University of Minnesota

Stephen C Schmechel

Gregory John Metzger

Joseph S Koopmeiners

Jonathan Henriksen

Ethan Yize Leng

Stephen Dankbar

Chaitanya Kalavagunta

Christopher A Warlick

Automated, machine learning-based systems are described for the analysis and annotation (i.e., detection or delineation) of prostate cancer (PCa) on histologically-stained pathology slides of prostatectomy specimens. A technical framework is described for automating the annotation of predicted PCa that is based on, for example, automated spatial alignment and colorimetric analysis of both H&E and IHC whole-slide images (WSIs). The WSIs may, as one example, be stained with a particular triple-antibody cocktail against high-molecular weight cytokeratin (HMWCK), p63, and &#x3b1;-methylacyl CoA racemase (AMACR).

Automated detection and annotation of prostate cancer on histopathology slides

A user-independent, quantitative, multiparametric MRI model is developed and validated on co-registered correlative histopathology, yielding improved performance for cancer detection over single parameter estimators. A computing device may be configured to receive a first parametric map that maps imaged tissue of a patient using values of a first parameter, and a second parametric map that maps the imaged tissue using values of a second parameter, wherein the parametric maps are generated from medical imaging data for the imaged tissue. The computing device may be further configured to apply a multiparametric model to the maps to generate at least one Composite Biomarker Score for the tissue, the model being a function of the first parameter and the second parameter. The function may be determined based on co-registered histopathology data. The computing device may be further configured to generate an indication of whether the tissue includes predicted cancer, and output the indication.

Medical imaging device rendering predictive prostate cancer visualizations using quantitative multiparametric MRI models

A computerized method for immunohistochemistry analysis of tissue utilizes digital images of multiple adjacent tissue sections aligned within a computerized software and processed with an algorithm to quantify a two-dimensional IHC signature score for each respective slide image. In various embodiments, the IHC score is performed over several adjacent sections and further processed to produce a three-dimensional IHC quantification referred to as an IHC signature map.

Computerized methods for tissue analysis

Growing community of inventors

Seattle, WA, United States of America

Stephen C Schmechel