Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision

TL;DR

This paper introduces Box-Adapt, a weakly supervised domain adaptation method for medical image segmentation that leverages bounding box annotations in the target domain to reduce labeling costs and improve segmentation performance.

Contribution

It proposes a novel two-stage approach that combines source domain segmentation masks with target domain bounding boxes for effective domain adaptation.

Findings

Significant improvement over baseline UDA methods in liver segmentation.

Effective utilization of bounding box supervision reduces annotation effort.

Demonstrated success in a real medical imaging task.

Abstract

Deep learning has achieved remarkable success in medicalimage segmentation, but it usually requires a large numberof images labeled with fine-grained segmentation masks, andthe annotation of these masks can be very expensive andtime-consuming. Therefore, recent methods try to use un-supervised domain adaptation (UDA) methods to borrow in-formation from labeled data from other datasets (source do-mains) to a new dataset (target domain). However, due tothe absence of labels in the target domain, the performance ofUDA methods is much worse than that of the fully supervisedmethod. In this paper, we propose a weakly supervised do-main adaptation setting, in which we can partially label newdatasets with bounding boxes, which are easier and cheaperto obtain than segmentation masks. Accordingly, we proposea new weakly-supervised domain adaptation method calledBox-Adapt, which fully explores the fine-grained segmenta-tion mask in the source domain and the weak bounding boxin the target domain. Our Box-Adapt is a two-stage methodthat first performs joint training on the source and target do-mains, and then conducts self-training with the pseudo-labelsof the target domain. We demonstrate the effectiveness of ourmethod in the liver segmentation task. Weakly supervised do-main adaptation