Kidney state evaluation device, method, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a kidney state evaluation device and method, equipment, a storage medium and a program product. In the device, an obtaining module obtains a kidney structure diagram, an RBF diagram and a T1Map; a registration module performs image registration on the kidney structure diagram, the RBF diagram and the T1Map to obtain a target kidney structure diagram, a target RBF diagram and a target T1MAP; the segmentation module is used for segmenting the target kidney structure diagram by using the trained kidney segmentation model to obtain respective segmentation masks of renal parenchyma, renal cortex and renal medullary; the processing module determines the form of renal parenchyma from the target kidney structure diagram, determines respective blood perfusion values of renal cortex and renal medullary from the target RBF diagram, and determines respective T1 relaxation time of renal cortex and renal medullary from the target T1Map based on the segmentation mask; and the evaluation module evaluates the state of the kidney according to the processing result. According to the scheme provided by the embodiment of the invention, the accuracy of kidney state evaluation can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a kidney status assessment device, method, equipment, storage medium and program product. Background Art

[0002] The kidneys are one of the important organs in the human body, responsible for filtering waste and excess water from the blood, maintaining electrolyte balance in the body, regulating blood pressure, and participating in the production of red blood cells.

[0003] Whether kidney function is normal or not is directly related to individual health and quality of life. Among them, renal fibrosis affects multiple biological pathways such as metal ion transport, glucose metabolism, immune function, inflammation and cell mitosis of organs, and is the main cause of organ disease.

[0004] Currently, kidney assessment protocols suffer from poor accuracy. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide an information recommendation method, data processing method, device and storage medium that solve the above problems or at least partially solve the above problems.

[0006] In a first aspect of the present application, a kidney status assessment device is provided, comprising:

[0007] The acquisition module is used to: acquire the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map;

[0008] A registration module is used to: perform image registration on the kidney structure image, the kidney blood perfusion image and the T1 relaxation time quantitative image to obtain a target kidney structure image, a target kidney blood perfusion image and a target T1 relaxation time quantitative image;

[0009] A segmentation module, used to segment the target kidney structure image using a trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla;

[0010] a processing module, configured to: determine the morphology of the renal parenchyma from a target kidney structure map, determine the blood perfusion values ​​of the renal cortex and the renal medulla from the target kidney blood perfusion map, and determine the T1 relaxation time of the renal cortex and the renal medulla from a target T1 relaxation time quantitative map based on the first segmentation mask, the second segmentation mask, and the third segmentation mask;

[0011] An evaluation module is used to evaluate the user's renal status according to the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation time of the renal cortex and the renal medulla.

[0012] A second aspect of the present application provides a kidney data processing method, comprising:

[0013] Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map;

[0014] Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map;

[0015] Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla;

[0016] Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

[0017] In a third aspect of the present application, an electronic device is provided. The electronic device comprises: a memory and a processor, wherein:

[0018] The memory is used to store programs;

[0019] The processor is coupled to the memory and is configured to execute the program stored in the memory to implement:

[0020] Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map;

[0021] Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map;

[0022] Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla;

[0023] Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

[0024] Optionally, the processor is further configured to implement:

[0025] The renal status of the user is evaluated based on the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

[0026] In a fourth aspect of the present application, a computer-readable storage medium storing a computer program is provided, wherein when the computer program is executed by a computer, the computer program can achieve:

[0027] Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map;

[0028] Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map;

[0029] Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla;

[0030] Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

[0031] Optionally, when the computer program is executed by a computer, it can also achieve:

[0032] The renal status of the user is evaluated based on the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

[0033] In a fifth aspect of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements:

[0034] Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map;

[0035] Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map;

[0036] Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla;

[0037] Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

[0038] Optionally, when the computer program is executed by a processor, it can also achieve:

[0039] The renal status of the user is evaluated based on the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

