A method for evaluating split kidney function of a child with hydronephrosis based on a magnetic resonance image

Abstract

The present application relates to the technical field of kidney function assessment, and particularly relates to a method for assessing the function of each kidney of a child with hydronephrosis based on magnetic resonance images, comprising the following steps: obtaining double-kidney magnetic resonance scanning data of the child with hydronephrosis, and obtaining clinical data and laboratory test data of the child with hydronephrosis; performing kidney region image segmentation and feature extraction in the double-kidney magnetic resonance scanning data to obtain morphological features, omics features and diffusion-weighted features of the hydronephrosis side and the contralateral kidney; and establishing a model for assessing the function of each kidney of the child with hydronephrosis by using the clinical data and the laboratory test data, and the morphological features, the omics features and the diffusion-weighted features of the hydronephrosis side and the contralateral kidney. The present application obtains the imaging data of the magnetic resonance plain scan and diffusion-weighted imaging of the child with hydronephrosis, analyzes the imaging features of each kidney by using an artificial intelligence algorithm, and realizes the assessment of the kidney function by using the analysis results in combination with the imaging features, the clinical biological information and the clinical features of the child.

Description

Technical Field

[0001] This invention relates to the field of renal function assessment technology, specifically to a method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging. Background Technology

[0002] Hydronephrosis is kidney damage caused by obstruction of urine flow from the kidney to the bladder. It is a common urological disease in children, with the most frequent cause being ureteropelvic junction obstruction (UPJO) due to intrinsic abnormalities in the proximal ureter. Hydronephrosis is not a static but dynamic process, and the optimal timing for treatment remains controversial, especially in pediatric patients. Assessment of split kidney function is a crucial factor in surgical treatment; previous reports have suggested that children with poor preoperative split kidney function have a poorer prognosis. Therefore, it is necessary to identify a non-invasive and accurate imaging biomarker for assessing split kidney function in children with hydronephrosis.

[0003] Assessing renal function using radionuclide renal scintigraphy is considered a reference standard and may aid in treatment decisions. However, radionuclide renal scintigraphy suffers from poor image quality and low soft tissue resolution. Furthermore, due to the use of radioactive tracers and ionizing radiation, it cannot be used for frequent follow-ups. Therefore, currently, renal function can be assessed using magnetic resonance imaging (MRI), which effectively avoids radionuclide and ionizing radiation.

[0004] However, while existing technologies can determine renal parenchymal features through magnetic resonance image analysis to assess hydronephrosis and renal function, the assessment process does not combine renal parenchymal features with laboratory indicators, clinical data, and omics characteristics for multimodal evaluation. The assessment features are singular and the accuracy is limited. At the same time, there is a lack of efficient and accurate renal parenchymal image segmentation methods in magnetic resonance image analysis, which affects the accuracy and efficiency of renal parenchymal feature extraction, ultimately impacting the efficiency and accuracy of renal function assessment. Summary of the Invention

[0005] The purpose of this invention is to provide a method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging, in order to solve the technical problems of existing multimodal assessments, which have limited accuracy due to their single assessment features, and the lack of efficient and accurate renal region image segmentation methods in magnetic resonance image analysis, which affects the accuracy and efficiency of renal parenchymal feature extraction.

[0006] To solve the above-mentioned technical problems, the present invention specifically provides the following technical solution:

[0007] A method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging includes the following steps:

[0008] Bilateral renal MRI scan data of children with hydronephrosis were obtained using T2WI and diffusion-weighted imaging DWI sequences, along with clinical and laboratory data.

[0009] In the bilateral renal magnetic resonance scan data, kidney region image segmentation and feature extraction were performed to obtain the morphological features, omics features and diffusion-weighted features of the hydronephrotic side and the contralateral kidney.

[0010] By using clinical and laboratory data, as well as morphological, omics, and diffusion-weighted features of the hydronephrosis side and contralateral kidney, an assessment model for the function of the efferent kidney in children with hydronephrosis was established.

[0011] As a preferred embodiment of the present invention, the method for kidney region image segmentation in the bilateral renal magnetic resonance scan data includes:

[0012] The bilateral renal magnetic resonance imaging data were used to segment the renal region image using a pre-established renal region image segmentation model framework to determine the hydronephrosis side renal region and the contralateral renal region.

[0013] The kidney region image segmentation model framework includes a hydronephrosis-side kidney enhancement module based on the U-net network, and two hydronephrosis-side kidney and contralateral kidney segmentation modules based on the Mask R-CNN network. The input of the hydronephrosis-side kidney enhancement module based on the U-net network is used as the input of the kidney region image segmentation model framework, and the output of the first hydronephrosis-side kidney and contralateral kidney segmentation module is used as the output of the kidney region image segmentation model framework.

[0014] The hydronephrosis-side kidney enhancement module is used to segment the hydronephrosis-side kidney region using the U-net network in the bilateral renal magnetic resonance scan data to obtain a hydronephrosis-side kidney mask image, and to fuse the hydronephrosis-side kidney mask image and the bilateral renal magnetic resonance scan data to obtain bilateral renal magnetic resonance scan data with hydronephrosis-side kidney enhancement.

[0015] The structural expression of the hydronephrosis-side kidney enhancement module is as follows:

[0016] ;

[0017] In the formula, Enhanced bilateral renal MRI data for the hydronephrosis-affected kidney. This is MRI data of both kidneys. The image shows a mask of the hydronephrotic kidney segmented using a U-net network. U-net is the U-net network itself. The enhancement coefficient of the hydronephrotic kidney;

[0018] ;

[0019] In the formula, GT is the actual masked image of the hydronephrotic kidney region. Enhanced image of the hydronephrotic kidney with masking. Image of the hydronephrotic kidney with masking. For Kullback-Leibler divergence calculation, This is a pixel overlay operation formula;

[0020] The first segmentation module for the hydronephrotic kidney and the contralateral kidney is used to segment the regions of the hydronephrotic kidney and the contralateral kidney in the enhanced bilateral renal magnetic resonance scan data of the hydronephrotic kidney using the Mask R-CNN network, so as to obtain the mask-enhanced image of the hydronephrotic kidney and the mask image of the contralateral kidney.

[0021] The structural expression for the segmentation module of the first hydronephrotic kidney and the contralateral kidney is as follows:

[0022] ;

[0023] In the formula, This is a masked image of the contralateral kidney. Mask R-CNN is used to enhance images of the kidney on the hydronephrotic side using a mask.

