IgA nephropathy prognosis method, system, and apparatus based on immunofluorescence images

Abstract

The application discloses an IgA nephropathy prognosis method, system and device based on an immunofluorescence image, belongs to the technical field of image data processing, and comprises the following steps: obtaining an identification model and a pathology model; extracting pathological features from an immunofluorescence image through the identification model; obtaining an IgA nephropathy prognosis condition through pathology model prediction of the pathological features; the extraction method of the pathological features comprises the following steps: cutting an immunofluorescence image into multiple small blocks; establishing labels for the small blocks to obtain a second training set; training the second training set based on a machine learning method to obtain the identification model; predicting the probability of the small blocks and the labels thereof based on the identification model; and constructing the pathological features according to the probability and the labels. The method based on computer vision extracts pathological features from an immunofluorescence image, and combines the machine learning method to predict the IgA nephropathy prognosis, is beneficial to automatic prediction, and avoids errors and omissions caused by manual naked-eye identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image data processing, in particular to an IgA nephropathy prognosis method, system and device based on immunofluorescence images. BACKGROUND

[0002] IgA nephropathy (IgAN) is the presence of dominant or co-dominant IgA deposition in the mesangial area, which is considered a primary glomerular disease and is the most common form of primary glomerular nephritis. Studies have shown that IgA deposition in the mesangial area and glomerular capillary loop is associated with more severe clinical and histopathological manifestations.

[0003] The core pathological marker of IgA nephropathy is the deposition of immune complexes mainly composed of IgA in the mesangial area of the glomerulus. This deposition is usually diffuse in granular or mass form, and in some cases it can extend along the capillary loop. Immunofluorescence examination can directly show the localization of IgA in the glomerulus through specific antibody labeling, and is an essential means for diagnosing the disease. IgA immunofluorescence examination can directly show the localization of IgA in the glomerulus through specific antibody labeling, and is an essential means for diagnosing the disease. IgA immunofluorescence images can show features such as deposition site, brightness and shape. Currently, these features are extracted from the images by manual visual inspection. However, there are subjective problems in reading the film, there is heterogeneity between different doctors, and key information may be missed by the naked eye. SUMMARY

[0004] To solve the above technical problems in the prior art, the present application provides an IgA nephropathy prognosis method, system and device based on immunofluorescence images, which extracts pathological features based on IgA immunofluorescence images and establishes a pathological model according to the pathological features, and makes an IgA nephropathy prognosis through the pathological model.

[0005] The present application discloses an IgA nephropathy prognosis method based on immunofluorescence images, comprising the following steps: obtaining a recognition model and a pathological model; identifying the immunofluorescence image through the recognition model to extract pathological features; predicting the pathological features through the pathological model to obtain the IgA nephropathy prognosis; wherein the extraction method of the pathological features comprises: dividing the immunofluorescence image into multiple small blocks; establishing a label for the small blocks to obtain a second training set; training the second training set based on a machine learning method to obtain the recognition model; predicting the probability and label of the small blocks based on the recognition model; and constructing the pathological features according to the probability and label.

[0006] Preferably, the prediction method of the pathological model comprises:

[0007] Based on the machine learning method, the training set is trained according to the pathological features to obtain the pathological model, and the pathological model is used to predict the IgA nephropathy prognosis.

[0008] Preferably, the specific method for constructing pathological features includes the following steps:

[0009] Based on the recognition model, the probability of small blocks and their labels are predicted to construct the third feature;

[0010] Combined with histogram statistics, the third small block is binned to obtain buckets;

[0011] Construct the fourth feature based on the probability of the small blocks in the bucket and the frequency of the label;

[0012] The third feature is vectorized based on the bag-of-words model, and the fifth feature is obtained based on the TF-IDF transformation;

[0013] The fourth feature and the fifth feature are fused to obtain the pathological feature.