[0040] In the technical scheme provided by the embodiment of the present application, the renal cortex and renal medulla in the renal structure diagram are automatically segmented using a segmentation model, and based on image registration technology and model segmentation results, the morphology (volume, surface area), blood perfusion, and evaluation indexes of T1 relaxation time of different renal regions after segmentation are automatically obtained from the renal blood perfusion map and the T1 relaxation time quantitative map, and then the renal state is evaluated based on the extracted morphology, blood perfusion, and T1 relaxation time. In other words, this scheme can comprehensively evaluate the renal state from aspects such as the morphology of the kidney, the blood perfusion of the renal cortex and the renal medulla and the T1 relaxation time. Moreover, the accuracy of quantitative information calculation and renal state evaluation can be guaranteed by image registration technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 A structural block diagram of a kidney status assessment device provided in one embodiment of the present application;

[0043] Figure 2A schematic diagram of a process flow of a kidney data processing method provided in one embodiment of the present application;

[0044] Figure 3 A schematic diagram of a kidney data processing method provided in one embodiment of the present application;

[0045] Figure 4 A structural block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below according to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0047] In addition, some of the processes described in the specification, claims and the above-mentioned figures of the present application include multiple operations that appear in a specific order, and these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0048] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0049] Structurally, the renal parenchyma (i.e., the kidney) is divided into two parts: the renal cortex and the renal medulla. The renal cortex is located in the superficial outer layer of the kidney and is mainly composed of glomeruli and renal tubules. It is connected to the renal columns located between the renal pyramids. The glomeruli are responsible for the initial filtration of the blood, while the renal tubules further process the filtered fluid, recover necessary substances, and excrete waste from the body. The renal medulla is a structure deep in the kidney. It is composed of more than ten renal pyramids and is mainly responsible for filtering impurities and storing urine. In renal imaging, morphological characteristics such as kidney volume play an important role in the monitoring and diagnosis of various diseases. For example, an increase in overall kidney volume is a key factor in the diagnosis of autosomal dominant polycystic kidney disease, and a disproportionate decrease in cortical volume relative to the medulla is a manifestation of aging and chronic kidney disease.

[0050] The kidneys are also well supplied with blood. In a normal adult at rest, 1200 ml of blood flows through both kidneys every minute, which is equivalent to 1 / 5 to 1 / 4 of the cardiac output. 80 to 90% of the blood is distributed in the renal cortex, supplied by the afferent arterioles, and 10% to 20% is distributed in the outer and inner medulla, supplied by the efferent arterioles. The renal perfusion volume usually refers mainly to the renal cortical blood flow.

[0051] In addition, the normality of kidney function is directly related to the individual's health and quality of life. Among them, kidney fibrosis affects multiple biological pathways such as metal ion transport, glucose metabolism, immune function, inflammation and cell mitosis of organs, and is the main cause of organ disease.

[0052] In the past, kidney assessment mainly relied on laboratory tests (such as serum creatinine and urea nitrogen levels) and imaging examinations such as ultrasound, computed tomography (CT), and magnetic resonance imaging (MRI), but they have limitations such as single modality and insufficient sensitivity. Therefore, there is an urgent need for a comprehensive kidney status analysis / assessment device that combines multi-dimensional information such as kidney morphology, blood perfusion, and function to comprehensively assess kidney status, thereby improving the accuracy of kidney status assessment.

[0053] Figure 1: This is a structural block diagram of a renal status assessment device provided in one embodiment of the present application. Among them, the renal status assessment device may include, but is not limited to: a device integrated in any terminal device such as a smart phone, a tablet computer, a PDA (Personal Digital Assistant), a smart TV, a laptop computer, a desktop computer, a smart wearable device, etc. The device includes a transceiver module for receiving data to be processed (such as the neck blood flow data described below), and a processor for processing the data to be processed. The processor of the device can be mounted in the above-mentioned terminal device. The processor of the device can be integrated with the transceiver module in the same device, or it can be integrated in different devices respectively, which is not limited in the embodiment of the present application. Optionally, the device also includes a display module for displaying the processing results (such as evaluation results) of the device, such as a screen in a terminal device.

[0054] like Figure 1 As shown, the device includes: an acquisition module 101, a registration module 102, a segmentation module 103, a processing module 104 and an evaluation module 105.