[0024] The second segmentation module for the hydronephrotic kidney and the contralateral kidney is used to segment the regions of the hydronephrotic kidney and the contralateral kidney in the bilateral renal magnetic resonance scan data using the Mask R-CNN network, so as to obtain the mask image of the hydronephrotic kidney and the mask image of the contralateral kidney.

[0025] The structural expression for the segmentation module of the second hydronephrotic kidney and the contralateral kidney is as follows:

[0026] ;

[0027] In the formula, Image of the kidney on the hydronephrotic side with a mask.

[0028] As a preferred embodiment of the present invention, the method for feature extraction from the bilateral renal magnetic resonance scanning data includes:

[0029] Morphological features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data obtained from T2WI sequences. The morphological features included: kidney thickness parameters, kidney volume parameters, and kidney diameter parameters.

[0030] Omics features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data obtained from T2WI sequences using the gray-level co-occurrence matrix method.

[0031] The diffusion-weighted features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data acquired from DWI sequences using the apparent diffusion coefficient ADC analysis method.

[0032] As a preferred embodiment of the present invention, the clinical data includes age, sex, height, weight, history of urinary tract infection, medical history, and symptoms.

[0033] As a preferred embodiment of the present invention, the laboratory test data includes nuclear medicine renography, blood eGFR, routine urine test and routine blood test.

[0034] As a preferred embodiment of the present invention, the method for constructing the evaluation model includes:

[0035] Clinical data and laboratory test data, as well as morphological, omics and diffusion-weighted features of the hydronephrotic side and the contralateral kidney, are used as inputs to the classification model, and the results of the kidney function assessment are used as the output of the classification model.

[0036] The classification model is trained to obtain an assessment model that outputs renal function assessment results based on clinical data, laboratory test data, and morphological, omics, and diffusion-weighted features of the hydronephrotic and contralateral kidneys.

[0037] As a preferred embodiment of the present invention, the method for extracting the diffusion-weighted features of the hydronephrotic kidney includes:

[0038] The hydronephrotic kidney region obtained from bilateral renal magnetic resonance imaging data acquired by DWI sequence is used as the input of the kidney region image segmentation model framework, and the renal parenchyma region in the hydronephrotic kidney is used as the output of the kidney region image segmentation model framework. The kidney region image segmentation model framework is then transferred to learn the renal parenchyma image segmentation model framework.

[0039] The renal parenchymal region in the hydronephrosis side kidney, determined by the mask-enhanced image of the renal parenchymal region of the hydronephrosis side kidney output by the renal parenchymal image segmentation model framework, is fused with the hydronephrosis side kidney region determined by the mask image of the hydronephrosis side kidney output by the renal region image segmentation model framework to obtain the region of interest enhanced hydronephrosis side kidney region. Apparent diffusion coefficient ADC analysis is then performed on the region of interest enhanced hydronephrosis side kidney region to obtain the diffusion-weighted features of the hydronephrosis side kidney.

[0040] The renal parenchyma image segmentation model framework includes a renal parenchyma region enhancement module based on the U-net network, and two renal parenchyma region segmentation modules for hydronephrotic kidneys based on the Mask R-CNN network. The input of the renal parenchyma region enhancement module based on the U-net network is used as the input of the renal parenchyma image segmentation model framework, and the output of the first hydronephrotic kidney renal parenchyma region segmentation module is used as the output of the renal parenchyma image segmentation model framework.

[0041] The renal parenchyma enhancement module is used to segment the renal parenchyma region in the hydronephrotic kidney region using the U-net network to obtain a renal parenchyma mask image of the hydronephrotic kidney, and to fuse the renal parenchyma mask image of the hydronephrotic kidney and the hydronephrotic kidney region to obtain a hydronephrotic kidney region with enhanced renal parenchyma.

[0042] The structural expression of the renal parenchyma enhancement module is as follows:

[0043] ;

[0044] In the formula, The renal parenchyma enhancement module outputs an enhanced version of the hydronephrotic kidney region. For images corresponding to the masked enhancement of the hydronephrosis-side kidney The area of ​​the kidney on the side with hydronephrosis was identified. This is a mask image of the renal parenchyma region of the hydronephrotic kidney obtained by segmentation using a U-net network. U-net is the U-net network. The enhancement coefficient of the renal parenchyma region;

[0045] ;

[0046] In the formula, GT en This is a true masked image of the renal parenchyma region of the hydronephrosis-related kidney. Masked enhanced image of the renal parenchyma region of the hydronephrosis-related kidney. This is a masked image of the renal parenchyma region of the hydronephrosis-related kidney. For Kullback-Leibler divergence calculation;

[0047] The first hydronephrotic kidney parenchyma segmentation module is used to segment the renal parenchyma region in the hydronephrotic kidney region with enhanced renal parenchyma region using the Mask R-CNN network, and obtain the mask-enhanced image of the hydronephrotic kidney parenchyma region.

[0048] The structural expression for the segmentation module of the renal parenchyma region of the first hydronephrotic kidney is:

[0049] ;

[0050] In the formula, Masked enhanced image of the renal parenchyma region of the hydronephrosis-related kidney. This refers to the Mask R-CNN network.

[0051] The second hydronephrotic kidney parenchyma segmentation module is used to segment the renal parenchyma region in the hydronephrotic kidney region using the Mask R-CNN network to obtain a mask image of the renal parenchyma region of the hydronephrotic kidney.

[0052] The structural expression for the segmentation module of the renal parenchyma region of the second hydronephrotic kidney is as follows:

[0053] ;

[0054] In the formula, This is a masked image of the renal parenchyma region of the kidney on the hydronephrosis side.

[0055] As a preferred embodiment of the present invention, the method for extracting the diffusion-weighted features of the contralateral kidney includes:

[0056] Apparent diffusion coefficient ADC analysis was performed on the contralateral kidney region determined by the contralateral kidney mask image output by the kidney region image segmentation model framework to obtain the diffusion-weighted features of the contralateral kidney.

[0057] As a preferred embodiment of the present invention, the diffusion-weighted features include mean, 5th, 25th, 50th, 75th and 90th percentiles, heterogeneity, skewness, kurtosis and entropy.

[0058] In a preferred embodiment of the present invention, the apparent diffusion coefficient ADC analysis method generates ADC maps of the hydronephrotic kidney region and the contralateral kidney region using a single exponential model. The single exponential model analysis formula is as follows:

[0059] ;

[0060] In the formula, S(b) is the DWI signal value at a specified b value when diffusion exists in the region, S0 is the DWI signal value when diffusion does not exist in the region, and b is the b value, which is used to determine the degree of diffusion motion weighting in the DWI signal.

