Deep Multiresolution Cellular Communities for Semantic Segmentation of Multi-Gigapixel Histology Images

Sajid Javed, Arif Mahmood, Naoufel Werghi, Nasir Rajpoot; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

Tissue phenotyping in cancer histology images is a fundamental step in computational pathology. Automatic tools for tissue phenotyping assist pathologists for digital profiling of the tumor microenvironment. Recently, deep learning and classical machine learning methods have been proposed for tissue phenotyping. However, these methods do not integrate the cellular community interaction features which present biological significance in tissue phenotyping context. In this paper, we propose to exploit deep multiresolution cellular communities for tissue phenotyping from multi-level cell graphs and show that such communities offer better performance compared to the deep learning and texture-based methods. We propose to use deep features extracted from two distinct layers of a deep neural network at the cell-level, in order to construct cellular graphs encoding cellular interactions at multiple scales. From these graphs, we extract cellular interaction-based features, which are then employed to construct patch-level graphs. Multiresolution communities are detected by considering the patch-level graphs as layers of multi-level graphs, and also by proposing novel objective function based on non-negative matrix factorization. We report results of our experiments on two datasets for colon cancer tissue phenotyping and demonstrate excellent performance of the proposed algorithm as compared to current state-of-the-art methods.