Deep Multitask Learning for Automated Tissue Segmentation and Cell Detection
Mohamed Mounib Benimam, Astri Frafjord, Alexandre Corthay, Thibault Lagache, Jean-Christophe Olivo-Marin, Vannary Meas‐Yedid · 2025
We propose a unified multitasking deep learning method to identify and segment structural regions and detect immune cells of non-small cell lung cancer tissue. This approach combines multitask learning and deep supervision to significantly reduce training time compared with single-task models, while achieving competitive performance with 50% fewer parameters. We balance tasks using homoscedastic uncertainty and address class imbalance through a combination of focal loss and class weight adjustment. Tested on multiplexed WSI, our method overcomes challenges related to variability and limited annotations, while extracting robust spatial information from the tumor microenvironment (TME). This data can be leveraged to quantify tumor-immune dynamics and intercellular communication, thereby providing objective insights into the TME's structural and functional complexity.