[0061] Compared with the prior art, the present invention has the following advantages:

[0062] This invention acquires MRI plain scan and diffusion-weighted imaging data of children with hydronephrosis, and uses artificial intelligence algorithms to perform renal imaging feature analysis on the image data. By combining the analysis results with imaging features, as well as the child's clinical biological information and clinical characteristics, renal function is assessed. This provides assistance for the formulation of subsequent clinical management plans and clinical decision-making for children with hydronephrosis, making it easier for doctors to understand the dynamic changes in the renal parenchyma and the progression of the disease, and thus adjust the treatment plan in a timely manner to improve the prognosis. Attached Figure Description

[0063] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0064] Figure 1 Flowchart of a method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging, provided in an embodiment of the present invention;

[0065] Figure 2 A block diagram of a renal function assessment system for children with hydronephrosis based on magnetic resonance imaging provided in an embodiment of the present invention;

[0066] Figure 3 This is a schematic diagram of the kidney region image segmentation model framework provided in an embodiment of the present invention;

[0067] Figure 4 This is a schematic diagram of the renal parenchyma image segmentation model framework provided in an embodiment of the present invention;

[0068] Figure 5 A flowchart for extracting kidney morphological and omics features provided in this embodiment of the invention;

[0069] Figure 6 The image segmentation result of the kidney region provided in the embodiment of the present invention. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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.

[0071] like Figure 1 As shown, this invention provides a method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging, including the following steps:

[0072] Bilateral renal MRI data of children with hydronephrosis were obtained using T2WI and diffusion-weighted imaging (DWI) sequences. Clinical and laboratory data of the children with hydronephrosis were also obtained. The T2WI sequence (which provides optimal contrast to show the renal parenchyma and the extent of hydronephrosis) and the diffusion-weighted imaging sequence (a non-invasive MRI sequence that reflects renal function and renal parenchyma) were used to obtain the raw MRI scan data.

[0073] Kidney region image segmentation and feature extraction were performed in bilateral renal magnetic resonance scan data to obtain morphological features, omics features and diffusion-weighted features of the hydronephrotic side and the contralateral kidney.

[0074] By using clinical and laboratory data, as well as morphological, omics, and diffusion-weighted features of the hydronephrosis side and contralateral kidney, an assessment model for the function of the efferent kidney in children with hydronephrosis was established.

[0075] This invention constructs an assessment model for evaluating the function of the two kidneys in children with hydronephrosis using multimodal features, overcoming the limitations of assessment based on single features and improving the accuracy of the assessment model. The multimodal features include clinical data and laboratory test data, as well as morphological features, omics features, and diffusion-weighted features of the hydronephrotic side and the contralateral kidney. The features of each modality are complementary to each other, thus providing more comprehensive information for the assessment of the two kidneys. Moreover, when the data quality of one modality is poor or missing, other modalities can make up for it, thereby improving the overall stability and reliability of the assessment process, that is, improving the robustness of the assessment model.

[0076] In order to obtain the morphological features of the hydronephrotic side and the contralateral kidney, the present invention first needs to perform image segmentation on the bilateral renal magnetic resonance scan data or nuclear magnetic resonance scan image, that is, to segment the hydronephrotic side and the contralateral (or normal) kidney region on the nuclear magnetic resonance scan image, and then extract the morphological features of the kidney based on the segmented hydronephrotic side kidney region and the contralateral kidney region.

[0077] like Figure 3As shown, this invention constructs a kidney region image segmentation model framework to segment the hydronephrosis side kidney region and the contralateral kidney region. It consists of a hydronephrosis side kidney enhancement module based on the U-net network, and two hydronephrosis side kidney and contralateral kidney segmentation modules based on the Mask R-CNN network. The hydronephrosis side kidney enhancement module is used to first segment the hydronephrosis side kidney region on the original bilateral kidney MRI scan data using the U-net network. The segmentation mask result of the hydronephrosis side kidney region is superimposed and fused onto the original bilateral kidney MRI scan data to form hydronephrosis side kidney enhanced bilateral kidney MRI scan data. It can enhance a specific region (hydronephrosis side kidney region) in the original bilateral kidney MRI scan data while keeping other regions unchanged, thereby highlighting the details of the hydronephrosis side kidney region.

[0078] Since this invention aims to assess the renal function of children with hydronephrosis, the hydronephrotic kidney is of greater concern in the assessment process. The renal parenchymal features of the hydronephrotic kidney play a dominant role, requiring higher precision in their extraction. Therefore, unilateral enhancement of the hydronephrotic kidney region is employed to meet the precision requirements for its renal parenchymal features, while the corresponding normal kidney's renal parenchymal features play a supporting role. This allows for a lower requirement for the normal kidney, eliminating the need for enhancement and satisfying the renal parenchymal feature extraction needs while reducing unnecessary computation.

[0079] Then, the enhanced details of the bilateral renal MRI scan data were re-segmented through the Mask R-CNN network structure (i.e., the segmentation module of the first hydronephrotic kidney and the contralateral kidney) to achieve higher precision in the segmentation of the hydronephrotic kidney region. The enhanced details were used to obtain more accurate segmentation results of the hydronephrotic kidney region.

[0080] The kidney region image segmentation model framework also includes a Mask R-CNN network structure (i.e., a segmentation module for the second hydronephrosis-side kidney and the contralateral kidney). This module is used to segment the hydronephrosis-side kidney region on the original bilateral renal MRI scan data. It essentially acts as a quantification component for enhancing the hydronephrosis-side kidney, monitoring the segmentation performance of the hydronephrosis-side kidney region obtained from the original bilateral renal MRI scan data and comparing it with the segmentation performance of the hydronephrosis-side kidney region obtained from bilateral renal MRI scan data with enhanced details. If the former's performance is lower than the latter's, it is fed back to the enhancement coefficient of the hydronephrosis-side kidney. superior, The activation of the enhancement module for the hydronephrotic kidney is triggered; that is, the segmentation of the first hydronephrotic kidney and the contralateral kidney is based on the enhanced bilateral renal MRI scan data of the hydronephrotic kidney. Furthermore, it integrates the preliminary segmentation performance of the hydronephrosis-side kidney in the hydronephrosis-side kidney enhancement module. , The lower the value, the better the initial segmentation performance of the hydronephrotic kidney. The higher the reliability of the initial segmentation result of the hydronephrotic kidney superimposed on the original bilateral renal MRI scan data, the better the detail enhancement effect will be. ,when The lower, The higher the value, the higher the reliability of the superposition. Ultimately, the segmentation of the first hydronephrotic kidney and the contralateral kidney is based on the enhanced bilateral renal MRI scan data of the hydronephrotic kidney. This involves adding unnecessary augmentation operations, sacrificing efficiency for improved accuracy.