[0055] The acquisition module 101 is used to acquire a user's renal structure map, a renal blood perfusion map, and a T1 relaxation time quantitative map.

[0056] Among them, the user's renal structure map, renal blood flow (RBF) map and T1 relaxation time quantitative map can be obtained based on data collected by a computer tomography device and / or a magnetic resonance imaging device.

[0057] Optionally, the renal structure image may be an image of the user's kidneys acquired by a computer tomography device or an image of the user's kidneys acquired by a magnetic resonance imaging device.

[0058] In practical applications, the clarity of the renal anatomical structure reflected in the renal structure map is higher than that reflected in the renal blood perfusion map and the T1 relaxation time quantitative map.

[0059] Among them, the renal structure map refers to an image used to display the renal structure, mainly used to reflect the anatomical information of the renal tissue, such as the morphology, size, and position. When obtaining the renal structure map, sequences such as VIBE (Volumetric Interpolated Breath-hold Examination), HASTE (Half-Fourier Acquisition Single-shot Turbo spin Echo), and respiratory navigation T2-weighted imaging can be used to obtain high-resolution images. It has the characteristics of fast imaging and multi-tissue contrast. In the case of no breath holding or a relatively short breath holding, the anatomical structure of the kidney can be clearly displayed, and the motion artifacts or chemical shift artifacts caused by breathing can be reduced.

[0060] Exemplarily, the structural image is obtained by performing magnetic resonance scanning on the kidney using T1-weighted imaging to obtain the morphological and structural information of the kidney. In other words, the structural image includes the morphological and structural information of the kidney.

[0061] Optionally, the renal blood perfusion map is generated based on an arterial spin labeling (ASL) sequence acquired by a magnetic resonance imaging device. ASL technology can be used to achieve non-invasive assessment. The ASL sequence can be one or more of a single-delay ASL sequence, a multi-delay ASL (MDASL) sequence, a pseudo-continuous arterial spin labeling (PCASL), and a pseudo-continuous arterial spin labeling sequence under multiple delay times (Post Label Delay, PLD).

[0062] In one embodiment, the PCASL sequence at multiple delay times may be processed to obtain a renal blood perfusion map that can quantify the renal blood perfusion value. Exemplarily, the renal blood perfusion map at each delay time may be determined using the following formula (1):

[0063]

[0064] Where i is the i-th voxel in the renal blood perfusion map, RBF i is the renal blood flow of the ith voxel, R 1a = 0.61, is the longitudinal relaxation rate of blood, M0 is the equilibrium magnetization of tissue, α = 0.8 is the labeling efficiency, τ = 1.5 s is the labeling duration, w i=0.5 / 1 / 1.5 / 2 / 2.5s is the set post-marking delay time, λ=0.9g / ml is the blood / tissue water partition coefficient, δ is the arterial transit time (ATT) value in each voxel, and △M(i) refers to the signal change of the i-th voxel.

[0065] Optionally, the T1 relaxation time quantitative map (T1Map) is obtained based on a T1Mapping sequence acquired by a magnetic resonance imaging device. The signal intensity value of each voxel in the T1 relaxation time quantitative map represents the T1 relaxation time of the voxel.

[0066] The inversion recovery sequence can be used for acquisition. According to the different signal strengths of tissues in different inversion recovery times (TI), the signal strengths of 4-5 TI values ​​can be acquired within one repetition time (TR), and the T1 value of the tissue can be calculated according to the following formula (2):

[0067] S(TI)=M0[1-2exp(-TI / T1)+exp(-TR / T1)(2)

[0068] where M0 is the equilibrium magnetization of the tissue.

[0069] The registration module 102 is used to perform image registration on the renal structure image, the renal blood perfusion image and the T1 relaxation time quantitative image to obtain a target renal structure image, a target renal blood perfusion image and a target T1 relaxation time quantitative image.

[0070] Image registration refers to the process of spatially aligning two or more images so that they have consistent anatomical structures or features in the same spatial coordinate system.

