Deep Multi-Magnification Networks for multi-class breast cancer image segmentation. (March 2021)

• Record Type: Journal Article
• Authors: Ho, David Joon; Yarlagadda, Dig V.K.; D'Alfonso, Timothy M.; Hanna, Matthew G.; Grabenstetter, Anne; Ntiamoah, Peter; Brogi, Edi; Tan, Lee K.; Fuchs, Thomas J.
• Is Part Of: Computerized medical imaging and graphics. Volume 88(2021)
• Publication Date: 2021-03
• Subjects: Breast cancer -- Computational pathology -- Multi-class image segmentation -- Deep Multi-Magnification Network -- Partial annotation; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2021.101866
• Languages: English
• ISSNs: 0895-6111

Abstract

Highlights: Multi-Magnification Network segments multiple tissue subtypes on pathology images. Features from both high magnifications and low magnifications are fully utilized. Partial annotation approach is proposed to reduce labeling burdens for pathologists. Sharp boundaries delineate tissue subtypes and outperform the state-of-the-art. Abstract: Pathologic analysis of surgical excision specimens for breast carcinoma is important to evaluate the completeness of surgical excision and has implications for future treatment. This analysis is performed manually by pathologists reviewing histologic slides prepared from formalin-fixed tissue. In this paper, we present Deep Multi-Magnification Network trained by partial annotation for automated multi-class tissue segmentation by a set of patches from multiple magnifications in digitized whole slide images. Our proposed architecture with multi-encoder, multi-decoder, and multi-concatenation outperforms other single and multi-magnification-based architectures by achieving the highest mean intersection-over-union, and can be used to facilitate pathologists' assessments of breast cancer.