[0081] When the former's performance is detected to be higher than or equal to the latter's, it indicates that the enhancement of the hydronephrotic kidney will not have a positive effect on improving segmentation performance, and will also be reflected in the enhancement coefficient of the hydronephrotic kidney. superior, The enhancement module for the hydronephrotic kidney is triggered to shut down, and the final segmentation of the first hydronephrotic kidney and the contralateral kidney is based on bilateral renal MRI scan data. The above is based on the original bilateral renal MRI scan data. At this point, the regional enhancement calculation is redundant and does not need to be performed, thus achieving improved efficiency while maintaining the required accuracy.

[0082] In summary, this invention can achieve adaptive enhancement of details in the hydronephrotic kidney. It enhances details in the hydronephrotic kidney when segmentation performance can be improved, and does not need to enhance details in the hydronephrotic kidney when segmentation performance cannot be improved. This reduces redundant calculations, and the adaptive enhancement can achieve a balance between segmentation accuracy and segmentation efficiency. Therefore, it can achieve efficient and accurate kidney region image segmentation.

[0083] Methods for kidney region image segmentation in bilateral renal magnetic resonance imaging data include:

[0084] The bilateral renal MRI scan data were used to segment the kidney regions using a pre-established kidney region image segmentation model framework, identifying the hydronephrotic kidney region and the contralateral kidney region, such as... Figure 6 As shown;

[0085] The kidney image segmentation model framework includes a hydronephrosis-side kidney enhancement module based on the U-net network, and two hydronephrosis-side kidney and contralateral kidney segmentation modules based on the Mask R-CNN network. The input of the hydronephrosis-side kidney enhancement module based on the U-net network is used as the input of the kidney region image segmentation model framework, and the output of the first hydronephrosis-side kidney and contralateral kidney segmentation module is used as the output of the kidney region image segmentation model framework.

[0086] The hydronephrotic kidney enhancement module is used to segment the hydronephrotic kidney region in bilateral renal magnetic resonance scan data using the U-net network to obtain a mask image of the hydronephrotic kidney, and to fuse the mask image of the hydronephrotic kidney and bilateral renal magnetic resonance scan data to obtain bilateral renal magnetic resonance scan data with hydronephrotic kidney enhancement.

[0087] U-Net is a convolutional neural network for image segmentation, shaped like a "U," primarily composed of an encoder (Contracting Path) and a decoder (Expanding Path). The encoder extracts features progressively through convolutional and pooling layers, while the decoder restores image resolution through upsampling and convolutional operations. U-Net's unique feature is its skip connections, which directly pass feature maps from the encoder to the decoder, helping to recover more precise details. This design allows U-Net to better preserve detail when processing image segmentation tasks, thereby improving segmentation accuracy and precision.

[0088] Mask R-CNN (Mask Region-based Convolutional Neural Network) is an object detection and instance segmentation model that extends Faster R-CNN. It can not only detect the location of objects in an image and identify their categories, but also generate pixel-level segmentation masks for each detected object, thereby achieving more refined object segmentation.

[0089] The structural expression of the enhancement module for the hydronephrosis-side kidney is as follows:

[0090] ;

[0091] In the formula, Enhanced bilateral renal MRI data for the hydronephrosis-affected kidney. This is MRI data of both kidneys. The image shows a mask of the hydronephrotic kidney segmented using a U-net network. U-net is the U-net network itself. The enhancement coefficient of the hydronephrotic kidney. This is a pixel overlay operation formula;

[0092] ;

[0093] In the formula, GT is the actual masked image of the hydronephrotic kidney region. Enhanced image of the hydronephrotic kidney with masking. The image shows a mask of the hydronephrotic kidney, output by the segmentation module for the second hydronephrotic kidney and the contralateral kidney. For Kullback-Leibler divergence calculation, and Corresponding to Figure 3 The compare module in [the context of the project].

[0094] The first segmentation module for the hydronephrotic kidney and the contralateral kidney is used to segment the regions of the hydronephrotic kidney and the contralateral kidney in the enhanced bilateral renal magnetic resonance scan data of the hydronephrotic kidney using the Mask R-CNN network, so as to obtain the mask-enhanced image of the hydronephrotic kidney and the mask image of the contralateral kidney.

[0095] The structural expression for the segmentation module of the first hydronephrotic kidney and the contralateral kidney is as follows:

[0096] ;

[0097] In the formula, This is a masked image of the contralateral kidney. Mask R-CNN is used to enhance images of the kidney on the hydronephrotic side using a mask.

[0098] The second segmentation module for the hydronephrotic kidney and the contralateral kidney is used to segment the regions of the hydronephrotic kidney and the contralateral kidney in the bilateral renal magnetic resonance scan data using the Mask R-CNN network, so as to obtain the mask image of the hydronephrotic kidney and the mask image of the contralateral kidney.

[0099] The structural expression for the segmentation module of the second hydronephrotic kidney and the contralateral kidney is as follows:

[0100] ;

[0101] In the formula, The image shows a mask of the hydronephrotic kidney, output by the segmentation module of the second hydronephrotic kidney and the contralateral kidney.

[0102] Methods for feature extraction from bilateral renal magnetic resonance imaging (MRI) scan data include:

[0103] Morphological features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data obtained from T2WI sequences. The morphological features included kidney thickness parameters, kidney volume parameters, and kidney diameter parameters.

[0104] Omics features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data obtained from T2WI sequences using the gray-level co-occurrence matrix method.

[0105] The diffusion-weighted features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data acquired from DWI sequences using the apparent diffusion coefficient ADC analysis method.

[0106] Clinical data include age, sex, height, weight, history of urinary tract infection, medical history, and symptoms.

[0107] Laboratory test data include nuclear medicine renography, serum eGFR, urinalysis, and complete blood count.

[0108] The methods for constructing evaluation models include:

[0109] Clinical data and laboratory test data, as well as regional characteristics, omics characteristics and diffusion-weighted characteristics of the hydronephrotic side and the contralateral kidney, are used as inputs to the classification model, and the results of the kidney function assessment are used as the output of the classification model.

