Multi-task learning for tissue segmentation and tumor detection in colorectal cancer histology slides
This work addresses the challenge of faster diagnostic pathology workflows for colorectal cancer, though it is incremental as it builds on existing U-Net and augmentation methods.
The authors tackled the problem of automating tissue segmentation and tumor detection in colorectal cancer histology slides, achieving a multi-task Dice score of up to 0.8655 for segmentation and an AUROC of up to 0.9750 for detection on a challenge validation set.
Automating tissue segmentation and tumor detection in histopathology images of colorectal cancer (CRC) is an enabler for faster diagnostic pathology workflows. At the same time it is a challenging task due to low availability of public annotated datasets and high variability of image appearance. The semi-supervised learning for CRC detection (SemiCOL) challenge 2023 provides partially annotated data to encourage the development of automated solutions for tissue segmentation and tumor detection. We propose a U-Net based multi-task model combined with channel-wise and image-statistics-based color augmentations, as well as test-time augmentation, as a candidate solution to the SemiCOL challenge. Our approach achieved a multi-task Dice score of .8655 (Arm 1) and .8515 (Arm 2) for tissue segmentation and AUROC of .9725 (Arm 1) and 0.9750 (Arm 2) for tumor detection on the challenge validation set. The source code for our approach is made publicly available at https://github.com/lely475/CTPLab_SemiCOL2023.