Mixed-Supervised Dual-Network for Medical Image Segmentation
This work addresses the high cost of annotation in medical imaging by enabling more efficient training with mixed supervision, though it is incremental as it builds on existing mixed-supervised and multi-task learning frameworks.
The paper tackles the challenge of requiring large, densely annotated datasets for medical image segmentation by proposing a mixed-supervised dual-network (MSDN) that uses both dense segmentations and weak bounding box labels, achieving improved performance over baselines on two datasets.
Deep learning based medical image segmentation models usually require large datasets with high-quality dense segmentations to train, which are very time-consuming and expensive to prepare. One way to tackle this challenge is by using the mixed-supervised learning framework, in which only a part of data is densely annotated with segmentation label and the rest is weakly labeled with bounding boxes. The model is trained jointly in a multi-task learning setting. In this paper, we propose Mixed-Supervised Dual-Network (MSDN), a novel architecture which consists of two separate networks for the detection and segmentation tasks respectively, and a series of connection modules between the layers of the two networks. These connection modules are used to transfer useful information from the auxiliary detection task to help the segmentation task. We propose to use a recent technique called "Squeeze and Excitation" in the connection module to boost the transfer. We conduct experiments on two medical image segmentation datasets. The proposed MSDN model outperforms multiple baselines.