An efficient context-aware approach for whole-slide image classification
Hongru Shen,
Jianghua Wu,
Xilin Shen,
Jiani Hu,
Jilei Liu,
Qiang Zhang,
Yan Sun,
Kexin Chen,
Xiangchun Li
Affiliations
Hongru Shen
Tianjin Cancer Institute, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
Jianghua Wu
Department of Pathology, Peking University Cancer Hospital & Institute, Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Beijing, China
Xilin Shen
Tianjin Cancer Institute, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
Jiani Hu
Tianjin Cancer Institute, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
Jilei Liu
Tianjin Cancer Institute, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
Qiang Zhang
Department of Maxillofacial and Otorhinolaryngology Oncology, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
Yan Sun
Department of Pathology, Tianjin’s Clinical Research Center for Cancer, Key Laboratory of Cancer Immunology and Biotherapy, National Clinical Research Center for Cancer, Tianjin Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
Kexin Chen
Department of Epidemiology and Biostatistics, Tianjin’s Clinical Research Center for Cancer, Key Laboratory of Molecular Cancer Epidemiology of Tianjin, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China; Corresponding author
Xiangchun Li
Tianjin Cancer Institute, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China; Corresponding author
Summary: Computational pathology for gigapixel whole-slide images (WSIs) at slide level is helpful in disease diagnosis and remains challenging. We propose a context-aware approach termed WSI inspection via transformer (WIT) for slide-level classification via holistically modeling dependencies among patches on WSI. WIT automatically learns feature representation of WSI by aggregating features of all image patches. We evaluate classification performance of WIT and 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 digital pathology tools.
