Deeply supervised UNet for semantic segmentation to assist dermatopathological assessment of Basal Cell Carcinoma (BCC)

TL;DR

This paper presents a deep learning-based semantic segmentation method using a deeply supervised UNet architecture to accurately identify Basal Cell Carcinoma regions in Whole Slide Images, aiding dermatopathological diagnosis.

Contribution

It introduces a novel application of deeply supervised UNet models with multiple encoders and training strategies for BCC detection in WSIs, validated on a large clinical dataset.

Findings

Achieved over 96% accuracy, sensitivity, and specificity.

Deep supervision and encoder choices influence model interpretability.

Validated on 650 WSIs with expert annotations.

Abstract

Accurate and fast assessment of resection margins is an essential part of a dermatopathologist's clinical routine. In this work, we successfully develop a deep learning method to assist the pathologists by marking critical regions that have a high probability of exhibiting pathological features in Whole Slide Images (WSI). We focus on detecting Basal Cell Carcinoma (BCC) through semantic segmentation using several models based on the UNet architecture. The study includes 650 WSI with 3443 tissue sections in total. Two clinical dermatopathologists annotated the data, marking tumor tissues' exact location on 100 WSI. The rest of the data, with ground-truth section-wise labels, is used to further validate and test the models. We analyze two different encoders for the first part of the UNet network and two additional training strategies: a) deep supervision, b) linear combination of decoder outputs, and obtain some interpretations about what the network's decoder does in each case. The best model achieves over 96%, accuracy, sensitivity, and specificity on the test set.