the enhanced tumor image, specifically including the following:

[0016] Progressive enhancement unit; alternately enhance the global features of the tumor position and morphology and the local features of the tumor boundary, and switch the processing of global and local features by adjusting the input order of the feature maps; the progressive enhancement is expressed as: ; ; ; where, and are the global feature enhancement result and the local feature enhancement result generated during the iterative process respectively, k is the number of iterations; α and β are parameters for adjusting the fusion of global and local features; s(·) is the fused feature; F(·) is the fusion operation; R(·) is the transformation operation; gd and ad represent the global feature and the local feature respectively;

[0017] Feature aggregation unit; performs feature aggregation and combines context information; introduces multi-scale feature enhancement and bilateral filtering; Feature aggregation is expressed as: ; ; ; ; where, is the result of the current feature and the feature of the previous layer after adjacent feature aggregation; and are the weighted coefficients of feature map fusion; is the feature of the current layer; is another adjacent feature of the current layer; is the feature map obtained in the previous layer; is the output feature map after pooling operation; is the feature fusion operation; is the upsampled feature map; is the upsampling operation; Concat(·) is the concatenation fusion; EP(·) is the bilateral filtering; 、 and are the adjustment coefficients; U and Q are the total numbers of scales of convolution and pooling respectively, u and q are the corresponding indices; and are the convolution and pooling operations of the corresponding scales respectively; and are the scale weighted coefficients;

[0018] Degraded feature selection unit; repairs the tumor image and preserves the phase information; removes interference through Fourier transform; restores the structural information through the phase spectrum; is expressed as: ; The frequency domain feature is expressed as: ; The amplitude spectrum and the phase spectrum are expressed as: ; ; Introduces wavelet transform, and the amplitude reconstruction is expressed as: ; The amplitude error is expressed as: ; where, T(·) is the image after Fourier transform, u and v are the frequency domain coordinates; f(·) is the pixel value of the tumor image in the spatial domain, x and y are the spatial coordinates; M and N are the spatial dimensions; R(·) and I(·) are the real and imaginary parts of the frequency domain respectively; A(·) is the amplitude spectrum; P(·) is the phase spectrum; is the reconstructed amplitude spectrum; is the convolution kernel; j is the imaginary unit; is the wavelet reconstruction enhancement coefficient; WT(·) is the wavelet transform operation;

[0019] Segmentation loss function construction unit; in the segmentation task of tumor images, each iteration includes: gradually optimizing the global and local features of tumor images through progressive enhancement; refining the features of the tumor region through feature aggregation; repairing the noise and image degradation in tumor images based on degraded feature selection to restore structural information; and obtaining the loss and the loss of each iteration are weighted to obtain the segmentation loss function and training is completed based on historical tumor image data; the segmentation loss function is expressed as: ; ; ; where S is the total number of iterations, and s is the iteration number index; is the iteration weight; is the iteration adjustment factor; is the current average iteration loss; y is the true tumor region label, i.e., whether it is a tumor region; p is the predicted tumor region label; A is the segmented region; B is the true tumor region.

[0020] Furthermore, after the tumor image enhancement module and the tumor image segmentation module are trained, the tumor image processing module obtains tumor image data in real time, enhances and segments the tumor image, and realizes tumor image processing.

[0021] The beneficial effects achieved by the present invention using the above solution are as follows:

[0022] (1) Aiming at the problems that general tumor image processing systems are prone to detail loss and boundary blurring when processing low-quality and noise-interfered tumor images, and the noise caused by imaging devices leads to poor processing accuracy, this solution uses structural loss and background light estimation to remove noise and restore details; introduces the attenuation effect and noise characteristics in the imaging process to enhance the repair ability of tumor images; introduces structural loss and boundary loss to enhance the boundary details of the tumor region and prevent artifacts and noise in the image from affecting subsequent processing; thereby improving the accuracy of tumor image processing.

[0023] (2)Regarding the problem that the general tumor image processing system has difficulty in accurately capturing the boundaries of small-sized tumors, poor processing effect for blurred and unobvious tumor regions, and thus poor tumor image processing effect, this solution enhances the global features and local features of the tumor region alternately, gradually optimizes the details of the tumor image, and improves the detection ability of the tumor region; the global features are used to capture the overall shape of the tumor, while the local features focus on the details, especially the tumor boundary; through multi-scale feature enhancement and bilateral filtering, combined with multi-scale convolution and pooling, the edges of the tumor region are retained and the background noise is removed. At the same time, through adjacent feature aggregation, the accuracy of the tumor region boundary is improved, and the interference of the blurred region is reduced; thus, the tumor details are restored, the boundary clarity is enhanced, and the tumor image processing effect is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a schematic flowchart of an intelligent tumor image processing system provided by the present invention;

[0025] Figure 2 is a schematic flowchart of the tumor image enhancement module;

[0026] Figure 3 is a schematic flowchart of the tumor image segmentation module.