[0014] Preferably, more specific methods for extracting pathological features include:

[0015] Preprocessing of IgA immunofluorescence images;

[0016] The pretreated IgA immunofluorescence image was divided into several small blocks;

[0017] screening valid small blocks from the plurality of small blocks;

[0018] Normalize the valid small blocks to obtain the third small block;

[0019] Create labels for the third small piece and obtain the second training set;

[0020] Based on the machine learning method, the second training set is trained to obtain a recognition model;

[0021] Based on the recognition model, predict the probability of the third small block;

[0022] According to the prediction threshold and probability, the label of the third small block is obtained, and the third feature is constructed according to the probability and label;

[0023] Combined with histogram statistics, the probability distribution of the third small block is obtained;

[0024] Bin the third small piece to obtain buckets;

[0025] After calculating the probability of the third small block and the frequency of the label in the bucket, normalization is performed to construct the fourth feature of the bucket;

[0026] After vectorizing the third feature based on the bag-of-words model, the fifth feature is obtained based on the TF-IDF transformation.

[0027] Fusing the fourth feature and the fifth feature to obtain a sixth feature vector and a feature set;

[0028] The sixth eigenvector of the feature set is screened to obtain the pathological features.

[0029] Preferably, the pathological feature or the sixth eigenvector is expressed as:

[0030]

[0031] in, is the feature connector, features fusion Expressed as the sixth eigenvector or pathological feature, Histo Prob and Histo Pred is the parameter of the fourth characteristic, Bow prob and Bow pred is the parameter of the fifth feature.

[0032] Preferably, the method of screening effective small blocks from a plurality of small blocks comprises:

[0033] Determining whether the proportion of bright pixels in the small block exceeds a first threshold;

[0034] If so, exclude the small piece;

[0035] If not, keep the small piece.

[0036] Preferably, the method for screening the sixth eigenvector of the feature set includes:

[0037] Methods for selecting the sixth eigenvector include:

[0038] A correlation-based filtering method retains the sixth eigenvector whose Pearson correlation coefficient exceeds the fourth threshold;

[0039] Using univariate Cox regression, the sixth eigenvector with a p-value below the fifth threshold was retained;

[0040] Select non-zero features to obtain pathological features.

[0041] Preferably, the machine learning method for training the recognition model includes any of the following models:

[0042] ResNet18, ResNet50, Inception_v3, DenseNet121, and VGG19.

[0043] Preferably, the pathology module includes: a Cox proportional hazards model or a nomogram model;

[0044] Based on the Min-Max normalization method, the probability and frequency of the label in the bucket are normalized.

[0045] The present invention also provides a system for implementing the above method, including a pathological feature recognition module and a prognosis module. The pathological feature recognition module is used to predict the immunofluorescence image through the recognition model and extract the pathological features; the prognosis module is used to predict the pathological features through the pathological model and obtain the prognosis of IgA nephropathy.

[0046] The present invention also provides a device comprising a processor and a memory,

[0047] The memory stores codes, and when the codes are processed by the processor, the above-mentioned IgA nephropathy prognosis method is implemented.

[0048] Compared with the existing technology, the beneficial effects of the present invention are: based on the computer vision method, pathological features are extracted from the IgA immunofluorescence image, and the prognosis of IgA nephropathy is predicted in combination with the machine learning method, which is conducive to automated prediction, avoids errors and omissions caused by manual visual recognition, and demonstrates robust prediction capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of the IgA nephropathy prognosis method based on multimodal data of the present invention;

[0050] Figure 2 It is a flow chart of the method for extracting pathological features;

[0051] Figure 3 It is the ROC curve of the training set of the recognition model;

[0052] Figure 4 is the test set ROC curve of the recognition model;

[0053] Figure 5 It is the KM curve diagram of the training set of the pathological model;

[0054] Figure 6 It is the KM curve diagram of the test set of the pathological model;

[0055] Figure 7 This is a diagram showing the activation of Grad-CAM;

[0056] Figure 8 This is the structure diagram of the COX univariate regression analysis of clinical characteristics;

[0057] Figure 9 It is the KM curve diagram of the training set of the first model;

[0058] Figure 10 This is the KM curve of the test set of the first model;

[0059] Figure 11 It is the KM curve diagram of the training set of the prognostic model;

[0060] Figure 12 It is the KM curve diagram of the test set of the prognostic model;

[0061] Figure 13 is the nomogram model for survival risk;

