Keywords: Prostate, cancer, domain agnostic, histopathology, deep learning, active learning
TL;DR: Prostate Cancer Grading of Core Needle Biopsies
Abstract: Gleason grading is a risk stratification procedure for prostate cancer that is subjective and based on the reporting pathologist's experience and skill. Deep Learning (DL) algorithms have showed potential in improving Gleason grading objectivity and efficiency. On Whole Slide Images (WSI) from a source other than training data, however, DL networks show domain shift and poor performance. Using a novel training process that learns domain agnostic features, we propose a DL approach for segmenting and grading epithelial tissue. When utilised as an aid for core needle biopsy (CNB) evaluation, our DL approach has the potential to increase grading consistency and accuracy, leading in better patient outcomes.
Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: recently published or submitted journal contributions
Primary Subject Area: Validation Study
Secondary Subject Area: Application: Histopathology
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.