[0027] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention, and do not constitute a limitation to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0029] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. 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 invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation to the present invention.

[0030] Example 1, refer to Figure 1 , an intelligent tumor image processing system provided by the present invention includes an image acquisition module, a tumor image enhancement module, a tumor image segmentation module, and a tumor image processing module;

[0031] The image acquisition module acquires historical tumor image data and sends the data to the tumor image enhancement module.

[0032] The tumor image enhancement module enhances low-quality tumor images, simulates the degradation process, generates high-quality tumor images, and sends the data to the tumor image segmentation module.

[0033] The tumor image segmentation module segments the enhanced tumor images through progressive enhancement, feature aggregation, and degraded feature selection, and sends the data to the tumor image processing module.

[0034] The tumor image processing module enhances and segments the real-time acquired tumor images, thereby realizing tumor image processing.

[0035] Example 2, refer to Figure 1 , based on the above example, in the image acquisition module, the historical tumor image data includes low-quality tumor images and high-quality tumor images, and the tumor area is delimited for the historical tumor image data.

[0036] Example 3, refer to Figure 1 and Figure 2 , based on the above example, the tumor image enhancement module is based on a generative adversarial network, takes a low-quality tumor image I as the input, and outputs a high-quality tumor image J as the target image, specifically including the following:

[0037] Tumor image degradation simulation unit; introducing the attenuation effect suffered by the tumor image during the imaging process and the noise characteristics of the imaging device; the tumor image degradation simulation is expressed as: ; ; where T is the transmission map, used to describe the attenuation degree of the tumor image during the imaging process; A is the background light, representing the background light or noise in the image that has nothing to do with the tumor; is the noise of the imaging device; and are the weighting coefficients of the noise; is Gaussian noise; is salt-and-pepper noise; and are the noise probabilities;

[0038] Tumor image enhancement inversion unit; accurately estimating the background light according to the noise distribution of the tumor image, which helps to generate a clear denoised image; by estimating the transmission map, it helps to improve the boundary blur of the tumor area and enhance the visibility of the tumor tissue; introducing low-frequency background noise, the background light estimation is expressed as: ; the transmission map estimation is expressed as: ; where is the background light estimated during the enhancement process; GB(·) is Gaussian blur; is the transmission map estimated during the enhancement process; is the Sigmoid activation function; and are 7×7 convolution and 3×3 convolution respectively; and are the adjustment parameters; is the low-frequency background noise;

[0039] Tumor image degradation estimation unit; By simulating the degradation process, it can generate low-quality tumor images with a more realistic sense and promote the generation of higher-quality tumor images during the enhancement process; The transmission map and background light estimation during the degradation process are respectively expressed as: ; ; where, and are the transmission map and background light estimated during the degradation process respectively; Max(·) is the max pooling operation; is the feature extracted from the high-quality tumor image J; is the residual learning;

[0040] Loss function design unit; By increasing the weight of the structural loss, it can better repair the tumor area; And the structural loss can help remove artifacts and noise in the tumor image and improve the clarity of the tumor image. Especially in low-quality tumor images, it can restore more delicate details of the tumor area; Construct the adversarial loss, expressed as: ; ; Construct the cycle consistency loss, expressed as: ; Construct the structural loss, expressed as: ; ; Construct the tumor boundary loss , expressed as: ; The final loss is expressed as: ; where, L1 and L2 are the adversarial losses of I and J respectively; D(·) is the discriminator; is the low-quality image enhanced by the generator; is the high-quality image processed by the degradation network; and are the images restored by enhancing the degradation process; is the L1 norm; and are the losses obtained by weighted averaging all the images in the low-quality tumor image and high-quality tumor image datasets respectively; and are the losses of the estimated transmission map and background light respectively; and They are the estimated transmission maps during the enhancement process and the degradation process respectively; and They are the estimated background lights during the enhancement process and the degradation process respectively; 、 、 and are loss weights; r is the pixel index; is the gradient difference between I and J at pixel r.