[0062] Figure 14 It is a system logic block diagram of the present invention. DETAILED DESCRIPTION

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0064] The present invention is described in further detail below with reference to the accompanying drawings:

[0065] Overview: IgA nephropathy (IgAN) is characterized by immunofluorescence detection of IgA deposits with or without C3 in the mesangial region. Microscopic pathological changes vary widely, ranging from mild lesions to crescentic nephritis (including minimal change disease, endocapillary proliferation, FSGS, membranoproliferative, crescentic, proliferative sclerosis, combined membranous nephropathy, and combined MCD). The most common pathological type is mesangial cell proliferation and matrix increase in the mesangial region, often accompanied by segmental sclerosis, crescents of varying sizes, and endothelial cell proliferation. The most popular classification is the Oxford EST (MEST) classification, proposed in 2009. It assesses pathological severity based on M (mesangial cell proliferation), E (endothelial cell proliferation), S (segmental sclerosis), and T (extent of tubulointerstitial damage in the renal cortex). This classification method relies primarily on subjective visual identification.

[0066] The pathogenesis of immunoglobulin A (IgA) nephropathy is the production of galactose-deficient IgA1 (Gd-IgA1) antibodies. Gd-IgA1 forms immune complexes that accumulate in the renal mesangium and cause renal damage. Gd-IgA1 not only has a tendency to self-aggregate but also amplifies the pathogenic effects of renal deposition through abnormal binding to serum proteins such as fibronectin. Deposition of IgA in the mesangium and glomerular capillary loops is associated with more severe clinical and histopathological manifestations.

[0067] The first aspect of the present invention provides a method for prognosticating IgA nephropathy based on immunofluorescence images, such as Figure 1 As shown, the following steps are included:

[0068] Step 101: Divide the immunofluorescence image into multiple small blocks.

[0069] Step 102: Create labels for the small blocks to obtain a second training set.

[0070] Step 103: Based on a machine learning method, the second training set is trained to obtain a recognition model.

[0071] Step 104: Predict the probability of the patch and its label through the recognition model.

[0072] Step 105: Construct pathological features based on the probabilities and their labels.

[0073] Step 106: Based on a machine learning method, the training set is trained according to the pathological features to obtain a pathological model, which is used to predict the prognosis of IgA nephropathy.

[0074] Visual recognition is performed through the recognition model, and visual features are converted into pathological features, which is conducive to automated prediction, avoids errors and omissions caused by manual visual recognition, demonstrates robust prediction capabilities, and realizes multimodal data fusion. Multimodal data fusion has a gain effect on long-term prognosis prediction.

[0075] In one specific example, historical data from patients diagnosed with IgA nephropathy by renal biopsy and followed for at least six months were collected from the First Medical Center of a certain hospital. A total of 488 subjects were included and randomly divided into a training set (n=341) and a test set (n=147). The prognostic endpoint was set as end-stage renal disease or a 50% decrease in eGFR. The collection of historical data was approved by the medical committee and the patients.

[0076] like Figure 2 Specific methods for extracting pathological features include:

[0077] Step 201: Preprocessing the IgA immunofluorescence image.

[0078] Preprocessing can include data augmentation and normalization. During image preparation, we applied Z-score normalization to the RGB channels to standardize the intensity distribution. During training, we used online data augmentation techniques, including random cropping and horizontal and vertical flipping, to increase data variability. During model testing, only normalization was applied to small patches to ensure consistency in data processing.

[0079] Step 202: Divide the pre-processed IgA immunofluorescence image into a plurality of patches.

[0080] In one specific test, the size of the small block was 512x512 pixels, and its large size could be processed at 20x magnification.

[0081] Step 203: screening effective small blocks from the plurality of small blocks.

[0082] For example, exclude small blocks mainly filled with bright pixels, which have a proportion of bright pixels exceeding a first threshold value and contain the least useful data. This can be achieved by eliminating all black backgrounds.

[0083] Step 204: normalizing the effective small blocks to obtain third small blocks.

[0084] Step 205: establishing labels for the third small blocks Patch prob to obtain a second training set.

