273 results about "Digital pathology" patented technology

The invention relates to the field of image analysis, in particular to a temporal bone disease classification method and system based on a multi-modal medical image fusion technology. The method comprises the following steps: acquiring a multi-modal image of a patient, performing adaptive distortion correction, and generating a standardized image set; performing layer-by-layer anatomical structure semantic segmentation and multi-modal image fusion on the standardized image set to construct an image fusion framework; according to the image fusion framework, performing intelligent recognition on the fine structure of the temporal bone, and constructing a personalized temporal bone anatomical structure chart; performing tissue function state analysis and digital pathology dynamic simulation based on the personalized temporal bone anatomical structure chart, and constructing a digital pathology model; and performing intelligent pathological feature classification based on the digital pathological model to obtain an intelligent classification report. According to the method, rapid, efficient and accurate temporal bone disease classification is realized.

The invention discloses a renal clear cell carcinoma prognosis prediction method based on multi-mode MRI (Magnetic Resonance Imaging) image and digital pathological omics fusion. The method comprises the following steps: S1, collecting a training data set based on an MR image and a pathological image; s2, feature extraction of MR radiomics; s3, deep learning feature extraction of the pathological image; s4, an MR-pathological feature fusion module; and S5, deploying the network. According to the method, depth features with prognosis information are obtained from two scales of pre-treatment images and post-operation pathology, effective features are extracted by adopting image omics and a convolutional neural network mode according to data characteristics of MR images and pathology images, and depth fusion of the two types of features is completed in a hidden space through a multi-task guiding mode, so that the accuracy of the MR image and the pathology image is improved. A precise prognosis model with multi-scale information is provided, and the method has a relatively strong clinical application prospect and is of great significance for realizing precise immunotherapy and improving prognosis of a patient.

The system and method for processing a digital pathology image using a machine learning model that includes a self-supervised hierarchical Vision Transformer (ViT) configured to perform unsupervised clustering with multiple classification tokens. The method includes receiving a digital pathology image that depicts a tissue slice stained with histological dyes. The digital pathology image may be processed to generate a result comprising multiple predicted classifications of individual patches of the digital pathology image. The result is generated by a machine-learning model using a self-supervised hierarchical Vision Transformer (ViT) that may further comprise a multi-head self-attention module configured to predict a crosspatch relevance metric using an attention mechanism for each individual patch in the digital pathology image thereby assigning the individual patches to a cluster based on the crosspatch relevance metrics.

The present disclosure relates to techniques for efficient development of initial models and efficient model update and / or adaptation to a different image domain using an adaptive learning framework. For efficient development of initial models, a two-step development strategy may be performed as follows: Phase 1: Model preconditioning, where an artificial intelligence system leverages existing annotated datasets and improves learning skills through training of these datasets; and Phase 2: Target-model training, where an artificial intelligence system utilizes the learning skills learned from Phase 1 to extend itself to a different image domain (target domain) with less number of annotations required in the target domain than conventional learning methods. To efficiently perform model update and adaptation to new datasets after initial model development, a digital pathology scenario is identified, an adaptive-learning method is selected based on the scenario, and the model is updated and adapted to new datasets using the adaptive-learning method.

The invention provides a pathology image segmentation method and device based on category labels and a readable storage medium, and the method comprises the steps: segmenting a full-view digital pathology (WSI) image, and extracting a feature map containing local textures and global semantics through a ResNet, ViT or a pathology-dedicated pre-training large model UNI; calculating the contribution degree of an image block to a classification result through an attention mechanism, and extracting the actual influence of features on a classification decision in combination with gradient analysis; and fusing the two weights by adopting a sorting weighting strategy, generating a lesion area mask through Gaussian blur and Otsu method threshold segmentation, and finally superposing the lesion area mask to an original image to output an interpretable segmentation result. According to the method, weak supervision segmentation can be realized only through slice-level labels, the labeling cost is remarkably reduced, the positioning precision is improved through complementary fusion of attention and gradient information, a visual and visual lesion area is generated, the model transparency and clinical practicability are enhanced, and the method is suitable for various pathological image analysis scenes.