[0041] By performing the above operations, for the general tumor image processing system, when processing tumor images with low quality and noise interference, problems such as detail loss, boundary blurring, and poor processing accuracy caused by the noise brought by the imaging device are likely to occur. This solution uses structural loss and background light estimation to remove noise and restore details; introduces the attenuation effect and noise characteristics in the imaging process to enhance the repair ability of tumor images; introduces structural loss and boundary loss to enhance the boundary details of the tumor area and prevent artifacts and noise in the image from affecting subsequent processing; thereby improving the accuracy of tumor image processing.

[0042] Example 4, refer to Figure 1 and Figure 3 Based on the above example, the tumor image segmentation module processes the enhanced tumor image, specifically including the following content:

[0043] Progressive enhancement unit; Tumor images usually contain complex edges and small-size features. By alternately enhancing the global features of the tumor position and morphology and the local features of the tumor boundary, the detection ability of the tumor area is enhanced; and by adjusting the input order of the feature maps to switch the processing of global and local features, the tumor edges and detail features are better captured; expressed as: ; ; ; where, and are the global feature enhancement result and the local feature enhancement result generated during the iterative process respectively, k is the number of iterations; α and β are parameters for adjusting the fusion of global and local features; s(·) is the fused feature; F(·) is the fusion operation; R(·) is the transformation operation; gd and ad represent global features and local features respectively;

[0044] Feature aggregation unit; for small-sized, blurred, and early-stage tumors, multi-scale processing can help capture fine morphological changes and insignificant tumor features; tumor images often have irregular shapes, and adjacent feature aggregation is used to improve the accuracy of the tumor region boundary and reduce the interference of blurred areas; capture tiny tumor features and combine feature aggregation with context information; introduce multi-scale feature enhancement and bilateral filtering to retain the edges of the tumor region and reflect the details of the tumor image; the feature aggregation is expressed as: ; ; ; ; where, is the result of aggregating the current feature and the feature of the previous layer through adjacent feature aggregation; and are the weighting coefficients for feature map fusion; is the feature of the current layer; is another adjacent feature of the current layer; is the feature map obtained in the previous layer; is the output feature map after pooling operation; is the feature fusion operation; is the upsampled feature map; is the upsampling operation; Concat(·) is concatenation fusion; EP(·) is bilateral filtering; 、 and are adjustment coefficients; U and Q are the total numbers of scales for convolution and pooling respectively, and u and q are the corresponding indices; and are the convolution and pooling operations for the corresponding scales respectively; and are the scale weighting coefficients;

[0045] Degraded feature selection unit; repair tumor images and maintain phase information; for low-quality or noise-interfered tumor images, remove interference through Fourier transform to improve the image quality and make tumor segmentation more accurate; restore structural information through the phase spectrum and enhance the morphological features of the tumor, especially in the case of missing details; expressed as: ; The frequency-domain feature is expressed as: ; The amplitude spectrum and phase spectrum are expressed as: ; ; Introduce wavelet transform, and the amplitude reconstruction is expressed as: ; The amplitude error is expressed as: ; where \(T(\cdot)\) is the image after Fourier transform, \(u\) and \(v\) are frequency domain coordinates; \(f(\cdot)\) is the pixel value of the tumor image in the spatial domain, \(x\) and \(y\) are spatial coordinates; \(M\) and \(N\) are spatial dimensions; \(R(\cdot)\) and \(I(\cdot)\) are the real and imaginary parts in the frequency domain respectively; \(A(\cdot)\) is the amplitude spectrum; \(P(\cdot)\) is the phase spectrum; is the reconstructed amplitude spectrum; is the convolution kernel; \(j\) is the imaginary unit; is the wavelet reconstruction enhancement coefficient; \(WT(\cdot)\) is the wavelet transform operation;

[0046] Segmentation loss function construction unit; in the segmentation task of tumor images, each iteration includes: gradually optimizing the global and local features of the tumor image through progressive enhancement; refining the features of the tumor region through feature aggregation; repairing the noise and image degradation in the tumor image based on degenerate feature selection to restore the structural information; taking the loss after the end of the iteration and the loss in each iteration are weighted to obtain the segmentation loss function and complete the training based on the historical tumor image data; the segmentation loss function is expressed as: ; ; ; where \(S\) is the total number of iterations, and \(s\) is the iteration number index; is the iteration weight; is the iteration adjustment factor; is the current average iteration loss; \(y\) is the true tumor region label, i.e., whether it is a tumor region; \(p\) is the predicted tumor region label; \(A\) is the segmented region; \(B\) is the true tumor region.

