Apparatuses and methods for digital pathology
Inventors
Natan, Michael J. • Bern, Marshall • Carlson, Eric
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11908130-B2
Publication Date
2024-02-20
Expiration Date
Abstract
Digital pathology is a promising alternative to manual slide analysis, but improvements in imaging and analysis methods are needed to provide an analysis data set of images that can easily be handled, stored, and importantly, delivered from one data location to another. Methods and software are described herein to improve image collection and analysis.
Core Innovation
The invention addresses a digital pathology workflow for managing and generating image data from a set of stained slides that comprises a tissue sample. It uses whole-slide images with multiplex staining and multiple imaging channels, where each imaging channel is associated with a corresponding biomarker or plurality of biomarkers.
The workflow selects a plurality of sub-regions from one of the set of stained slides and identifies, for each imaging channel, variations of contrast thresholds, variations of thresholds of marker positivity, or variations of both. These threshold variations are combined so that, for each sub-region and each imaging-channel threshold combination, the invention generates a plurality of masks segmented to identify cells.
The invention ranks the plurality of masks based on an ability of each mask to accurately identify cells that are positive for the corresponding biomarker or plurality of biomarkers of each imaging channel. It then selects a set of final mask parameters from the ranked masks and generates a set of slide images for all slides of the set of stained slides.
Claims Coverage
The partial content provides three independent claims: two method claims and one system claim. Across these independent claims, the inventive features focus on selecting sub-regions, identifying per-imaging-channel variations of contrast and marker-positivity thresholds tied to biomarkers, generating and ranking segmented cell masks, and selecting final mask parameters to generate slide images for all stained slides, with the system claim implemented by processors and memory.
Selecting sub-regions from stained slides
Selecting a plurality of sub-regions from one of the set of stained slides.
Channel-wise biomarker-associated threshold variations
Identifying, for each imaging channel of a first plurality of imaging channels, variations of contrast thresholds, variations of thresholds of marker positivity, or variations of both, wherein each imaging channel is associated with a corresponding biomarker or plurality of biomarkers.
Generating segmented cell masks for threshold combinations
Generating a plurality of masks for each of the plurality of sub-regions corresponding to each combination of the variations of contrast thresholds and variations of thresholds of marker positivity for each imaging channel, wherein each mask is segmented to identify cells.
Ranking masks by biomarker-positive cell identification accuracy
Ranking the plurality of masks based on an ability of each mask to accurately identify cells that are positive for the corresponding biomarker or plurality of biomarkers of each imaging channel.
Selecting final mask parameters and generating slide images
Selecting a set of final mask parameters from the plurality of masks based on the rankings and generating a set of slide images for all slides of the set of stained slides using the set of final mask parameters.
Processor-implemented system for generating image data
A system for generating image data for a set of stained slides comprising one or more processors and memory configured to store computer-program instructions that, when executed, perform a computer-implemented method comprising selecting a plurality of sub-regions, identifying channel-specific threshold variations associated with biomarkers, generating masks segmented to identify cells, ranking the masks, selecting final mask parameters, and generating slide images for all slides using the final mask parameters.
Across the independent claims, the core coverage is the generation of multiple segmented cell-identification masks from selected sub-regions using biomarker-associated variations of contrast and marker-positivity thresholds per imaging channel, followed by ranking masks for accurate identification of biomarker-positive cells and selecting final mask parameters to generate slide images for all slides.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?