10 results about "Whole slide image" patented technology

The present invention relates to an apparatus, system, and method including a hierarchical deep learning model for analyzing large-scale pathology images in the form of Whole Slide Images (WSI) using a hierarchical deep learning model. More specifically, the invention relates to an apparatus, system, and method including a hierarchical deep learning model that divides a large-scale pathology image, which is a pyramid-shaped whole slide image composed of multiple magnification layers of high-magnification pathology images and low-magnification pathology images, into patches, thereby enabling more accurate analysis by applying the high-magnification pathology images to a segmentation model and generating faster analysis results by applying the low-magnification pathology images to a regression model.

Various examples of the disclosure pertain to using whole-slide images that depict healthy tissue for a training process for at least one machine-learning algorithm for digital pathology. For instance, an autoencoder neural network can be trained based on the healthy tissue.

A classification method and system of whole slide images based on learnable feature merging and topology-awareness are disclosed. The classification method comprises: performing image block segmentation on a whole slide image to obtain a plurality of image blocks, and obtaining an initial feature sequence containing two-dimensional spatial coordinates and image block features; processing the initial feature sequence to obtain an assignment matrix for feature soft assignment, and weighting and aggregating the image block features based on the assignment matrix into a plurality of merged features to obtain a merged feature sequence; calculating a spatial distance matrix according to the two-dimensional spatial coordinates, and mapping the spatial distance matrix into a topology-aware spatial bias matrix using the assignment matrix; performing global attention calculation on the merged feature sequence by taking the topology-aware spatial bias matrix as a negative bias term, so that the attention interaction weight decays with the increase of the spatial distance, and predicting the classification result of the whole slide image. The classification method can reduce the computational overhead while maintaining the boundary information and spatial consistency.

An apparatus for interacting with one or more digital whole slide images (WSIs) acquired by an imaging device includes a display, a memory, and one or more hardware processors. The memory is configured to store computer-executable instructions. The one or more hardware processors are in communication with the display and the memory. The one or more hardware processors are configured to drive the display using the computer-executable instructions of the memory such that the one or more hardware processors are configured to generate a user interface. The user interface includes an image layer and one or more mask layers overlaying the image layer. The one or more mask layers have a predetermined opacity level. The one or more hardware processors are further configured to automatically adjust the predetermined opacity level as a function of a magnification level of the image layer.

Systems (600) and methods (S100) for adapting treatment plans to the characteristics of individual anatomical pathologies (e.g., tumors), and systems, methods, and devices for implementing an adaptive therapy workflow (220) that automatically updates (S103) treatment plans based on whole slide images (WSIs) of the target anatomical pathologies.

Systems, apparatuses, and methods are provided for generating patch-level predictions in whole slide images (WSIs) using classification models trained with attention and self-attention mechanisms. A WSI is divided into patches, and each patch is processed by a feature extraction model to obtain features. Attention-based aggregation assigns weights to patch features during training, enabling the classification model to generate patch-level predictions for disease-associated or non-disease-associated target classes during inference, including artifacts. A patch is classified as positive for a target class if its predicted probability exceeds a threshold, and negative otherwise. Training uses multiple instance learning and attention-derived data to optimize model performance. This approach supports granular and interpretable outputs for diagnostic and quality assurance applications.

The present application relates to the technical field of image detection, and discloses a cervical whole slide image detection method, a device, and a computer program product. The cervical whole slide image detection method comprises: acquiring a cervical cytology whole slide image to be detected; cropping said cervical cytology whole slide image to obtain an image block; then inputting the image block into a cell detector to obtain a preset cell image in the image block outputted by the cell detector; and performing feature extraction on the preset cell image by means of a feature extraction network in a slide classifier, and predicting an extracted feature by means of a multi-instance learning classifier in the slide classifier to obtain a cervical cytology whole slide image detection result. By executing the above operations, the accuracy of cervical whole slide image detection is improved.

The scheme provides a pathological whole section image storage method and data supply method for AI processing, comprising: acquiring at least one multi-layer pyramid structure pathological whole section image, and storing each pyramid level image of the pathological whole section image in a storage engine by dividing the image into multiple image blocks; and constructing a first-level positioning index, a second-level prediction index and a third-level semantic index for each image block in the storage engine. The scheme adopts a three-level index linkage data supply logic, filters redundant data layer by layer, extracts only the minimum effective data required by the AI task, and improves the accuracy and efficiency of data supply.

This invention discloses a multimodal cervical cancer immune subtype prediction method based on deep learning, including the following steps: (1) Data acquisition: acquiring pathological whole slide image data and transcriptome sequencing data of cervical cancer patients; (2) Data preprocessing: performing tissue segmentation, multi-scale block division and normalization processing on the whole slide images, and performing protein-coding gene screening and standardization processing on the transcriptome data; (3) Model construction: constructing an image feature extraction branch based on attention mechanism convolutional neural network, a gene feature extraction branch based on deep fully connected network, and a multimodal fusion module based on feature splicing or decision weighting; (4) Model training: using weighted cross-entropy loss function and cosine annealing strategy to train the model and optimize parameters to solve the problem of sample class imbalance; (5) Model prediction: this invention effectively overcomes the information bottleneck of single-modal data by synergistically fusing the spatial morphological features of pathological images and the molecular functional features of gene expression, and significantly improves the accuracy and robustness of cervical cancer C1 / C2 immune subtype prediction.

According to systems and techniques disclosed herein, a method for generating a navigable three-dimensional image of a tissue sample may include receiving a plurality of whole slide images (WSI) associated with the tissue sample. The method may further include providing the plurality of whole slide images to a machine-learning model. The machine-learning model may have been trained to identify one or more positional features within the plurality of whole slide images and output a plurality of relative positional relationships corresponding to each of the plurality of whole slide images. The method may further include generating the navigable three-dimensional image of the tissue sample based on the plurality of relative positional relationships. The method may further include generating an interactive display incorporating the navigable three-dimensional image. The method may further include providing, to a user interface, the interactive display.