Mixed Supervision of Histopathology Improves Prostate Cancer Classification from MRI

TL;DR

This study introduces a deep learning approach that combines diverse histopathological supervision signals, including weakly labeled data, to improve non-invasive prostate cancer detection from MRI, surpassing existing clinical standards.

Contribution

The paper presents a novel mixed supervision method using distribution regression to incorporate weakly labeled histopathology data, enhancing prostate cancer classification from MRI.

Findings

Deep networks with mixed supervision outperform PI-RADS standards.

Inclusion of weak supervision from systematic biopsies improves accuracy.

Model evaluated on 973 MRI exams with significant performance gains.

Abstract

Non-invasive prostate cancer detection from MRI has the potential to revolutionize patient care by providing early detection of clinically-significant disease (ISUP grade group >= 2), but has thus far shown limited positive predictive value. To address this, we present an MRI-based deep learning method for predicting clinically significant prostate cancer applicable to a patient population with subsequent ground truth biopsy results ranging from benign pathology to ISUP grade group~5. Specifically, we demonstrate that mixed supervision via diverse histopathological ground truth improves classification performance despite the cost of reduced concordance with image-based segmentation. That is, where prior approaches have utilized pathology results as ground truth derived from targeted biopsies and whole-mount prostatectomy to strongly supervise the localization of clinically significant cancer, our approach also utilizes weak supervision signals extracted from nontargeted systematic biopsies with regional localization to improve overall performance. Our key innovation is performing regression by distribution rather than simply by value, enabling use of additional pathology findings traditionally ignored by deep learning strategies. We evaluated our model on a dataset of 973 (testing n=160) multi-parametric prostate MRI exams collected at UCSF from 2015-2018 followed by MRI/ultrasound fusion (targeted) biopsy and systematic (nontargeted) biopsy of the prostate gland, demonstrating that deep networks trained with mixed supervision of histopathology can significantly exceed the performance of the Prostate Imaging-Reporting and Data System (PI-RADS) clinical standard for prostate MRI interpretation.