US 11,636,288 B2 · Platform, device and process for annotation and classification of tissue specimens using convolutional neural network

Abstract

Embodiments described herein provide a platform, device and process for digital pathology that enable multi-level annotation and visualization of histopathologic slides using a modular arrangement of deep convolutional neural networks (CNNs). The CNNs can be trained using pathology images (e.g., in some cases increasing the base of data by breaking larger fields of view into smaller ones) to learn features consistent with certain pathologies. The platform can use the CNNs to visually annotate pathology slides at an interface tool of a display device. The platform can automate the process of selection, as well as provide an opportunity for the pathologist to see a depiction of predicted results. The platform can use the CNNs to identify regions of interest on pathology slides. The interface tool can enable a predicted region of interest (ROI) type to be visually presented on a surface map showing the basis of the prediction. If the ROI primarily lands in part of the hyperdimensional space not occupied by any training set, then the interface tool is capable of marking it as an ROI of unknown type.

Claims20

Dependent claims

A computer platform for digital pathology comprising:

memory having a stored data structure defining a hierarchy of convolutional neural networks that model a hyperdimensional space, the hierarchy of convolutional neural networks trained using pathology images;
one or more processors in communication with the memory having the stored data structure defining the hierarchy of convolutional neural networks;
and
one or more programs, wherein the one or more program are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions to:
determine a region of interest on a pathology slide and a predicted region of interest (ROI) type by classifying a plurality of pathology features abstracted from the pathology slide and identifying the region of interest on the pathology slide by a processor of the one or more processors using the hierarchy of convolutional neural networks defined by the data structure stored in the memory;
and
generate, at an interface tool for display on a display device, output indications of the region of interest on a visual representation of the pathology slide, a reduced dimensionality view of the pathology features for classifying the predicted region of interest type, and annotations of the predicted region of interest type on the visual representation of the pathology slide.

4 more elements

A computer product with non-transitory computer readable media storing program instructions to configure a processor to:

determine a region of interest on a pathology slide and a predicted region of interest (ROI) type by classifying a plurality of pathology features abstracted from the pathology slide by the processor using a hierarchy of convolutional neural networks that model a hyperdimensional space, the hierarchy of convolutional neural networks trained using pathology images, the hierarchy of convolutional neural networks stored on a memory accessible by the processor;
generate output indications of the region of interest on a visual representation of the pathology slide, a reduced dimensionality view of the pathology features for classifying the predicted region of interest type, and annotations of the predicted region of interest type on the visual representation of the pathology slide;
and
update an interface tool to display the output indications and the annotations on a display device.

1 more element

Dependencies are inferred from the claim text.

Platform, device and process for annotation and classification of tissue specimens using convolutional neural network

Life of this patent

Platform, device and process for annotation and classification of tissue specimens using convolutional neural network

Life of this patent

Abstract

Claims20