[0110] The classification model was trained to obtain an assessment model that outputs renal function assessment results based on clinical data, laboratory test data, and morphological, omics, and diffusion-weighted features of the hydronephrotic and contralateral kidneys.

[0111] The renal parenchyma is the main functional tissue of the kidney, located below the renal capsule. It consists of the renal cortex and the renal medulla. The renal cortex is the outer layer and contains the glomeruli and renal tubules; the renal medulla is the inner layer and consists of structures such as the renal pyramids and collecting ducts. Diffusion-weighted features are mainly found in the renal parenchyma in DWI sequences. Therefore, ADC analysis focuses primarily on the renal parenchymal region.

[0112] In extracting the diffusion-weighted features of the hydronephrotic kidney, this invention uses the hydronephrotic kidney as the region of interest, with a greater focus on the renal parenchyma within it. In other words, the ADC analysis of the hydronephrotic kidney focuses on the entire region, but with a particular emphasis on the renal parenchyma. Similarly, in cases of enhanced hydronephrotic kidney, the renal parenchyma is enhanced, and ADC analysis is performed on the enhanced hydronephrotic kidney. The resulting diffusion-weighted features of the hydronephrotic kidney highlight the details of the diffusion-weighted features of the renal parenchyma, effectively reflecting the microstructural features of the renal parenchyma and enhancing the feature extraction of the region of interest.

[0113] Therefore, this invention first performs precise segmentation of the renal parenchyma region in the hydronephrosis-side kidney, and then superimposes it onto the hydronephrosis-side kidney region to achieve precise enhancement of the renal parenchyma region in the hydronephrosis-side kidney, such as... Figure 4As shown, this invention migrates the kidney region image segmentation model framework to the hydronephrosis image segmentation model framework to achieve segmentation of the renal parenchyma region in the hydronephrosis side kidney region. It consists of a renal parenchyma region enhancement module based on the U-net network and two hydronephrosis side kidney parenchyma region segmentation modules based on the Mask R-CNN network. The renal parenchyma region enhancement module is used to first use the U-net network to initially segment the renal parenchyma region in the original hydronephrosis side kidney region (determined by the kidney region image segmentation model framework). The segmentation mask result of the renal parenchyma region is superimposed and fused onto the original hydronephrosis side kidney region to form a hydronephrosis side kidney region with enhanced renal parenchyma region. It can enhance a specific region (renal parenchyma region) in the original hydronephrosis side kidney region while keeping other regions unchanged, thereby highlighting the details of the renal parenchyma region.

[0114] Then, the hydronephrosis-side kidney region, with enhanced details, is re-segmented using the Mask R-CNN network structure (i.e., the first hydronephrosis-side kidney parenchyma region segmentation module) for more accurate renal parenchyma region segmentation, obtaining more precise renal parenchyma region segmentation results through enhanced details.

[0115] The renal parenchyma image segmentation model framework also includes a Mask R-CNN network structure (i.e., a segmentation module for the renal parenchyma region of the second hydronephrotic kidney). This module is used to segment the renal parenchyma region on the original hydronephrotic kidney region. It essentially acts as a quantification component for enhancing the renal parenchyma region, monitoring the segmentation performance of the renal parenchyma region obtained on the original hydronephrotic kidney region and comparing it with the segmentation performance of the renal parenchyma region obtained on the hydronephrotic kidney region with enhanced renal parenchyma details. When the former's performance is lower than the latter's, it is fed back to the enhancement coefficient of the renal parenchyma region. superior, The activation of the renal parenchymal region enhancement module is triggered, meaning the segmentation of the first hydronephrosis-side renal parenchymal region segmentation module is based on the hydronephrosis-side renal parenchymal region with enhanced renal parenchymal region. Furthermore, it integrates the preliminary segmentation performance of the renal parenchyma region from the renal parenchyma region enhancement module. , The lower the value, the better the initial segmentation performance of the renal parenchyma region. The higher the reliability of overlaying the initial segmentation results onto the original hydronephrosis-side kidney region, the better the detail enhancement effect will be. ,when The lower, The higher the value, the higher the reliability of the superposition. Ultimately, the segmentation of the first hydronephrosis-side kidney parenchyma region module is based on the hydronephrosis-side kidney region with enhanced renal parenchyma. This involves adding unnecessary augmentation operations, sacrificing efficiency for improved accuracy.

[0116] When the former's performance is detected to be higher than or equal to the latter's, it indicates that the enhancement of the renal parenchyma region will not have a positive effect on improving segmentation performance, and will also be reflected in the enhancement coefficient of the renal parenchyma region. superior, The renal parenchyma enhancement module is triggered to close, and the final segmentation of the first hydronephrosis-side renal parenchyma region is based on the hydronephrosis-side renal region. The above is based on the original hydronephrosis-side kidney region. At this point, the region enhancement operation is redundant and does not need to be performed, thus achieving improved efficiency while maintaining the required accuracy.

[0117] In summary, this invention can achieve adaptive enhancement of details in the renal parenchyma region. It can enhance the details of the renal parenchyma region when it can improve segmentation performance, and it does not need to enhance the details of the renal parenchyma region when it cannot improve segmentation performance. This reduces redundant calculations, and the adaptive enhancement can achieve a balance between segmentation accuracy and segmentation efficiency. Therefore, it can achieve efficient and accurate segmentation of the renal parenchyma region.

[0118] After accurately segmenting the renal parenchyma from the hydronephrotic kidney region, the segment is overlaid and fused into the hydronephrotic kidney region to enhance the image of the renal parenchyma in the hydronephrotic kidney region. After ADC analysis, the diffusion-weighted features of the renal parenchyma region can be enhanced. Based on the extraction of diffusion-weighted features of the entire hydronephrotic kidney region, it is easier to extract the key features in the diffusion-weighted features.

[0119] Methods for extracting diffusion-weighted features of the hydronephrotic kidney include:

[0120] The hydronephrotic kidney region obtained from bilateral renal magnetic resonance imaging data acquired by DWI sequence is used as the input of the kidney region image segmentation model framework, and the renal parenchyma region in the hydronephrotic kidney is used as the output of the kidney region image segmentation model framework. The kidney region image segmentation model framework is then transferred to learn the renal parenchyma image segmentation model framework.

