A Data-Efficient Deep Learning Framework for Segmentation and Classification of Histopathology Images

TL;DR

This paper presents a data-efficient deep learning framework for segmenting and classifying inflammatory cells in histopathology images, enhancing accuracy and offering a promising tool for autoimmune disease research.

Contribution

The study introduces a novel deep learning approach with improved classification and segmentation performance, including a new autoencoder architecture for better segmentation accuracy.

Findings

Classification performance improved by 26%

Segmentation performance improved by 5%

Additional 3% segmentation improvement with autoencoder

Abstract

The current study of cell architecture of inflammation in histopathology images commonly performed for diagnosis and research purposes excludes a lot of information available on the biopsy slide. In autoimmune diseases, major outstanding research questions remain regarding which cell types participate in inflammation at the tissue level, and how they interact with each other. While these questions can be partially answered using traditional methods, artificial intelligence approaches for segmentation and classification provide a much more efficient method to understand the architecture of inflammation in autoimmune disease, holding great promise for novel insights. In this paper, we empirically develop deep learning approaches that use dermatomyositis biopsies of human tissue to detect and identify inflammatory cells. Our approach improves classification performance by 26% and segmentation performance by 5%. We also propose a novel post-processing autoencoder architecture that improves segmentation performance by an additional 3%.