Deep Learning Models Delineates Multiple Nuclear Phenotypes in H&E Stained Histology Sections
This work addresses nuclear segmentation for histopathology analysis, which is incremental as it builds on existing deep learning methods to improve handling of specific challenges like overlapping nuclei and diverse phenotypes.
The authors tackled the complex problem of nuclear segmentation in H&E stained histology sections, which is complicated by variations in nuclear geometry, type, and phenotypes, and achieved a solution by fusing very deep convolutional networks to handle multiple nuclear phenotypes and overlapping nuclei, validated on breast and brain histology datasets.
Nuclear segmentation is an important step for profiling aberrant regions of histology sections. However, segmentation is a complex problem as a result of variations in nuclear geometry (e.g., size, shape), nuclear type (e.g., epithelial, fibroblast), and nuclear phenotypes (e.g., vesicular, aneuploidy). The problem is further complicated as a result of variations in sample preparation. It is shown and validated that fusion of very deep convolutional networks overcomes (i) complexities associated with multiple nuclear phenotypes, and (ii) separation of overlapping nuclei. The fusion relies on integrating of networks that learn region- and boundary-based representations. The system has been validated on a diverse set of nuclear phenotypes that correspond to the breast and brain histology sections.