[0121] The renal parenchymal region in the hydronephrosis side kidney, determined by the mask-enhanced image of the renal parenchymal region of the hydronephrosis side kidney output by the renal parenchymal image segmentation model framework, is fused with the hydronephrosis side kidney region determined by the mask image of the hydronephrosis side kidney output by the renal region image segmentation model framework to obtain the region of interest enhanced hydronephrosis side kidney region. Apparent diffusion coefficient ADC analysis is then performed on the region of interest enhanced hydronephrosis side kidney region to obtain the diffusion-weighted features of the hydronephrosis side kidney.

[0122] The renal parenchyma image segmentation model framework includes a renal parenchyma region enhancement module based on the U-net network, and two renal parenchyma region segmentation modules for hydronephrotic kidneys based on the Mask R-CNN network. The input of the renal parenchyma region enhancement module based on the U-net network is used as the input of the renal parenchyma image segmentation model framework, and the output of the first renal parenchyma region segmentation module for hydronephrotic kidneys is used as the output of the renal parenchyma image segmentation model framework.

[0123] The renal parenchyma enhancement module is used to segment the renal parenchyma region in the hydronephrotic kidney region using the U-net network to obtain the hydronephrotic mask image of the hydronephrotic kidney, and to fuse the hydronephrotic mask image of the hydronephrotic kidney and the hydronephrotic kidney region to obtain the hydronephrotic kidney region with enhanced renal parenchyma.

[0124] The structural expression of the renal parenchymal region enhancement module is as follows:

[0125] ;

[0126] In the formula, The hydronephrotic region shows enhancement of the renal parenchyma. For images corresponding to the masked enhancement of the hydronephrosis-side kidney The area of ​​the kidney on the side with hydronephrosis was identified. This is a mask image of the renal parenchyma region of the hydronephrotic kidney obtained by segmentation using a U-net network. U-net is the U-net network. The enhancement coefficient of the renal parenchyma region;

[0127] ;

[0128] In the formula, GT en This is a true masked image of the renal parenchyma region of the hydronephrosis-related kidney. Masked enhanced image of the renal parenchyma region of the hydronephrosis-related kidney. This is a mask image of the renal parenchyma region of the hydronephrosis-side kidney, output by the renal parenchyma region segmentation module of the second hydronephrosis-side kidney. For Kullback-Leibler divergence calculation;

[0129] The first hydronephrotic kidney parenchyma segmentation module is used to segment the renal parenchyma region in the hydronephrotic kidney region with enhanced renal parenchyma region using the Mask R-CNN network, and obtain the mask-enhanced image of the hydronephrotic kidney parenchyma region.

[0130] The structural expression for the segmentation module of the renal parenchyma region of the first hydronephrotic kidney is:

[0131] ;

[0132] In the formula, Masked enhanced image of the renal parenchyma region of the hydronephrosis-related kidney. For Mask R-CNN network;

[0133] The second hydronephrotic kidney parenchyma segmentation module is used to segment the renal parenchyma region in the hydronephrotic kidney region using the Mask R-CNN network to obtain a mask image of the renal parenchyma region of the hydronephrotic kidney.

[0134] The structural expression for the segmentation module of the renal parenchyma region of the second hydronephrotic kidney is as follows:

[0135] ;

[0136] In the formula, The image is a mask image of the renal parenchyma region of the hydronephrotic kidney, output by the segmentation module of the renal parenchyma region of the second hydronephrotic kidney.

[0137] like Figure 5 As shown in Table 1, the methods for extracting the diffusion-weighted features of the contralateral kidney include:

[0138] Apparent diffusion coefficient ADC analysis was performed on the contralateral kidney region determined by the contralateral kidney mask image output by the kidney region image segmentation model framework to obtain the diffusion-weighted features of the contralateral kidney.

[0139] In the apparent diffusion coefficient ADC analysis method, ADC maps of the hydronephrotic kidney region and the contralateral kidney region are generated through a single exponential model analysis (e.g., ...). Figure 5 As shown), the single-exponential model analysis formula is:

[0140] ;

[0141] In the formula, S(b) is the DWI signal value at a specified b value when diffusion exists in the region, S0 is the DWI signal value when diffusion does not exist in the region, and b is the b value, which is used to determine the degree of diffusion motion weighting in the DWI signal.

[0142] The diffusion-weighted features include the mean, 5th, 25th, 50th, 75th and 90th percentiles, heterogeneity, skewness, kurtosis and entropy (as shown in Table 1).

[0143] Table 1. Diffusion-weighted characteristic data (excerpt)

[0144]

[0145] like Figure 2 As shown, this invention provides a system for assessing renal function in children with hydronephrosis based on magnetic resonance imaging (MRI), applied to a method for assessing renal function in children with hydronephrosis based on MRI. The system includes:

[0146] The data acquisition unit is used to acquire bilateral renal MRI scan data of children with hydronephrosis through T2WI sequence and diffusion-weighted imaging (DWI) sequence, as well as clinical and laboratory test data of children with hydronephrosis. The T2WI sequence (which provides optimal contrast to show the renal parenchyma and the extent of hydronephrosis) and the diffusion-weighted imaging sequence (a non-invasive MRI sequence that reflects renal function and renal parenchyma) are used to obtain raw MRI scan data.

[0147] The data acquisition unit includes an image acquisition module and a clinical data acquisition module. The workflow of the image acquisition module is as follows: After guiding the child in breathing training or after the child has been sedated with chloral hydrate, a bilateral renal MRI scan is performed in the supine position. The specific image scanning parameters are as follows: T2WI scan parameters: 3.0 T MR scanner, 8-channel cardiac coil, TR 5300ms, TE 66.55ms, slice thickness 3mm, FA 110°; DWI parameters: TR / TE (ms), 4000 / shortest TE; matrix 128×96, bandwidth, 250 kHz; slice thickness 3mm, b-value (s / mm2) 0, 800.

[0148] The clinical data acquisition module is used to record the patient's age, gender, height, weight, history of urinary tract infection, medical history, and symptoms. It can assess the patient's general health status and relevant risk factors that affect the patient's prognosis.

[0149] The clinical data acquisition module is used to assess the necessity and efficacy of surgical treatment by detecting biological information such as nuclear medicine renogram, blood eGFR, routine urine (white blood cells, red blood cells, etc.) and routine blood.

[0150] The renal parenchymal feature analysis unit is used to segment and extract features of renal regions in bilateral renal magnetic resonance scan data to obtain morphological features, omics features and diffusion-weighted features of the hydronephrotic side and the contralateral kidney.

[0151] The renal parenchyma feature analysis unit includes an image data loading module, a kidney segmentation module, a renal parenchyma feature extraction module, a texture feature extraction module, and a diffusion-weighted imaging feature extraction module.