The invention provides an instance segmentation method and device for early intestinal cancer vessel infringement phenomenon analysis and a readable storage medium, and the method comprises the steps: constructing an end-to-end automatic process: firstly, carrying out the multi-magnification overlapping cutting of a digital pathological image, and carrying out the high-sensitivity instance segmentation through a Mask2form instance segmentation network; combining the overlapped masks by adopting an efficient union lookup algorithm, and recursively complementing incomplete instances in combination with an ROI (Region of Interest) expansion algorithm; hE, CD-31 and D2-40 dyeing full slice level alignment is realized through rigid-non-rigid-micro registration, and a three-mode instance level graph block is cut based on a registration result; and finally, fusing multi-modal features by using a hybrid expert network enhanced by a large pathological model, and dynamically screening expert paths to carry out true and false positive judgment. The invention provides an efficient technical scheme for early accurate diagnosis of intestinal cancer, and is suitable for pathological big data analysis and clinical auxiliary diagnosis.

The invention belongs to the technical field of medical image processing, and particularly relates to an esophageal cancer treatment effect and survival combined prediction method and system based on multiple modalities, and the method comprises the steps: obtaining a preoperative CT image and Hamp of an esophageal squamous cell carcinoma patient; e, the dyed digital pathological image, transcriptome data and clinical diagnosis and treatment information are preprocessed and subjected to feature extraction, and radiomics embedding representation, pathomics embedding representation and pipeline branch embedding representation are obtained respectively; the radiomics embedded representation, the pathomics embedded representation and the pipeline branch embedded representation are aligned and input into a multi-modal fusion module based on a multi-head self-attention mechanism for feature fusion, and fusion feature representation is generated; and based on the fusion feature representation, synchronously outputting a curative effect prediction result and a survival prediction result by using a multi-task output module, and evaluating model prediction performance by using a curative effect evaluation index and a survival analysis index.

The invention discloses a UNET supervised network slice HE virtual staining method and system for pathological analysis, and belongs to the technical field of artificial intelligence digital pathological analysis. Global scanning imaging is performed on a pathological slice to obtain an HE scanning image and a fluorescence confocal scanning image, and a UNET supervised network data set is established; a UNET supervised virtual dyeing network model is constructed; training and verifying the UNET supervised virtual dyeing network model by using the UNET supervised network data set; and carrying out HE virtual staining on the fluorescence imaging pathological section image by using the trained UNET supervised virtual staining network model. The method has the remarkable advantages in the aspects of dyeing precision, dyeing efficiency and robustness, and automatic and rapid virtual dyeing of different types of biological tissue sections can be achieved without accurate image registration.

The invention belongs to the field of digital pathological image processing, and particularly relates to an intelligent auxiliary diagnosis system and method based on cell contours. The intelligent auxiliary diagnosis method based on the cell contour comprises the following steps: S10, acquiring a stained pathological tissue image, separating an HE staining channel in the pathological tissue image through a color deconvolution algorithm, and identifying the position of a cell nucleus in a marked image according to a separation result as an initial position; calculating the staining intensity of each cell nucleus according to the separation result, constructing a contour characteristic spectrum based on the staining intensity of the cell nucleus, and extracting tissue microenvironment indication information in the pathological tissue image; s20, defining a dyeing concentration peak region as a first core region, and defining a cell nucleus edge diffusion region as a second peripheral region; and combining the geometrical morphology characteristics of the cell nucleus with the gradient distribution of the dyeing intensity. According to the scheme, the cells in the pathological tissue image can be accurately segmented and classified, a quantitative diagnosis basis can be provided, and the working pressure of doctors is relieved.

The invention discloses a hepatocellular carcinoma postoperative early recurrence prediction method based on multi-modal fusion. The method comprises the following steps: firstly, integrating clinical data of a training set, a preoperative enhanced CT image and a postoperative full-view digital pathological image, and carrying out standardized correction; then, traditional image omics features and deep learning features are extracted from the CT image, cell nucleus morphological features and tumor microenvironment spatial configuration features are extracted from the pathological image, and key feature signatures are screened out through a maximum correlation minimum redundancy algorithm (mRMR) and LASSO regression in combination with clinical features. And then carrying out progressive model construction by adopting an XGBoost algorithm, sequentially establishing a clinical single-mode model, an image single-mode model, a pathological single-mode model and a multi-mode fusion model, and explaining and visualizing the models by utilizing an SHAP value and a Grad-CAM technology. Finally, the performance of the model is evaluated in a multi-dimensional mode through internal cross validation, foresight and external independent validation, risk layering is carried out based on the prediction probability, and individualized postoperative management is guided.

