Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a bi-level collaborative learning framework designed to enhance few-shot scribble-supervised medical image segmentation by addressing the challenges of sparse supervision and limited annotated samples. The framework employs an upper-level superpixel model to generate region-structural priors, which inform a lower-level segmentation model, while also utilizing pseudo-label propagation and spatial-prior-guided filtering to improve segmentation accuracy. Experimental results demonstrate that this approach significantly surpasses existing state-of-the-art methods on the ACDC and Prostate datasets, showcasing its effectiveness in real clinical scenarios.
Bidirectional collaboration between superpixel and segmentation models leads to a dramatic improvement in few-shot scribble-supervised segmentation accuracy.
Scribble annotations offer an efficient alternative to costly pixel-wise labeling for medical image segmentation, yet in real clinical scenarios, scribble-annotated samples are often still limited, imposing the dual challenges of sparse supervision and annotated sample scarcity. These compounded constraints severely deprive models of the structural evidence needed for complete region recovery and precise boundary delineation. To break this bottleneck, we propose a bi-level collaborative learning framework for few-shot scribble-supervised medical image segmentation. Specifically, an upper-level learnable superpixel model is introduced to provide region-structural priors for lower-level segmentation, while superpixel-based region-wise pseudo-label propagation and a spatial-prior-guided filtering strategy are performed to generate reliable dense pseudo-labels for segmentation learning. Meanwhile, the anatomical semantics learned by the lower-level segmentation model under the guidance of the current superpixels are fed back to the upper level, further driving it to learn region-structural representations better aligned with the segmentation task. Through bidirectional interaction and collaborative learning between the upper and lower levels, the proposed framework significantly outperforms existing state-of-the-art scribble-supervised methods on the ACDC and Prostate datasets under the few-shot scribble-supervised setting.