[0152] The image data loading module is used to receive the above-mentioned magnetic resonance scanning T2WI plain scan sequence and diffusion-weighted imaging (DWI) data, load the raw magnetic resonance data and perform preprocessing, including image denoising and other methods;

[0153] The kidney segmentation module separates the hydronephrotic kidney and the contralateral kidney from the scan field based on a pre-established kidney region image segmentation model framework.

[0154] The renal parenchyma feature extraction module is used to extract morphological features of the hydronephrotic side and the contralateral kidney in T2WI sequences, including: kidney thickness parameters, kidney volume parameters, and kidney diameter parameters, such as anteroposterior diameter, lateral diameter, and superior-inferior diameter;

[0155] The texture feature extraction module is used to extract the texture features of the hydronephrotic side and the contralateral renal parenchyma in T2WI sequences, and describes the texture features of the renal parenchyma through methods such as gray-level co-occurrence matrix.

[0156] The diffusion-weighted imaging feature extraction module is used to extract diffusion-weighted features of the renal parenchyma through ADC value analysis after DWI post-processing.

[0157] The sub-renal function assessment unit is used to input clinical data and laboratory test data, as well as morphological characteristics, omics characteristics and diffusion-weighted characteristics of the hydronephrotic side and the contralateral kidney into the assessment model, and output the sub-renal function assessment results of children with hydronephrosis.

[0158] The process of establishing the decision information support module is as follows: First, collect the patient's clinical data, imaging features, and laboratory test data. Select feature pairs related to treatment decisions and prognosis from the collected big data sample, extract and post-process these feature parameters, and conduct large-sample training and model evaluation and verification on the post-processed feature data. Finally, use the prognosis model to evaluate and make decisions on the patient's prognosis.

[0159] The treatment suggestion feedback module is used for treatment plan recommendations, risk assessment, and prognosis evaluation.

[0160] Among them, the treatment plan recommendation is based on the clinical and imaging characteristics of the child, the establishment of a renal function prediction model and the output of clinical decision-making suggestions. The renal function prediction model is established based on large-sample clinical retrospective research data, the renal function assessment model and the prognostic follow-up results of the child; combined with the latest clinical guidelines and evidence-based medicine, individualized post-treatment and follow-up plans are recommended.

[0161] Risk assessment and prognostic evaluation are used to evaluate the prognosis of children with the disease and to provide corresponding assessment indicators and prognostic evaluation criteria.

[0162] The prognosis management module is used for integrating patient information and facilitating multidisciplinary collaborative consultations.

[0163] Patient information integration is used to integrate clinical information, laboratory and examination data to understand the dynamic changes in the renal parenchyma and the progression of the disease, so as to adjust the treatment plan in a timely manner and improve the prognosis.

[0164] Multidisciplinary collaborative consultations facilitate communication and collaboration among members of a subject team, support remote consultations, allow data from different regions to be uploaded and shared, and enable joint discussions on the child's condition to provide diagnostic and treatment recommendations.

[0165] This invention acquires MRI plain scan and diffusion-weighted imaging data of children with hydronephrosis, and uses artificial intelligence algorithms to perform renal imaging feature analysis on the image data. By combining the analysis results with imaging features, as well as the child's clinical biological information and clinical characteristics, renal function is assessed. This provides assistance for the formulation of subsequent clinical management plans and clinical decision-making for children with hydronephrosis, making it easier for doctors to understand the dynamic changes in the renal parenchyma and the progression of the disease, and thus adjust the treatment plan in a timely manner to improve the prognosis.

[0166] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.

Claims

1. A method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging, characterized in that, Includes the following steps: Bilateral renal MRI scan data of children with hydronephrosis were obtained using T2WI and diffusion-weighted imaging DWI sequences, along with clinical and laboratory data. In the bilateral renal magnetic resonance scan data, kidney region image segmentation and feature extraction were performed to obtain the morphological features, omics features and diffusion-weighted features of the hydronephrotic side and the contralateral kidney. Based on clinical and laboratory data, as well as morphological, omics, and diffusion-weighted features of the hydronephrosis side and contralateral kidney, an assessment model for the function of the efferent kidney in children with hydronephrosis was established. Methods for segmenting kidney region images in the bilateral renal magnetic resonance imaging data include: The bilateral renal magnetic resonance imaging data were used to segment the renal region image using a pre-established renal region image segmentation model framework to determine the hydronephrosis side renal region and the contralateral renal region. The kidney region image segmentation model framework includes a hydronephrosis-side kidney enhancement module based on the U-net network, and two hydronephrosis-side kidney and contralateral kidney segmentation modules based on the Mask R-CNN network. The input of the hydronephrosis-side kidney enhancement module based on the U-net network is used as the input of the kidney region image segmentation model framework, and the output of the first hydronephrosis-side kidney and contralateral kidney segmentation module is used as the output of the kidney region image segmentation model framework. The hydronephrosis-side kidney enhancement module is used to segment the hydronephrosis-side kidney region using the U-net network in the bilateral renal magnetic resonance scan data to obtain a hydronephrosis-side kidney mask image, and to fuse the hydronephrosis-side kidney mask image and the bilateral renal magnetic resonance scan data to obtain bilateral renal magnetic resonance scan data with hydronephrosis-side kidney enhancement. The structural expression of the hydronephrosis-side kidney enhancement module is as follows: ； In the formula, Enhanced bilateral renal MRI data for the hydronephrosis-affected kidney. This is MRI data of both kidneys. This is a mask image of the hydronephrotic kidney obtained by segmentation using a U-net network. U-net is the U-net network. The enhancement coefficient of the hydronephrotic kidney. This is a pixel overlay operation formula; ； In the formula, GT is the actual masked image of the hydronephrotic kidney region. Enhanced image of the hydronephrotic kidney with masking. Image of the hydronephrotic kidney with a mask. For Kullback-Leibler divergence calculation; The first segmentation module for the hydronephrotic kidney and the contralateral kidney is used to segment the regions of the hydronephrotic kidney and the contralateral kidney in the enhanced bilateral renal magnetic resonance scan data of the hydronephrotic kidney using the Mask R-CNN network, so as to obtain the mask-enhanced image of the hydronephrotic kidney and the mask image of the contralateral kidney. The structural expression for the segmentation module of the first hydronephrotic kidney and the contralateral kidney is as follows: ； In the formula, This is a masked image of the contralateral kidney. Mask R-CNN is used to enhance images of the kidney on the hydronephrotic side using a mask. The second segmentation module for the hydronephrotic kidney and the contralateral kidney is used to segment the regions of the hydronephrotic kidney and the contralateral kidney in the bilateral renal magnetic resonance scan data using the Mask R-CNN network, so as to obtain the mask image of the hydronephrotic kidney and the mask image of the contralateral kidney. The structural expression for the segmentation module of the second hydronephrotic kidney and the contralateral kidney is as follows: ； In the formula, Image of the kidney on the hydronephrotic side with a mask.