Described herein are systems, methods, and programming for analyzing and classifying digital pathology images agnostic to sample processing techniques used to prepare the digital pathology images. In some embodiments, image data including a first image set and a second image set may be obtained. The first and second image sets may be processed using a first and second slide preparation machine, respectively. A first augmented view set and a second augmented view set may be generated based on augmentations applied to the first and second image sets. For each image, a first vision transformer to may be trained to: generate a first representation of an augmented view of the first augmented view set, and enhance a similarity between the first representation and a second representation of an augmented view of the second augmented view set. The second representation may be generated via a second vision transformer.

The invention discloses a pathological image sjogren syndrome automatic diagnosis method, device and equipment and a storage medium, and relates to the technical field of medical data processing, and the method comprises the steps: carrying out the image preprocessing of an original digital pathological section image, and obtaining an optimized image block; performing cell-tissue collaborative segmentation on the optimized image blocks to obtain a cell entity set and a tissue entity set; the cell entity set and the tissue entity set are mapped into a heterogeneous graph structure, and the heterogeneous graph structure takes cell graph nodes and tissue graph nodes as vertexes and takes a spatial adjacency relation as edges; and performing sicca syndrome state judgment based on the heterogeneous graph structure. According to the method, the heterogeneous graph structure is constructed, the cells and the tissues are abstracted into the nodes, the spatial adjacency relation edges are established, modeling of the global relation between the cells and the cross-scale relation between the cells and the tissues is achieved, global topology perception is achieved, the diagnosis accuracy is improved, and an end-to-end intelligent analysis process from a pathological image to sicca syndrome diagnosis is formed.

The invention provides a digital pathological section color calibration method and device, and the method comprises the following steps: obtaining a standard color image and an image to be subjected to color correction, and extracting the feature points of the standard color image and the feature points of the image to be subjected to color correction, matching the standard color image and the image to be subjected to color correction based on the feature points to obtain a standard color matching image and a matching image to be subjected to color correction; performing histogram color correction on the matching image to be subjected to color correction by taking a standard color matching image as a reference to obtain a first color correction image, and performing CCM color correction on the first color correction image by taking the standard color matching image as the reference to obtain a second color correction image, and performing gamma correction on the color of the second color correction image by taking a standard color matching image as a reference to obtain a color correction completed image. According to the scheme, all pixel information of the target image is fully utilized, the color correction process is quantified to eliminate artificial errors, and the efficiency and accuracy of color correction of the digital pathological image can be remarkably improved.

The invention relates to the technical field of digital pathology acquisition, and discloses a digital pathology picture acquisition method. The method comprises the following steps: acquiring sample characteristic data such as thickness, dyeing degree and structural characteristics of a tissue sample to be detected, and determining initial image acquisition parameters including exposure time, image resolution and optical magnification; and meanwhile, environment condition data such as temperature, humidity and environment illumination intensity of a scanning environment are collected, so that whether the initial parameters are adjusted or not is judged. When adjustment is needed, collecting preliminary image data, extracting quality features including image definition, color accuracy and detail retention degree, calculating feature values, and comparing the feature values with historical image quality feature values in a historical database; and if the same characteristic value does not exist in the historical database, calculating the similarity, and adjusting the initial image acquisition parameters according to the comparison result or the similarity. According to the method, sample characteristics and environmental conditions are comprehensively considered, and the quality of the digital pathological picture is effectively improved.