[0071] Image registration is to find a spatial transformation relationship so that the reference image and the image to be registered are aligned in space, ensuring that the same anatomical point or feature point in the image has the same position in the two images. This alignment is achieved by calculating the transformation parameters between the two images, usually including translation, rotation, scaling and other operations.

[0072] The image registration technology is used to spatially align the renal structure map, the renal blood perfusion map, and the T1 relaxation time quantitative map to obtain the target renal structure map, the target renal blood perfusion map, and the target T1 relaxation time quantitative map. The same anatomical feature point of the kidney has the same position or coordinates in the target renal structure map, the target renal blood perfusion map, and the target T1 relaxation time quantitative map. There may be multiple anatomical feature points of the kidney, such as: vascular branch points, renal pelvis, etc.

[0073] In an optional embodiment, the renal blood perfusion map and the T1 relaxation time quantitative map can be converted to the coordinate system of the renal structure map, respectively, to obtain the target renal blood perfusion map and the target T1 relaxation time quantitative map. In this embodiment, the target renal structure map is also the renal structure map. In other words, the image registration between the renal structure map, the renal blood perfusion map and the T1 relaxation time quantitative map can be achieved by only performing coordinate conversion on the renal blood perfusion map and the T1 relaxation time quantitative map.

[0074] Optionally, the renal blood perfusion map and the T1 relaxation time quantitative map can be converted to the coordinate system of the renal structure map based on a non-rigid registration algorithm of feature point matching to obtain the target renal blood perfusion map and the target T1 relaxation time quantitative map. The feature points are also anatomical feature points. The transformation process involves non-rigid transformation, that is, the distance between two points in one image will be transformed after being transformed into another image.

[0075] In one embodiment, the above image registration process may include the following steps:

[0076] S11. Determine a plurality of first anatomical feature points in the target image.

[0077] Wherein, the target image is one of the renal blood perfusion image and the T1 relaxation time quantitative image.

[0078] The plurality of first anatomical feature points may include, but are not limited to, a blood vessel branch point and a renal pelvis. These points have obvious anatomical features, so as to be accurately identified in the two images.

[0079] Exemplarily, corresponding anatomical feature points are identified and marked in the target image.

[0080] S12. Determine a plurality of second anatomical feature points in the kidney structure map.

[0081] The plurality of second anatomical feature points may include, but are not limited to, a blood vessel branch point and a renal pelvis.

[0082] Exemplarily, corresponding anatomical feature points are identified and marked in the target image.

[0083] S13. Pair the plurality of first anatomical feature points with the plurality of second anatomical feature points using a point-by-point mutual information method to obtain a plurality of feature point pairs.

[0084] Pointwise Mutual Information (PMI) is a method used in probability theory and information theory to measure the correlation between two events or variables. The basic principle is that if two events x and y are independent, then the probability of their simultaneous occurrence P(x, y) is equal to the product of their respective probabilities P(x) and P(y). If x and y are not independent, that is, there is a correlation between them, then P(x, y) will be greater than P(x)P(y).

[0085] In an optional implementation, a correlation between any first anatomical feature point in the plurality of first anatomical feature points and any second anatomical feature point in the plurality of second anatomical feature points is calculated using a point-by-point mutual information method, and a plurality of feature point pairs are determined based on the correlation, wherein one feature point in each feature point pair comes from the plurality of first anatomical feature points, and the other feature point comes from the second anatomical feature point.

[0086] The specific steps to achieve this are as follows:

[0087] A. Local area selection:

[0088] Define a local region for each feature point, which should be small enough to capture local features but large enough to contain enough information. The local region can be circular or square, and its size may need to be adjusted according to the resolution of the image and the local variation of the feature points.

[0089] B. Calculate the local histogram:

[0090] For each local area of ​​a feature point, calculate the histogram of its intensity value. This histogram will be used for subsequent mutual information calculation.

[0091] C. Estimating the joint probability distribution:

[0092] For each pair of corresponding feature points in the two images, the joint probability distribution of their local area intensity values ​​is estimated by calculating the intersection of the two histograms.