2. The method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 1, characterized in that: The method for feature extraction from the bilateral renal magnetic resonance imaging data includes: Morphological features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data obtained from T2WI sequences. The morphological features included: kidney thickness parameters, kidney volume parameters, and kidney diameter parameters. Omics features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data obtained from T2WI sequences using the gray-level co-occurrence matrix method. The diffusion-weighted features of the hydronephrotic kidney and the contralateral kidney were extracted from bilateral renal magnetic resonance imaging data acquired from DWI sequences using the apparent diffusion coefficient ADC analysis method.

3. The method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 1, characterized in that: The clinical data included age, sex, height, weight, history of urinary tract infection, medical history, and symptoms.

4. The method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 1, characterized in that: The laboratory test data include nuclear medicine renography, serum eGFR, urinalysis, and complete blood count.

5. The method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 2, characterized in that: The method for constructing the evaluation model includes: Clinical data and laboratory test data, as well as morphological, omics and diffusion-weighted features of the hydronephrotic side and the contralateral kidney, are used as inputs to the classification model, and the results of the kidney function assessment are used as the output of the classification model. The classification model is trained to obtain an assessment model that outputs renal function assessment results based on clinical data, laboratory test data, and morphological, omics, and diffusion-weighted features of the hydronephrotic and contralateral kidneys.

6. The method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 2, characterized in that: The method for extracting the diffusion-weighted features of the hydronephrotic kidney includes: The hydronephrotic kidney region obtained from bilateral renal magnetic resonance imaging data acquired by DWI sequence is used as the input of the kidney region image segmentation model framework, and the renal parenchyma region in the hydronephrotic kidney is used as the output of the kidney region image segmentation model framework. The kidney region image segmentation model framework is then transferred to learn the renal parenchyma image segmentation model framework. The renal parenchymal region in the hydronephrosis side kidney, determined by the mask-enhanced image of the renal parenchymal region of the hydronephrosis side kidney output by the renal parenchymal image segmentation model framework, is fused with the hydronephrosis side kidney region determined by the mask image of the hydronephrosis side kidney output by the renal region image segmentation model framework to obtain the region of interest enhanced hydronephrosis side kidney region. Apparent diffusion coefficient ADC analysis is then performed on the region of interest enhanced hydronephrosis side kidney region to obtain the diffusion-weighted features of the hydronephrosis side kidney. The renal parenchyma image segmentation model framework includes a renal parenchyma region enhancement module based on the U-net network, and two renal parenchyma region segmentation modules for hydronephrotic kidneys based on the Mask R-CNN network. The input of the renal parenchyma region enhancement module based on the U-net network is used as the input of the renal parenchyma image segmentation model framework, and the output of the first hydronephrotic kidney renal parenchyma region segmentation module is used as the output of the renal parenchyma image segmentation model framework. The renal parenchyma enhancement module is used to segment the renal parenchyma region in the hydronephrotic kidney region using the U-net network to obtain a renal parenchyma mask image of the hydronephrotic kidney, and to fuse the renal parenchyma mask image of the hydronephrotic kidney and the hydronephrotic kidney region to obtain a hydronephrotic kidney region with enhanced renal parenchyma. The structural expression of the renal parenchyma enhancement module is as follows: ； In the formula, The renal parenchyma enhancement module outputs an enhanced version of the hydronephrotic kidney region. For images corresponding to the masked enhancement of the hydronephrosis-side kidney The area of ​​the kidney on the side with hydronephrosis was identified. This is a mask image of the renal parenchyma region of the hydronephrotic kidney obtained by segmentation using a U-net network. U-net is the U-net network. The enhancement coefficient of the renal parenchyma region. This is a pixel overlay operation formula; ； In the formula, GT en This is a true masked image of the renal parenchyma region of the hydronephrosis-related kidney. Masked enhanced image of the renal parenchyma region of the hydronephrosis-related kidney. This is a masked image of the renal parenchyma region of the hydronephrosis-related kidney. For Kullback-Leibler divergence calculation; The first hydronephrotic kidney parenchyma segmentation module is used to segment the renal parenchyma region in the hydronephrotic kidney region with enhanced renal parenchyma region using the Mask R-CNN network, and obtain the mask-enhanced image of the hydronephrotic kidney parenchyma region. The structural expression for the segmentation module of the renal parenchyma region of the first hydronephrotic kidney is: ； In the formula, Masked enhanced image of the renal parenchyma region of the hydronephrosis-related kidney. For Mask R-CNN network; The second hydronephrotic kidney parenchyma segmentation module is used to segment the renal parenchyma region in the hydronephrotic kidney region using the Mask R-CNN network to obtain a mask image of the renal parenchyma region of the hydronephrotic kidney. The structural expression for the segmentation module of the renal parenchyma region of the second hydronephrotic kidney is as follows: ； In the formula, This is a masked image of the renal parenchyma region of the kidney on the hydronephrosis side.

7. The method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 2, characterized in that: The method for extracting the diffusion-weighted features of the contralateral kidney includes: Apparent diffusion coefficient ADC analysis was performed on the contralateral kidney region determined by the contralateral kidney mask image output by the kidney region image segmentation model framework to obtain the diffusion-weighted features of the contralateral kidney.

8. A method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 2, characterized in that: The diffusion-weighted features include mean, 5th, 25th, 50th, 75th and 90th percentiles, heterogeneity, skewness, kurtosis and entropy.

9. A method for assessing renal function in children with hydronephrosis based on magnetic resonance imaging according to claim 2, characterized in that: The apparent diffusion coefficient ADC analysis method generates ADC maps of the hydronephrotic kidney region and the contralateral kidney region using a single exponential model. The single exponential model analysis formula is as follows: ； In the formula, S(b) is the DWI signal value at a specified b value when diffusion exists in the region, S0 is the DWI signal value when diffusion does not exist in the region, and b is the b value, which is used to determine the degree of diffusion motion weighting in the DWI signal.

Images