The invention provides a full-slice image classification method and system based on multi-branch attention and random instance masks and a medium, and the method comprises the steps: obtaining a full-slice digital pathological image, carrying out the image segmentation, and obtaining a plurality of instances; performing feature extraction based on a feature extraction network to obtain an instance feature sequence; carrying out parallel analysis on the instance feature sequence based on a multi-branch attention mechanism, executing a random Top-K instance mask operation, and carrying out weighted summation on the instance feature sequence based on the attention distribution of each attention branch; aggregating the packet level feature representations of all the attention branches, generating a comprehensive feature representation of the full-slice digital pathological image, and obtaining a classification prediction result; by setting a plurality of parallel attention branches, different branches are promoted to actively learn and capture a plurality of different visual modes existing in the full-slice digital pathological image, so that tumor heterogeneity can be effectively represented, and the generalization ability of full-slice digital pathological image classification is improved.

The invention provides a digital pathological image high-color accurate splicing method and device based on feature point matching. The method comprises the following steps: obtaining a target splicing region in a target splicing image and a to-be-spliced region in a to-be-spliced image based on a scanning sequence of digital pathological images; performing affine transformation on the to-be-spliced region by using the affine transformation matrix to obtain an initial correction region; constructing a global color mapping function, and mapping the initial correction image by using the global color mapping function to obtain a color correction image; and splicing the color correction image and the target splicing image based on the scanning sequence of the pathological images to obtain a digital pathological image splicing result. According to the scheme, only the target splicing area and the to-be-spliced area are subjected to feature point matching, the cumulative distribution function of the effective feature points is calculated according to the RGB channels, and the global color mapping function is constructed and optimized, so that accurate color correction is realized, and the visual integrity and consistency of the spliced image are improved.

The invention provides a digital pathological section auxiliary diagnosis warning device and method, and the device comprises a first region obtaining module which is used for obtaining a section warning region, and the predicted cancer probability of the section warning region is included in a cancer-free probability interval; the second area acquisition module is used for collecting a local area of which the predicted cancerous probability is within a cancerous probability interval in the slice warning area; the warning island display module is used for displaying a warning island in the slice viewing interface, and the warning island comprises a thumbnail of a local area; and the visual field following module is used for acquiring the target thumbnail selected by the user and displaying the slice visual field corresponding to the target thumbnail to the user. According to the digital pathological section auxiliary diagnosis warning device and method, the local area with the predicted cancer probability in the cancer probability interval in the section warning area is collected, and the corresponding thumbnail is displayed in the warning island, so that a user can conveniently check all high-risk tiny cancer lesions in a unified manner, the diagnosis accuracy of the section is improved, and missed diagnosis is avoided.

The present invention discloses a method and device for self-supervised color normalization of pathological images, which belongs to the technical field of combining digital pathology and image processing, and includes: constructing a pathological image database; designing a color normalization model, which includes a common feature domain extraction module, a content sensor, a scene sensor, and a fusion module, and the color normalization model can perform color conversion on the pathological image to obtain a color normalized image; based on the pixel-level difference between the input original pathological image and the color normalized image, a self-supervised loss function is constructed and the color normalization model is trained, and the model can realize adaptive color style normalization of an image of any unknown pathological data center toward an image of a selected pathological data center.

The invention belongs to the field of digital pathological image processing, and discloses an OpenSlide-based digital pathological image processing method and a related device, and the method comprises the steps: obtaining a digital pathological image, calling an OpenSlide library to analyze a pyramid structure of the image to generate a multi-resolution hierarchy, and dynamically calculating a loaded image region based on a slice request instruction input by a user; a double-Canvas rendering mode is adopted, a bottom layer Canvas loads an image area in real time, a labeling layer Canvas independently renders a labeling path, and separation of an image and a label is achieved; and generating a closed path based on the superposed image and the annotation mode, and exporting the annotation data in a general format. According to the method, the user interaction experience is improved, the interface operation is more intuitive, the process is simplified, and the drawing mode switching is convenient; the labeling efficiency is improved, real-time adjustment of complex contours is supported, and the workload is reduced; a data export function is enhanced, effective association of annotation information is realized, and multi-format universality is supported; multi-level support is improved, level switching is smooth, loading is fast, and tool performance and user experience are improved.