[0093] D. Calculate mutual information:

[0094] The mutual information between each pair of feature points is calculated using the following formula (3):

[0095] MI(x,y)=∑ i,j P(x i ,y i )log(P(x i ,y i ) / P(x i )P(y i ))(3)

[0096] Among them, P(x i ,y i ) is the joint probability of two feature points on specific voxels i and j, P(x i ) and P(y i ) are the respective marginal probabilities.

[0097] E. Construct the change matrix:

[0098] The calculated mutual information is combined into a mutual information change matrix.

[0099] F. Find the best matching feature point:

[0100] In the mutual information change matrix, a mutual information threshold is set. When this threshold is exceeded, the corresponding feature point is considered to be the most likely matching feature point.

[0101] S14. Determine a transformation matrix according to the multiple feature point pairs.

[0102] A transformation matrix is ​​determined according to respective coordinate information of two feature points in each feature point pair among the plurality of feature point pairs.

[0103] Based on the multiple feature point pairs found, the transformation model between images can be calculated through rigid transformation (translation, rotation, etc.) and affine transformation (scaling, shearing, etc.), an error function can be constructed, and the transformation matrix can be obtained by minimizing the error function.

[0104] S15. According to the transformation matrix, the target image is converted into the coordinate system of the kidney structure image.

[0105] The target image is modified according to the transformation matrix, thereby obtaining an image that is registered with the kidney structure image.

[0106] The calculated transformation matrix is ​​applied to all pixels of the target image to transform the target image into the coordinate system of the kidney structure image. After applying the transformation, the registration quality is evaluated by calculating the overlap rate of the corresponding anatomical structures of the two images after registration, the mean square error and other indicators. If the registration effect is not ideal, it can be optimized by adjusting the matching point selection strategy, the parameters of the mutual information calculation and other methods.

[0107] For example: according to the first transformation matrix, the renal blood perfusion map is modified to obtain a target renal blood perfusion map registered with the renal structure map.

[0108] For another example, the T1 relaxation time quantitative map is modified according to the second transformation matrix, so as to obtain a target T1 relaxation time quantitative map registered with the kidney structure map.

[0109] It should be noted that the first transformation matrix and the second transformation matrix may be determined in the manner provided in the above embodiment, wherein the first transformation matrix and the second transformation matrix may be different.

[0110] The segmentation module 103 is used to segment the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the kidney parenchyma, a second segmentation mask of the kidney cortex, and a third segmentation mask of the kidney medulla.

[0111] The kidney segmentation model may be a deep learning model. In an optional implementation, the kidney segmentation model may be a deep learning model of an encoding-decoding structure.

[0112] Exemplarily, the model may include: a feature sharing and encoder module, a feature recognition module, and a decoding and upsampling module. The input of the model is an image block cut from a renal structural image, and six types of segmentation results, including left renal parenchyma, right renal parenchyma, left renal cortex, right renal cortex, left renal medulla, and right renal medulla, are obtained through three sub-segmentation networks.

[0113] The first segmentation mask of the renal parenchyma includes: a first segmentation mask of the left renal parenchyma and a first segmentation mask of the right renal parenchyma; the second segmentation mask of the renal cortex includes: a second segmentation mask of the left renal cortex and a second segmentation mask of the right renal cortex; the third segmentation mask of the renal medulla includes: a third segmentation mask of the left renal medulla and a third segmentation mask of the right renal medulla.

[0114] A training method for the kidney segmentation model is described below, and the method comprises the following steps:

[0115] S21. Obtain training samples.

[0116] The training samples include: sample kidney structure diagram and expected segmentation results.

[0117] The desired segmentation result may be obtained through manual annotation, and this embodiment of the present application does not specifically limit this.

[0118] S22, inputting the sample kidney structure image into the kidney segmentation model to obtain an actual segmentation result of the kidney segmentation model.

[0119] Optionally, the sample kidney structure image may be cropped to obtain a plurality of image blocks, and the plurality of image blocks may be input into a kidney segmentation model to obtain an actual segmentation result of the kidney segmentation model.

[0120] S23. According to the expected segmentation result and the actual segmentation result, the parameters of the kidney segmentation model are optimized using a cross entropy loss function and a Dice loss function.

