Mitosis Detection Under Limited Annotation: A Joint Learning Approach

TL;DR

This paper introduces a joint learning framework that improves mitosis detection in breast cancer histopathology images using limited annotations by combining class label and spatial distribution information, achieving high accuracy with less data.

Contribution

The proposed deep classification framework effectively leverages class labels and spatial relationships to enhance mitosis detection with limited training data, outperforming existing methods.

Findings

Significant improvement in detection accuracy with small training datasets

Achieves comparable or superior performance to state-of-the-art methods

Effective use of class label and spatial distribution information

Abstract

Mitotic counting is a vital prognostic marker of tumor proliferation in breast cancer. Deep learning-based mitotic detection is on par with pathologists, but it requires large labeled data for training. We propose a deep classification framework for enhancing mitosis detection by leveraging class label information, via softmax loss, and spatial distribution information among samples, via distance metric learning. We also investigate strategies towards steadily providing informative samples to boost the learning. The efficacy of the proposed framework is established through evaluation on ICPR 2012 and AMIDA 2013 mitotic data. Our framework significantly improves the detection with small training data and achieves on par or superior performance compared to state-of-the-art methods for using the entire training data.