[0047] By performing the above operations, for the general tumor image processing system, there is a problem that for small-sized tumors, it is difficult to accurately capture the boundaries, and the effect of processing fuzzy and unobvious tumor regions is poor, which in turn leads to poor tumor image processing effects. In this solution, the global and local features of the tumor region are alternately enhanced, the details of the tumor image are gradually optimized, and the detection ability of the tumor region is improved; the global features are used to capture the overall morphology of the tumor, while the local features focus on the details, especially the tumor boundary; through multi-scale feature enhancement and bilateral filtering, combined with multi-scale convolution and pooling, the edges of the tumor region are retained and the background noise is removed. At the same time, through adjacent feature aggregation, the accuracy of the tumor region boundary is improved, and the interference of the fuzzy region is reduced; thus, the tumor details are restored, the boundary clarity is enhanced, and the tumor image processing effect is improved.

[0048] Example Five, refer to Figure 1 , based on the above example, after the tumor image enhancement module and the tumor image segmentation module are trained, the tumor image processing module obtains tumor image data in real time, enhances and segments the tumor image, and realizes tumor image processing.

[0049] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0050] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention.

[0051] The above description of the present invention and its embodiments is not restrictive. What is shown in the drawings is only one of the embodiments of the present invention, and the actual structure is not limited thereto. In general, if those of ordinary skill in the art are inspired by it and, without departing from the gist of the present invention, design similar structural modes and embodiments to this technical solution without creative efforts, they shall fall within the protection scope of the present invention.

Claims

1. An intelligent tumor image processing system, characterized in that: The system includes an image acquisition module, a tumor image enhancement module, a tumor image segmentation module and a tumor image processing module; The image acquisition module acquires historical tumor image data; The tumor image enhancement module enhances the low-quality tumor image, simulates the degradation process, and generates a high-quality tumor image; The tumor image segmentation module segments the enhanced tumor image through progressive enhancement, feature aggregation and degenerate feature selection; The tumor image processing module performs enhanced segmentation on the tumor image collected in real time, thereby realizing tumor image processing; The tumor image enhancement module includes a tumor image degradation simulation unit; the attenuation effect of the tumor image during the imaging process and the noise characteristics of the imaging device are introduced; the tumor image degradation simulation is expressed as: ; ; Wherein, T is the transmission diagram, which is used to describe the attenuation degree of the tumor image during the imaging process; A is the background light; is the noise of the imaging device; and is the weighting coefficient of noise; is Gaussian noise; It’s salt and pepper noise; and is the noise probability; I and J are low-quality tumor images and high-quality tumor images, respectively; The tumor image segmentation module processes the enhanced tumor image, specifically including the following contents: Progressive enhancement unit; by alternately enhancing the global features of tumor location and morphology and the local features of tumor boundaries, and switching the processing of global and local features by adjusting the input order of feature maps; progressive enhancement is expressed as: ; ; ;in, and are the global feature enhancement results and local feature enhancement results generated in the iterative process, k is the number of iterations; α and β are parameters for adjusting the fusion of global and local features; s(·) is the fused feature; F(·) is the fusion operation; R(·) is the transformation operation; gd and ad represent the global feature and local feature, respectively; Feature aggregation unit; combine feature aggregation with context information; introduce multi-scale feature enhancement and bilateral filtering; feature aggregation is expressed as: ; ; ; ;in, It is the result of aggregating the current feature and the feature of the previous layer through adjacent features; and is the weight coefficient of feature map fusion; is the feature of the current layer; is another adjacent feature of the current layer; It is the feature map obtained in the previous layer; It is the output feature map after the pooling operation; It is a feature fusion operation; It is the feature map after upsampling; is an upsampling operation; Concat(·) is concatenation and fusion; EP(·) is bilateral filtering; , and is the adjustment coefficient; U and Q are the total number of scales of convolution and pooling, respectively, and u and q are the corresponding indices; and They are the convolution and pooling operations of corresponding scales respectively; and is the scale weighting coefficient; Degenerate feature selection unit; repair tumor image and maintain phase information; remove interference through Fourier transform; restore structural information through phase spectrum; expressed as: ; The frequency domain characteristics are expressed as: ; Amplitude spectrum and phase spectrum representation: ; ; Introducing wavelet transform, the amplitude reconstruction is expressed as: ; Amplitude error It is expressed as: ; Wherein, T(·) is the image after Fourier transformation, u and v are the frequency domain coordinates; f(·) is the pixel value of the tumor image in the spatial domain, x and y are the spatial coordinates; M and N are the spatial dimensions; R(·) and I(·) are the real and imaginary parts of the frequency domain, respectively; A(·) is the amplitude spectrum; P(·) is the phase spectrum; is the reconstructed amplitude spectrum; is the convolution kernel; j is the imaginary unit; is the wavelet reconstruction enhancement coefficient; WT(·) is the wavelet transform operation; Segmentation loss function building block.

