SP${ }^3$ : Superpixel-propagated pseudo-label learning for weakly semi-supervised medical image segmentation

TL;DR

This paper introduces SP${ }^3$, a superpixel-propagated pseudo-label learning method that enhances weakly semi-supervised medical image segmentation by leveraging superpixel structure to improve pseudo-label quality and reduce annotation effort.

Contribution

The novel SP${ }^3$ method propagates scribble annotations to superpixels, refines pseudo-labels with dynamic thresholding, and incorporates superpixel-level uncertainty for stable learning, advancing weakly semi-supervised segmentation.

Findings

Achieves ~80% Dice score with only 3% annotation effort.

Outperforms eight weakly and semi-supervised methods.

State-of-the-art results on tumor and organ segmentation datasets.

Abstract

Deep learning-based medical image segmentation helps assist diagnosis and accelerate the treatment process while the model training usually requires large-scale dense annotation datasets. Weakly semi-supervised medical image segmentation is an essential application because it only requires a small amount of scribbles and a large number of unlabeled data to train the model, which greatly reduces the clinician's effort to fully annotate images. To handle the inadequate supervisory information challenge in weakly semi-supervised segmentation (WSSS), a SuperPixel-Propagated Pseudo-label (SP${}^3$) learning method is proposed, using the structural information contained in superpixel for supplemental information. Specifically, the annotation of scribbles is propagated to superpixels and thus obtains a dense annotation for supervised training. Since the quality of pseudo-labels is limited by the low-quality annotation, the beneficial superpixels selected by dynamic thresholding are used to refine pseudo-labels. Furthermore, aiming to alleviate the negative impact of noise in pseudo-label, superpixel-level uncertainty is incorporated to guide the pseudo-label supervision for stable learning. Our method achieves state-of-the-art performance on both tumor and organ segmentation datasets under the WSSS setting, using only 3\% of the annotation workload compared to fully supervised methods and attaining approximately 80\% Dice score. Additionally, our method outperforms eight weakly and semi-supervised methods under both weakly supervised and semi-supervised settings. Results of extensive experiments validate the effectiveness and annotation efficiency of our weakly semi-supervised segmentation, which can assist clinicians in achieving automated segmentation for organs or tumors quickly and ultimately benefit patients.