The invention relates to the technical field of medical image processing, and discloses a tumor cell accurate recognition and analysis system based on a digital pathological image, which effectively overcomes the problem of global context deficiency caused by traditional pathological image blocking processing by constructing a microcosmic and macroscopic parallel multi-scale feature extraction mechanism. A cell topological graph is constructed by utilizing spatial semantic double constraints to simulate a biological spatial distribution rule of tumor cells, and precise navigation and weighted enhancement of microscopic cell characteristics by macroscopic organization structure information are realized through a cross-scale attention aggregation technology. Therefore, the model can fully refer to the surrounding microenvironment when identifying the heterotypic cells, and the misjudgment risk caused by background noise or local form similarity is remarkably reduced; in addition, a structured decision-making mechanism based on manifold consistency eliminates isolated prediction noisy points and ensures the continuity and rationality of a diagnosis result on a biological structure.

In one embodiment, a method includes accessing a slide image associated with a tissue for a medical analysis, segmenting the slide image into a plurality of tiles, selecting one or more tiles from the plurality of tiles by one or more machine-learning models based on one or more criteria associated with the medical analysis, displaying the one or more selected tiles for user review via a user interface, receiving one or more user inputs associated with the one or more tiles via the user interface, and generating an analysis result for the medical analysis based on the one or more user inputs and the one or more tiles.

Segmentation or other classification of digital pathology images with a deep learning model allows for sophisticated spatial features for cancer diagnosis to be extracted in an automated, fast, and accurate manner. A tiered analysis of tissue structure based in part on deep learning methods is provided. First, tissues depicted in a digital pathology image are segmented into cellular compartments (e.g., epithelial and stromal compartments). Second, the heterogeneity in the different cellular compartments are examined based on a clustering algorithm. Tissue can then be characterized in terms of inertia (or other spatial measures or features), which can be used to recognize disease. In some instances, multidimensional inertia (i.e., inertia computed in different cellular compartments or clustered components) can be used as an indicator of disease and its outcome.

Techniques for using combination stain types for machine learning models for digital pathology are described herein. In an example, a system accesses a first image of a sample comprising an immunohistochemistry (IHC) stain for a biomarker. The system accesses a second image of the sample comprising a hematoxylin and eosin (H&E) stain for nuclei. The system can segment tissue regions in the one or more first images and the second image, partitions the tissue regions in the one or more first images and the second image, and extracts features from the set of tiles using a feature extractor. The system can generate, by a machine-learning model, an output classification indicating a first phenotype based on the features extracted from the set of tiles. The machine-learning model can include one or more classifiers and an aggregation model that provides an aggregated output for the set of tiles.

The embodiment of the invention discloses a gastric biopsy pathological risk degree hierarchical identification processing method and system, and relates to the technical field of medical artificial intelligence, and the method comprises the steps: obtaining a digital pathological image of a to-be-diagnosed gastric biopsy pathological section; analyzing the digital pathological image based on an artificial intelligence classification model to obtain a risk level corresponding to the digital pathological image; distributing the digital pathological image to a preset diagnosis path matched with the risk level; wherein the preset diagnosis paths corresponding to different risk levels are different in detail degrees of auxiliary diagnosis information provided by the system or triggered automatic auditing processes; receiving a diagnosis result of manual examination and verification for the digital pathological image, and using the diagnosis result as feedback data for updating the artificial intelligence classification model; through automatic risk layering and differentiated path distribution, diagnosis resources can be optimized, diagnosis efficiency and accuracy can be improved, and continuous evolution of the model can be realized.

The invention discloses a hierarchical optimization multi-instance learning method for digital pathological section brain tumor classification. The hierarchical optimization multi-instance learning method comprises the following steps: extracting and aggregating multi-instance features through alternate training of a feature encoder and an aggregator; a region of interest is automatically searched in a low-magnification image, and then feature extraction and classification are performed on a high-magnification region of interest. According to the method, the region-of-interest is detected by using low magnification, and then the tumor category is comprehensively judged in multiple magnification near the region-of-interest in stages. More importantly, in a model training link, a feature extractor is trained by utilizing a pseudo tag of patch in a region of interest, so that features are better extracted for a specific task and a data set. In order to reduce the noise of the false label, the patent provides a label correction mechanism to ensure the purity of the false label. In general, the HOMIL combines low-magnification tissue structure characteristics and high-magnification cell characteristics, comprehensively predicts brain tumors, and greatly reduces the model reasoning time.