[0085] Specifically, according to the case of end-stage renal disease or eGFR reduction by a second threshold value (such as 50%), IgA immunofluorescence images and patients are divided into high-risk and low-risk groups, and the high-risk and low-risk group labels are used to mark the corresponding small blocks / third small blocks. However, the grouping method is not limited to this, and the X-tile software can be used to determine the optimal survival cut-off point to divide the patients into high-risk / low-risk groups, and the grouping labels can be marked on the corresponding small blocks.

[0086] Step 206: training the second training set based on a machine learning method to obtain a recognition model.

[0087] Specifically, the recognition model uses ResNet18, ResNet50, Inception_v3 and DenseNet121, preferably ResNet 18 model, and the performance of each model in the training set is shown in Table 1, and the performance in the test set is shown in Table 2. Among them, DenseNet121 is the most complex, and ResNet50 is a widely used convolutional neural network model.

[0088] To ensure robust performance in different populations, transfer learning is used to initialize model parameters using pre-trained weights on the ImageNet dataset, allowing the model to utilize general visual features. To promote better generalization ability, a cosine decay learning rate scheduling strategy is used, which is defined as:

[0089] η t = η min + 0.5 × (η max - η min ) × (1+cos(π × T cur / T i ))

[0090] wherein,η t is the current learning rate, η min represents the minimum learning rate, η max is the maximum learning rate, T cur The current iteration number, T i Corresponding to the total number of iteration cycles, such as 16.

[0091] The training process is optimized using stochastic gradient descent (SGD) and softmax cross entropy as the loss function to improve the efficiency and performance of the model.

[0092] Table 1

[0093]

[0094] Table 2

[0095]

[0096] Among them, Acc (Accuracy) refers to the proportion of correct predictions among all prediction results. AUC (Area Under the Curve) is usually used to evaluate the performance of a binary classification model. It is the area under the ROC curve (Receiver Operating Characteristic Curve). Sensitivity is also called the true positive rate, which refers to the proportion of people who are tested positive among the population that actually has the disease. Specificity is also called the true negative rate, which refers to the proportion of people who are tested negative among the population that actually does not have the disease. PPV (Positive Predictive Value) refers to the proportion of people who are actually sick among the population with a positive test result. NPV (Negative Predictive Value) refers to the proportion of people who are actually not sick among the population with a negative test result.

[0097] The ROC curve of the training set of the recognition model can be found in Figure 3 , the ROC curve of the test set can be found in Figure 4. In the ResNet18 model, the AUC values ​​in the training and test cohorts were 0.610 and 0.617, respectively. These AUC metrics represent the model's ability to effectively distinguish between categories, indicating that its performance is at a moderate level. The AUC for the training set fell within the 95% confidence interval (CI) of 0.5977-0.6213, while the AUC for the test set fell within the 95% CI of 0.5968-0.6372, indicating that the model's performance on different datasets has a certain degree of consistency, although its discriminative ability is limited.

[0098] The analysis results indicate that while the ResNet18 model performs acceptably, it is not the highest-performing model available. However, this choice may have been influenced by other factors, such as model simplicity, computational efficiency, or generalization performance during training and testing. In applications, efforts should focus on enhancing the model's robustness and discriminative capabilities, perhaps by exploring model tuning, augmentation techniques, or incorporating more discriminative features during training.

[0099] After the recognition model is trained, it can be extended to predict the label and probability of each patch. These probabilities are aggregated through histogram features and bag-of-words (BoW) features to facilitate prediction at the level of the entire immunofluorescence image.

[0100] Step 207: Based on the recognition model, predict the probability of the third small block Patch pred , according to the prediction threshold and probability, obtain the label of the third small block and the third feature.

[0101] If the probability of the third small block being a high-risk group is predicted, when the probability exceeds the third threshold, the third small block is determined to be a high-risk group. The third feature of the third small block includes: probability Patch pred and tags Patch prob .

[0102] Step 208: Combined with histogram statistics, the third small block is binned to obtain buckets; and the fourth feature is obtained based on the probability and label frequency of the third small block in the bucket.

