Constrained Deep Weak Supervision for Histopathology Image Segmentation

TL;DR

This paper introduces a novel weakly-supervised deep learning method for histopathology image segmentation, leveraging multiple instance learning, deep supervision, and constraints to improve accuracy and efficiency.

Contribution

It presents an end-to-end fully convolutional network with deep weak supervision and constraint integration, advancing weakly-supervised segmentation in medical imaging.

Findings

Achieves state-of-the-art results on histopathology datasets

Efficient training with easy implementation

Applicable to various medical imaging modalities

Abstract

In this paper, we develop a new weakly-supervised learning algorithm to learn to segment cancerous regions in histopathology images. Our work is under a multiple instance learning framework (MIL) with a new formulation, deep weak supervision (DWS); we also propose an effective way to introduce constraints to our neural networks to assist the learning process. The contributions of our algorithm are threefold: (1) We build an end-to-end learning system that segments cancerous regions with fully convolutional networks (FCN) in which image-to-image weakly-supervised learning is performed. (2) We develop a deep week supervision formulation to exploit multi-scale learning under weak supervision within fully convolutional networks. (3) Constraints about positive instances are introduced in our approach to effectively explore additional weakly-supervised information that is easy to obtain and enjoys a significant boost to the learning process. The proposed algorithm, abbreviated as DWS-MIL, is easy to implement and can be trained efficiently. Our system demonstrates state-of-the-art results on large-scale histopathology image datasets and can be applied to various applications in medical imaging beyond histopathology images such as MRI, CT, and ultrasound images.