2. The intelligent tumor image processing system according to claim 1, characterized in that: The tumor image enhancement module is based on a generative adversarial network, inputs a low-quality tumor image I, and outputs a high-quality tumor image J as a target image; specifically, it includes the following contents: Tumor image degradation simulation unit; Tumor image enhancement inversion unit; accurately estimate the background light according to the noise distribution of the tumor image; introduce low-frequency background noise by estimating the transmission map, and the background light estimation is expressed as: ; The transmission graph estimation is expressed as: ;in, is the estimated background light during the enhancement process; GB(·) is the Gaussian blur; is the estimated transmission map during the enhancement process; is the Sigmoid activation function; and They are 7×7 convolution and 3×3 convolution respectively; and is the adjustment parameter; It is low-frequency background noise; Tumor image degradation estimation unit; the transmission map and background light estimation during the degradation process are expressed as: ; ;in, and are the estimated transmission map and background light in the degradation process, respectively; Max(·) is the maximum pooling operation; are features extracted from high-quality tumor images J; It is residual learning; Loss function design unit; construct adversarial loss, expressed as: ; ; Construct cycle consistency loss, expressed as: ; Construct the structural loss, expressed as: ; ; Construct tumor boundary loss , expressed as: Final loss It is expressed as: ; Where L1 and L2 are the adversarial losses of I and J respectively; D(·) is the discriminator; is a low-quality image enhanced by the generator; It is a high-quality image after being processed by the degradation network; and is the image restored by enhancing the degradation process; is the L1 norm; and The loss is obtained by weighted averaging all images in the low-quality tumor image and high-quality tumor image datasets; and are the estimated transmission map and the loss of background light, respectively; and They are the estimated transmission diagrams during the enhancement process and the degradation process, respectively; and are the estimated background light during the enhancement process and the degradation process, respectively; , , and is the loss weight; r is the pixel index; is the gradient difference between I and J at pixel r.

3. The intelligent tumor image processing system according to claim 2, characterized in that: The loss function design unit is to construct adversarial loss, which is expressed as: ; ; Construct cycle consistency loss, expressed as: ; Construct the structural loss, expressed as: ; ; Construct tumor boundary loss , expressed as: Final loss It is expressed as: ; Where L1 and L2 are the adversarial losses of I and J respectively; D(·) is the discriminator; is a low-quality image enhanced by the generator; It is a high-quality image after being processed by the degradation network; and is the image restored by enhancing the degradation process; is the L1 norm; and The loss is obtained by weighted averaging all images in the low-quality tumor image and high-quality tumor image datasets; and are the estimated transmission map and the loss of background light, respectively; and They are the estimated transmission diagrams during the enhancement process and the degradation process, respectively; and are the estimated background light during the enhancement process and the degradation process, respectively; , , and is the loss weight; r is the pixel index; is the gradient difference between I and J at pixel r.

4. The intelligent tumor image processing system according to claim 3, characterized in that: The segmentation loss function construction unit is in the segmentation task of the tumor image, and each iteration includes: gradually optimizing the global and local features of the tumor image through progressive enhancement; refining the features of the tumor area through feature aggregation; repairing the noise and image degradation in the tumor image based on the degradation feature selection, and restoring the structural information; converting the loss after the iteration into With each iteration loss Weighted segmentation loss function , and completed the training based on historical tumor image data; the segmentation loss function is expressed as: ; ; ; Where S is the total number of iterations and s is the iteration index; is the iteration weight; is the iteration adjustment factor; is the current average iteration loss; y is the true tumor region label, i.e., whether it is a tumor region; p is the predicted tumor region label; A is the segmented region; and B is the true tumor region.

5. The intelligent tumor image processing system according to claim 1, characterized in that: The tumor image processing module acquires tumor image data in real time, enhances and segments the tumor image, and realizes tumor image processing after the training of the tumor image enhancement module and the tumor image segmentation module is completed.

6. The intelligent tumor image processing system according to claim 1, characterized in that: In the image acquisition module, the historical tumor image data includes low-quality tumor images and high-quality tumor images; and the tumor area is delineated for the historical tumor image data.

Images