[0103] More specifically, the probability distribution of the third small block is obtained by combining histogram statistics (e.g., number of bins = 50, step size = 0.02, but not limited to this). The third small block is binned to obtain buckets. The probability of the third small block and the frequency of the label in the bucket are calculated and normalized to construct the fourth feature of the bucket: Histo Prob and Histo Pred .

[0104] The Min-Max normalization method can be used to normalize the probability and frequency of the label in the bucket.

[0105] Step 209: Based on the Bag-of-Words model (BOW), the third feature is vectorized and the fifth feature is obtained based on the TF-IDF transformation: Bow prob and Bow pred .

[0106] Step 210: Fuse the fourth feature and the fifth feature to obtain the sixth feature vector features fusion and feature sets, i.e., pathological features.

[0107] The feature set includes the sixth feature vectors of multiple small blocks, the sixth feature vector features fusion Expressed as:

[0108]

[0109] in, Feature connector.

[0110] Step 211: Screen the sixth feature vector of the feature set to obtain pathological features / pathological features pathomics .

[0111] First, a correlation-based filtering method is used to retain features with a Pearson correlation coefficient exceeding a fourth threshold (e.g., 0.9). Then, a further selection is performed using univariate Cox regression to retain only features with a p-value below a fifth threshold (e.g., 0.05). Non-zero features can also be selected.

[0112] In one specific implementation, after normalizing and partitioning the IgA immunofluorescence image (512×512 pixels / block), a pre-trained ResNet-18 model was used to extract the third eigenvector (containing morphological parameters and spatial distribution characteristics) of each image block. This was accomplished using a weakly supervised learning strategy to generate predicted labels and corresponding probabilities for each individual block / third block. This led to the generation of two core feature sets: 101 probabilistic features: based on the high-risk / low-risk probability distribution of the image block, the proportion of blocks at each risk level was calculated using histogram binning; and two predicted label features.

[0113] Step 212: The training set is trained based on a machine learning method and pathological features to obtain a pathological model. For example, the pathological model is trained based on a Cox proportional hazards model (also known as a multivariate Cox model).

[0114] like Figure 5 andFigure 6 The Kaplan-Meier (KM) curve for the survival analysis of the pathological model showed that the C-index (Concordance Index) for the training and test sets was 0.757 and 0.755, respectively. The C-index, or concordance index, is used to evaluate the predictive ability of the model.

[0115] Visualization can be achieved based on Grad-CAM, using Gradient Weighted Class Activation Mapping (Grad-CAM) to visualize the recognition ability of deep learning models on various samples. Figure 7 The Grad-CAM activations of the final convolutional layer are shown, key regions influencing prognostic prediction are identified, and insights into model interpretability are provided.

[0116] Clinical features in historical data can be divided into continuous variables, categorical variables, and Oxford pathology classification variables. Univariate analysis and multivariate analysis can be used to analyze clinical features, such as using Cox regression to screen for clinical features (P < 0.05).

[0117] As shown in Table 3, baseline comparisons of the training and test sets showed that there were no significant differences in the continuous variables: age, proteinuria, mean arterial pressure (MAP), and baseline estimated glomerular filtration rate (eGFRbaseline) between the training and test sets (p>0.05). Specifically, the mean age was 35.16±11.01 years, 35.16±11.19 in the training and test sets, and 35.18±10.63 in the test sets (p=0.645). The mean proteinuria level was 1.61±1.53 g / d, and the distribution was consistent between the two groups (p=0.176).

[0118] Categorical variables: RAS inhibitor use (86.27% vs 87.76%, p=0.63) and immunosuppression use (56.30% vs 51.02%, p=0.329) were balanced between the two groups. Continuous variables were normalized using the Shapiro-Wilk test and analyzed using the t-test and Mann-Whitney U test, respectively. Categorical variables were analyzed using the chi-squared test. In one specific embodiment, the analysis was performed using Python 3.7.12 and scikit-learn 1.0.2, and the model was trained using an NVIDIA 4090 GPU and PyTorch 1.8.1.

[0119] There was no statistical difference in the distribution of each component (M / E / S / T) of the Oxford pathological classification (MEST-C score): segmental sclerosis (S1) accounted for 72.13% of the whole group, 73.31% of the training set, and 69.39% of the test set (p=0.437), and tubular atrophy (T1-2) accounted for 73.18% of the whole group, with no significant shift between groups (p=0.143).

