2021/04/01 by Nima Hatami, Hatami, Nima, Mohsin Bilal +3
Computer Science · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Computer and information sciences #FOS: Electrical engineering #Image Retrieval and Classification Techniques #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2104.00669
openalex publication_date 2021/04/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The problem of recognizing various types of tissues present in multi-gigapixel histology images is an important fundamental pre-requisite for downstream analysis of the tumor microenvironment in a bottom-up analysis paradigm for computational pathology. In this paper, we propose a deep dictionary learning approach to solve the problem of tissue phenotyping in histology images. We propose deep Multi-Resolution Dictionary Learning (deepMRDL) in order to benefit from deep texture descriptors at multiple different spatial resolutions. We show the efficacy of the proposed approach through extensive experiments on four benchmark histology image datasets from different organs (colorectal cancer, breast cancer and breast lymphnodes) and tasks (namely, cancer grading, tissue phenotyping, tumor detection and tissue type classification). We also show that the proposed framework can employ most off-the-shelf CNNs models to generate effective deep texture descriptors.