[0121] In order to train the model, the embodiment of the present application adopts a composite loss function, including cross-entropy loss and Dice loss. The cross-entropy loss function is used to measure the difference between the probability distribution of the model output and the true label, which is suitable for multi-category segmentation tasks, while the Dice loss function focuses on calculating the overlap between the predicted area and the true area, which is particularly suitable for dealing with class imbalance problems. This combination of loss functions can simultaneously optimize the classification accuracy and segmentation accuracy of the model.

[0122] Among them, the function of Cross-Entropy Loss is defined as follows:

[0123]

[0124] Where C is the number of categories, y ic is an indicator variable. If sample i belongs to category c, then y ic =1, otherwise y ic =0, p ic is the probability that the model predicts that sample i belongs to category c. Any pixel in the structure diagram is a sample.

[0125] The function definition of Dice Loss is as follows:

[0126]

[0127] Where N is the number of samples, y i is the true label of the i-th sample, p i is the label predicted by the model for the i-th sample, and ε is a small constant used to prevent the denominator from being zero.

[0128] In addition, during the model training process, data enhancement strategies can be implemented, including operations such as rotation, scaling, and flipping, to enhance the generalization ability of the model. In addition, small batch gradient descent method can be used for training, combined with learning rate decay strategy and early stopping method to prevent overfitting and accelerate the convergence of the model.

[0129] The processing module 104 is used to: determine the morphology of the renal parenchyma from the target kidney structure map based on the first segmentation mask, the second segmentation mask and the third segmentation mask, determine the blood perfusion values ​​of the renal cortex and the renal medulla respectively from the target renal blood perfusion map, and determine the T1 relaxation time of the renal cortex and the renal medulla respectively from the target T1 relaxation time quantitative map.

[0130] Among them, the morphology of renal parenchyma may include: volume and surface area.

[0131] Based on the first segmentation mask of the left renal parenchyma, the morphology of the left renal parenchyma is determined from the renal structure map.

[0132] Based on the first segmentation mask of the right renal parenchyma, the morphology of the right renal parenchyma is determined from the renal structure map.

[0133] Based on the second segmentation mask of the left renal cortex, a blood perfusion value of the left renal cortex is determined from the target renal blood perfusion map.

[0134] Based on the second segmentation mask of the left renal cortex, the T1 relaxation time of the left renal cortex is determined from the target T1 relaxation time quantitative map.

[0135] Based on the second segmentation mask of the right renal cortex, a blood perfusion value of the right renal cortex is determined from the target renal blood perfusion map.

[0136] Based on the second segmentation mask of the right renal cortex, the T1 relaxation time of the right renal cortex is determined from the target T1 relaxation time quantitative map.

[0137] Based on the third segmentation mask of the left renal medulla, a blood perfusion value of the left renal medulla is determined from the target renal blood perfusion map.

[0138] Based on the third segmentation mask of the left renal medulla, the T1 relaxation time of the left renal medulla is determined from the target T1 relaxation time quantitative map.

[0139] Based on the third segmentation mask of the right renal medulla, a blood perfusion value of the right renal medulla is determined from the target renal blood perfusion map.

[0140] Based on the third segmentation mask of the right renal medulla, the T1 relaxation time of the right renal medulla is determined from the target T1 relaxation time quantitative map.

[0141] The evaluation module 105 is used to evaluate the user's renal status according to the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation time of the renal cortex and the renal medulla.

[0142] In an optional embodiment, the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation time of the renal cortex and the renal medulla, respectively, may be compared with prior information on the state of renal disease to evaluate the state of the kidney.

[0143] Among them, the renal status may include the renal perfusion status.

[0144] In summary, the technical solution provided in the embodiments of the present application will utilize the advantages of multimodal magnetic resonance imaging to automatically segment the renal cortex and medulla, and automatically obtain the evaluation indicators of the morphology (volume, surface area), blood perfusion, and functional quantification of different renal regions after segmentation, establish a correlation between the evaluation indicators and disease manifestations, and thereby achieve non-invasive assessment of renal status.

