Deep Multi-Magnification Networks for Multi-Class Breast Cancer Image Segmentation
This work addresses the problem of automating pathologic analysis for breast cancer assessment, which is currently manual and time-consuming for pathologists, representing a domain-specific incremental improvement.
The paper tackled automated multi-class tissue segmentation in breast cancer histology slides by introducing a Deep Multi-Magnification Network trained with partial annotation, achieving the highest mean intersection-over-union compared to other architectures.
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.