An efficient context-aware approach for whole-slide image classification

• DOI: 10.1016/j.isci.2023.108175
• Publication Date: 2023-10-12T06:25:25Z
• Authors: Hongru Shen; Jianghua Wu; Xilin Shen; Jiani Hu; Jilei Liu; Qiang Zhang; Yan Sun; Kexin Chen; Xiangchun Li
• Keywords: Oncology; Science; Q; 0202 electrical engineering, electronic engineering, information engineering; pathology; 02 engineering and technology; Computer science; Article; 3. Good health

AbstractComputational pathology for gigapixel whole slide images (WSIs) at slide-level is helpful in disease diagnosis and remains challenging. We propose a context-aware approach termedWSIInspection via Transformer (WIT) for slide-level classification via holistically modeling dependencies among patches on the WSI. WIT automatically learns feature representation of WSI by aggregating features of all image patches. We evaluate classification performance of WIT along with state-of-the-art baseline method. WIT achieved an accuracy of 82.1% (95% CI, 80.7% - 83.3%) in the detection of 32 cancer types on the TCGA dataset, 0.918 (0.910 - 0.925) in diagnosis of cancer on the CPTAC dataset and 0.882 (0.87 - 0.890) in the diagnosis of prostate cancer from needle biopsy slide, outperforming the baseline by 31.6%, 5.4% and 9.3%, respectively. WIT can pinpoint the WSI regions that are most influential for its decision. WIT represents a new paradigm for computational pathology, facilitating the development of effective tools for digital pathology.