[0145] Figure 2 A flowchart of a kidney data processing method provided in an embodiment of the present application. The execution subject of the method may include a terminal device and / or a server, which is not specifically limited in the embodiment of the present application. Among them, the terminal device: can also be called a terminal. It can be a mobile terminal, a fixed terminal or a portable terminal, such as a mobile phone, a site, a unit, a device, a multimedia computer, a multimedia tablet, an Internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a personal communication system device, a personal navigation device, a personal digital assistant, an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination thereof, including accessories, peripherals or any combination thereof of these devices. Server: A server can be one or more servers. A server can also be a physical server or a virtual server, etc. A server can be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and big data and artificial intelligence platforms.

[0146] like Figure 2 As shown, the method may include:

[0147] 201. Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map.

[0148] like Figure 3 As shown, the PCASL sequence is processed to obtain the RBF map, and the T1Mapping sequence is processed to obtain the T1Map.

[0149] 202. Perform image registration on the renal structure image, the renal blood perfusion image, and the T1 relaxation time quantitative image to obtain a target renal structure image, a target renal blood perfusion image, and a target T1 relaxation time quantitative image.

[0150] like Figure 3 As shown, the RBF map, T1Map and structural image are registered to obtain the target kidney structure map, target kidney blood perfusion map and target T1 relaxation time quantitative map.

[0151] 203. Use the trained kidney segmentation model to segment the target kidney structure image to obtain a first segmentation mask of the kidney parenchyma, a second segmentation mask of the kidney cortex, and a third segmentation mask of the kidney medulla.

[0152] like Figure 3 As shown, a segmentation model is constructed, and the target kidney structure image is segmented by the constructed segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla.

[0153] 204. Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, determine the morphology of the renal parenchyma from the renal structure map, determine the blood perfusion values ​​of the renal cortex and the renal medulla respectively from the target renal blood perfusion map, and determine the T1 relaxation time of the renal cortex and the renal medulla respectively from the target T1 relaxation time quantitative map.

[0154] like Figure 3 As shown, the morphology of the renal parenchyma includes the surface area and volume. After obtaining the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation time of the renal cortex and the renal medulla, the renal status can be evaluated.

[0155] The specific implementation of the above steps 201 to 204 can refer to the corresponding contents in the above embodiments, which will not be repeated here.

[0156] Optionally, the above method may further include:

[0157] 205. Evaluate the renal status of the user according to the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

[0158] It should be noted here that: for the contents of each step not fully described in detail in the method provided in the embodiment of the present application, please refer to the corresponding contents in the above embodiment, which will not be repeated here. In addition, in addition to the above steps, the method provided in the embodiment of the present application may also include other parts or all of the steps in the above embodiments, which can be specifically referred to the corresponding contents in the above embodiments, which will not be repeated here.

[0159] Figure 4 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present application. Figure 4As shown, the electronic device includes a memory 1101 and a processor 1102. The memory 1101 can be configured to store various other data to support operations on the electronic device. Examples of these data include instructions for any application or method for operating on the electronic device. The memory 1101 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read only memory (EEPROM), an erasable programmable read only memory (EPROM), a programmable read only memory (PROM), a read only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk.

[0160] The memory 1101 is used to store programs;

[0161] The processor 1102 is coupled to the memory 1101 and is used to execute the program stored in the memory 1101 to implement the kidney data processing method provided by the above-mentioned method embodiments.

[0162] Further, if Figure 4 As shown, the electronic device also includes: a communication component 1103, a display 1104, a power component 1105, an audio component 1106 and other components. Figure 4 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 4 Components shown.

[0163] Accordingly, an embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the steps or functions of the kidney data processing method provided by the above-mentioned method embodiments.

[0164] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, can implement the steps or functions of the methods provided in the above-mentioned method embodiments.