[0120] Table 3

[0121]

[0122] In Table 3, continuous variables are presented as mean ± standard deviation; categorical variables are presented as frequency (percentage). P values ​​reflect the difference between the training and test sets; *p < 0.05 was considered statistically significant. RAS: renin-angiotensin system inhibitor; MEST-C: Oxford classification (mesangial proliferation (M), endothelial proliferation (E), segmental sclerosis (S), tubular atrophy (T), and cellular crescents (C).

[0123] The method for screening clinical characteristics can be based on the COX univariate regression analysis method or the Pearson correlation coefficient method. Figure 8 Oxford classification of M, S, and T lesions, immunosuppressant use, urine protein, and mean arterial pressure were associated with the prognosis of IgA nephropathy. X-tile was used to determine the optimal risk stratification threshold, dividing the patients into low-risk and high-risk groups.

[0124] Based on the machine learning method, the first model is trained according to the clinical characteristics. Figure 9 and Figure 10 The survival analysis KM (Kaplan-Meier) curve showed that the C-index (Concordance Index, C-Index) of the training set and test set were 0.855 and 0.860, respectively.

[0125] The prognostic model was constructed based on the integration of immunofluorescence omics features and clinical characteristics, such as Figure 11 and Figure 12 The survival analysis KM curves showed that the model's C-index for the training and test sets was 0.882 and 0.888, respectively. This performance outperformed the first model based solely on clinical features. X-tile was used to determine the optimal risk stratification threshold, dividing patients into low-risk and high-risk groups.

[0126] Time-dependent survival analysis: As shown in Table 4, in the 5-year survival prediction analysis, the AUC values ​​of different models showed significant differences in predictive efficacy. The first model, also known as the clinical model, achieved AUC values ​​of 0.884 and 0.927 in the training and test sets, respectively, demonstrating robust predictive ability. The prognostic model, also known as the combined model, significantly improved its AUC value to 0.931 (training set) and 0.940 (test set) by integrating clinical and pathological features, validating the synergistic advantage of multimodal data (p < 0.001).

[0127] In the 7-year survival prediction, the AUC values ​​of each model were generally lower than those in the 5-year analysis, but still maintained a consistent pattern: the AUC of the first model training set was 0.908, and the test set slightly dropped to 0.871; the AUC of the prognostic model training set and test set were 0.917 and 0.901, respectively, continuing to lead, further confirming the gain effect of cross-modal integration on long-term prognosis prediction (ΔAUC = +4.7% vs clinical model).

[0128] Table 4

[0129]

[0130] The present invention also constructs a nomogram model of 3-year and 5-year survival risk based on pathological and clinical characteristics, such as Figure 13 , the corresponding survival risk can be found based on the corresponding characteristics. A nomogram is a graphical tool used to predict or evaluate the probability or value of an event. It integrates multiple related variables for comprehensive analysis.

[0131] The second aspect of the present invention provides a system for implementing the above method, such as Figure 14 , including pathological feature recognition module 1 and prognosis module 2,

[0132] The pathological feature recognition module 1 is used to predict the immunofluorescence image and extract the pathological features through the recognition model;

[0133] Prognostic module 2 is used to predict pathological features through a pathological model to obtain the prognosis of IgA nephropathy.

[0134] The prognosis module can also be used to predict the prognosis by the historical data and the IgA immunofluorescence image through the prognosis model or the first model.

[0135] The system also provides a model training module 3 for training a training set according to pathological features based on a machine learning method to obtain a pathological model, which is used for IgA nephropathy prognosis prediction.

[0136] The third aspect of the present application provides a device, which comprises a processor and a memory, and the memory stores codes which are processed by the processor to realize the above-mentioned prognosis method.

[0137] The present application extracts pathological features from IgA immunofluorescence images based on computer vision methods, which can automatically extract pathological features and avoid errors and omissions caused by manual / visual recognition. In addition, the present application combines clinical features to predict the prognosis of IgA nephropathy, which is beneficial to automatic prediction and has robust prediction ability. The present application realizes multi-modal data fusion, and multi-modal data fusion has a gain effect on long-term prognosis prediction.