A computer-implemented method for processing digital pathology images, the method including receiving a plurality of digital pathology images of at least one pathology specimen, the pathology specimen being associated with a patient. The method may further include determining receiving metadata corresponding to the plurality of digital pathology images, the metadata comprising data regarding previous medical treatment of the patient. Next, the method may include providing the medical images and metadata as input to a machine learning system, the machine learning system having been trained by receiving as input historical treatment information and digital images labeled with a predicted treatment regimen. Lastly, the method may include outputting, by the machine learning system, a treatment effectiveness assessment.

The invention relates to the technical field of image processing, in particular to a stomach cancer tissue typing auxiliary recognition method based on digital pathological sections. According to the method, morphological feature recognition is carried out on edge information in a grayscale image of a slice, and normal cell edges and abnormal cell edges are screened out according to the size of morphological feature indexes and the morphology of a cell edge curve. A first abnormal area and a second abnormal area are screened out according to the proximity relation, then enhancement coefficients of the two abnormal areas are calculated and enhanced, and a gastric cancer tissue typing recognition result is obtained according to the enhanced stomach pathology image. According to the invention, the object of the enhancement process is only limited to the abnormal region, and different degrees of enhancement are realized for different types of abnormal regions, so that the calculation amount of the enhancement process is reduced, the enhancement process has pertinence, excessive enhancement cannot be caused, and a clear slice image is obtained for tissue typing identification; and the tissue typing recognition efficiency is improved.

The invention relates to the field of digital pathology, and provides a digital slice quality control method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a highest magnification tile of a digital slice to be subjected to quality control; based on a trained pathological defect segmentation model, carrying out pathological defect identification and segmentation on the highest-magnification tile to obtain a highest-magnification mask graph; performing pixel-level statistics on the highest-magnification mask image to obtain a single-tile quality control result, and summarizing the single-tile quality control result to obtain a global quality control result of the digital slice; and based on the highest multiplying power mask graph, reconstructing a pyramid mask graph containing multiple multiplying power hierarchies by adopting a plurality of parallel processes, and performing rechecking based on the global quality control result and the pyramid mask graph. According to the digital slice quality control method and device, the electronic equipment and the storage medium provided by the invention, the efficiency bottleneck problem of the quality control process is effectively solved through the technical innovation of reconstructing the pyramid mask graph by the parallel process.

The invention discloses a pathological image full-automatic segmentation and classification method and system based on deep learning, and the method comprises the steps: selecting a to-be-processed tissue slice image, extracting the feature information of a cell nucleus in the to-be-processed tissue slice image, and carrying out the initialization processing; the unified feature decoder is introduced to process the image, and different feature information is integrated; carrying out instance segmentation on the cell nucleus by adopting a convolutional neural network, and optimizing a feature extraction process in combination with a self-attention mechanism and a residual network; meanwhile, a classification module is used for carrying out category prediction on cell nucleuses, and tissue region guide information is fused; and carrying out comprehensive optimization on the segmentation result and the classification result through multi-task joint training until a preset stop condition is met, and obtaining a high-quality cell nucleus segmentation and classification result. The method can automatically and efficiently perform cell nucleus segmentation and classification in the digital pathological image, has high accuracy and stability, is suitable for various complicated tissue slice analysis tasks, and does not need manual intervention.

The present disclosure relates to techniques for transforming digital pathology images obtained by different slide scanners into a common format for image analysis. Particularly, aspects of the present disclosure are directed to obtaining a source image of a biological specimen, the source image is generated from a first type of scanner, inputting into a generator model a randomly generated noise vector and a latent feature vector from the source image as input data, generating, by the generator model, a new image based on the input data, inputting into a discriminator model the new image, generating, by the discriminator model, a probability for the new image being authentic or fake, determining whether the new image is authentic or fake based on the generated probability, and outputting the new image when the image is authentic.