[0165] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0166] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM (Read Only Memory) / RAM (Random Access Memory), a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A kidney status assessment device, characterized in that: include: The acquisition module is used to: acquire the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map; A registration module is used to: perform image registration on the kidney structure image, the kidney blood perfusion image and the T1 relaxation time quantitative image to obtain a target kidney structure image, a target kidney blood perfusion image and a target T1 relaxation time quantitative image; A segmentation module, used to segment the target kidney structure image using a trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla; a processing module, configured to: determine the morphology of the renal parenchyma from a target kidney structure map, determine the blood perfusion values ​​of the renal cortex and the renal medulla from the target kidney blood perfusion map, and determine the T1 relaxation time of the renal cortex and the renal medulla from a target T1 relaxation time quantitative map based on the first segmentation mask, the second segmentation mask, and the third segmentation mask; An evaluation module is used to evaluate the user's renal status according to the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation time of the renal cortex and the renal medulla.

2. The device according to claim 1, characterized in that The registration module is used to: convert the renal blood perfusion map and the T1 relaxation time quantitative map into the coordinate system of the renal structure map based on a non-rigid registration algorithm of feature point matching to obtain the target renal blood perfusion map and the target T1 relaxation time quantitative map, and the target renal structure map is the renal structure map.

3. The device according to claim 2, characterized in that Registration module for: Determining a plurality of first anatomical feature points in a target image, wherein the target image is one of the renal blood perfusion image and the T1 relaxation time quantitative image; Determine a plurality of second anatomical feature points in the kidney structure map; Pairing the plurality of first anatomical feature points with the plurality of second anatomical feature points using a point-by-point mutual information method to obtain a plurality of feature point pairs; Determine a transformation matrix according to the plurality of feature point pairs; According to the transformation matrix, the target image is transformed into the coordinate system of the kidney structure image.

4. The device according to claim 1, characterized in that The acquisition module is used to: acquire a user's kidney structure map, an ASL image sequence of the user's kidney, and a T1 Mapping sequence of the user's kidney; determine the user's renal blood perfusion map based on the ASL image sequence; and determine the user's T1 relaxation time quantitative map based on the T1 Mapping sequence.

5. The device according to claim 1, characterized in that The training process of the kidney segmentation model includes: Acquire a training sample, wherein the training sample includes: a sample kidney structure image and an expected segmentation result; Inputting the sample kidney structure image into the kidney segmentation model to obtain an actual segmentation result of the kidney segmentation model; According to the expected segmentation result and the actual segmentation result, the parameters of the kidney segmentation model are optimized using a cross entropy loss function and a Dice loss function.

6. A method for processing kidney data, characterized in that: include: Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map; Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map; Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla; Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

7. An electronic device, characterized in that: include: A memory and a processor, wherein The memory is used to store programs; The processor is coupled to the memory and is configured to execute the program stored in the memory to implement: Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map; Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map; Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla; Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

8. The device according to claim 7, characterized in that The processor is further configured to implement: The renal status of the user is evaluated based on the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a computer, it can achieve: Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map; Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map; Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla; Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

10. The medium according to claim 9, characterized in that When the computer program is executed by a computer, it can also achieve: The renal status of the user is evaluated based on the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements: Obtain the user's renal structure map, renal blood perfusion map and T1 relaxation time quantitative map; Performing image registration on the kidney structure map, the kidney blood perfusion map and the T1 relaxation time quantitative map to obtain a target kidney structure map, a target kidney blood perfusion map and a target T1 relaxation time quantitative map; Segmenting the target kidney structure image using the trained kidney segmentation model to obtain a first segmentation mask of the renal parenchyma, a second segmentation mask of the renal cortex, and a third segmentation mask of the renal medulla; Based on the first segmentation mask, the second segmentation mask and the third segmentation mask, the morphology of the renal parenchyma is determined from the renal structure map, the blood perfusion values ​​of the renal cortex and the renal medulla are determined from the target renal blood perfusion map, and the T1 relaxation time of the renal cortex and the renal medulla are determined from the target T1 relaxation time quantitative map.

12. The product according to claim 11, characterized in that When the computer program is executed by a processor, it can also achieve: The renal status of the user is evaluated based on the morphology of the renal parenchyma, the blood perfusion values ​​of the renal cortex and the renal medulla, and the T1 relaxation times of the renal cortex and the renal medulla.

Images