Deep Learning with Uncertainty Quantification for Predicting the Segmentation Dice Coefficient of Prostate Cancer Biopsy Images

TL;DR

This paper introduces a method combining deep learning with uncertainty quantification to predict segmentation performance in prostate cancer biopsy images, enhancing trust and evaluation in clinical settings.

Contribution

The study demonstrates that uncertainty estimates can effectively predict Dice scores, providing a novel comprehensive performance metric for prostate cancer image segmentation.

Findings

Uncertainty estimates significantly correlate with model performance.

Linear models can predict Dice scores from uncertainty measures with low error.

Uncertainty-based evaluation improves trust in deep learning models for clinical use.

Abstract

Deep learning models (DLMs) can achieve state-of-the-art performance in histopathology image segmentation and classification, but have limited deployment potential in real-world clinical settings. Uncertainty estimates of DLMs can increase trust by identifying predictions and images that need further review. Dice scores and coefficients (Dice) are benchmarks for evaluation of image segmentation performance, but are usually not evaluated with DLM uncertainty quantification. This study reports DLMs trained with uncertainty estimations, using randomly initialized weights and Monte Carlo dropout, to segment tumors from microscopic Hematoxylin and Eosin dye stained prostate core biopsy histology RGB images. Image-level maps showed significant correlation (Spearman's rank, p < 0.05) between overall and specific prostate tissue image sub-region uncertainties with model performance estimations by Dice. This study reports that linear models, which can predict Dice segmentation scores from multiple clinical sub-region-based uncertainties of prostate cancer, can serve as a more comprehensive performance evaluation metric without loss in predictive capability of DLMs, with a low root mean square error.