[0138] A multi-modal survival prediction model is constructed by feature fusion, and a Cox proportional hazards model is finally established to complete survival analysis. Experiments show that this method can effectively capture potential pathological feature patterns, and the multi-modal model exhibits a C-index of 0.888 in the test set, providing reliable prognosis estimates for medical or patients, and serving as a reliable tool for individualized medical evaluation. It should be noted that the prognosis method of the present application is used to provide suggestions for medical personnel or patients, and does not belong to the method of disease treatment or diagnosis.

[0139] The above is only a preferred embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An IgA nephropathy prognosis method based on immunofluorescence imaging, characterized in that: The following steps are involved: Obtain recognition models and pathological models; Using the recognition model, predicting the immunofluorescence image and extracting pathological features; Based on the machine learning method, the training set is trained according to the pathological characteristics to obtain the pathological model; The pathological features are predicted through the pathological model to obtain the prognosis of IgA nephropathy; Among them, the pathological feature extraction methods include: Preprocessing of IgA immunofluorescence images; The pretreated IgA immunofluorescence image was divided into several small blocks; screening valid small blocks from the plurality of small blocks; Normalize the valid small blocks to obtain the third small block; Create labels for the third small piece and obtain the second training set; Based on the machine learning method, the second training set is trained to obtain a recognition model; Based on the recognition model, predict the probability of the third small block; According to the prediction threshold and probability, the label of the third small block is obtained, and the third feature is constructed according to the probability and label; Combined with histogram statistics, the probability distribution of the third small block is obtained; Bin the third small piece to obtain buckets; After calculating the probability of the third small block and the frequency of the label in the bucket, normalization is performed to construct the fourth feature of the bucket; After vectorizing the third feature based on the bag-of-words model, the fifth feature is obtained based on the TF-IDF transformation. Fusing the fourth feature and the fifth feature to obtain a sixth feature vector and a feature set; The sixth eigenvector of the feature set is screened to obtain the pathological features.

2. The IgA nephropathy prognosis method according to claim 1, characterized in that: The pathological feature or the sixth eigenvector is expressed as: ； in, is the feature connector, features fusion Expressed as the sixth eigenvector or pathological feature, Histo Prob and Histo Pred is the parameter of the fourth characteristic, Bow prob and Bow pred is the parameter of the fifth feature.

3. The IgA nephropathy prognosis method according to claim 1, wherein Methods for screening valid small blocks from multiple small blocks include: Determining whether the proportion of bright pixels in the small block exceeds a first threshold; If so, exclude the small piece; If not, retain the small piece.

4. The IgA nephropathy prognosis method according to claim 1, characterized in that: Methods for screening the sixth eigenvector of the feature set include: Methods for selecting the sixth eigenvector include: A correlation-based filtering method retains the sixth eigenvector whose Pearson correlation coefficient exceeds the fourth threshold; Using univariate Cox regression, the sixth eigenvector with a p-value below the fifth threshold was retained; Select non-zero features to obtain pathological features.

5. The IgA nephropathy prognosis method according to claim 1, characterized in that: Machine learning methods for training recognition models include any of the following models: ResNet18, ResNet50, Inception_v3 and DenseNet121.

6. The IgA nephropathy prognosis method according to claim 1, characterized in that: Pathology modules include: Cox proportional hazards model or nomogram model; Based on the Min-Max normalization method, the probability and frequency of the label in the bucket are normalized.

7. An IgA nephropathy prognosis system based on immunofluorescence images, characterized in that: Used to implement the IgA nephropathy prognosis method according to any one of claims 1 to 6, comprising a pathological feature recognition module and a prognosis module, The pathological feature recognition module is used to predict immunofluorescence images and extract pathological features through the recognition model; The prognostic module is used to predict pathological features through the pathological model and obtain the prognosis of IgA nephropathy.

8. An IgA nephropathy prognosis device based on immunofluorescence images, characterized in that: including processor and memory, The memory stores codes, and when the codes are processed by the processor, the IgA nephropathy prognosis method according to any one of claims 1 to 6 is implemented.

Images