DARCNN: Domain Adaptive Region-based Convolutional Neural Network for Unsupervised Instance Segmentation in Biomedical Images

TL;DR

This paper introduces DARCNN, a novel domain adaptive neural network that enables unsupervised instance segmentation in biomedical images by transferring knowledge from large labeled datasets like COCO, overcoming domain shifts.

Contribution

The paper presents DARCNN, a new model with domain separation, self-supervised consistency, and pseudo-labeling to adapt from natural images to biomedical data for segmentation.

Findings

DARCNN achieves effective unsupervised segmentation across various biomedical datasets.

The model successfully transfers knowledge from COCO to biomedical images.

Domain adaptation techniques significantly improve segmentation performance.

Abstract

In the biomedical domain, there is an abundance of dense, complex data where objects of interest may be challenging to detect or constrained by limits of human knowledge. Labelled domain specific datasets for supervised tasks are often expensive to obtain, and furthermore discovery of novel distinct objects may be desirable for unbiased scientific discovery. Therefore, we propose leveraging the wealth of annotations in benchmark computer vision datasets to conduct unsupervised instance segmentation for diverse biomedical datasets. The key obstacle is thus overcoming the large domain shift from common to biomedical images. We propose a Domain Adaptive Region-based Convolutional Neural Network (DARCNN), that adapts knowledge of object definition from COCO, a large labelled vision dataset, to multiple biomedical datasets. We introduce a domain separation module, a self-supervised representation consistency loss, and an augmented pseudo-labelling stage within DARCNN to effectively perform domain adaptation across such large domain shifts. We showcase DARCNN's performance for unsupervised instance segmentation on numerous biomedical datasets.