Search papers, labs, and topics across Lattice.
This paper introduces LUTSeg, a novel longitudinal dataset for ulcer tissue segmentation, featuring 141 images from 39 patients with annotations across five tissue categories by multiple expert clinicians. The dataset addresses the critical need for high-quality, multi-tissue wound datasets, particularly for underrepresented conditions like leprosy, and includes a gold-standard subset for assessing inter-rater agreement. The authors also present TiSage, a semi-supervised segmentation framework that leverages multi-scale semantic priors from a frozen medical vision-language model, achieving superior performance in low-label scenarios compared to existing methods.
A groundbreaking dataset and framework that significantly enhance ulcer tissue segmentation accuracy, even with limited labeled data.
Quantifying wound tissue composition is essential for monitoring chronic ulcer progression and guiding treatment decisions. However, pixel-level annotations are costly, and multi-tissue wound datasets remain scarce, particularly for neglected diseases such as leprosy. We introduce LUTSeg, a longitudinal chronic ulcer dataset comprising 141 images from 39 patients with wound masks and five tissue categories annotated by five expert clinicians, including a multi-expert gold-standard subset for inter-rater agreement analysis. To establish an initial benchmark for LUTSeg, we further propose TiSage, a semi-supervised tissue segmentation framework that integrates multi-scale semantic priors from a frozen medical vision-language model within a teacher-student architecture. We evaluate TiSage on LUTSeg and DFUTissue, showing improvements over supervised and semi-supervised baselines in most low-label settings. Code&data: https://github.com/carlosh93/TiSage
