Assessing Multimodal Chronic Wound Embeddings with Expert Triplet Agreement
This addresses the challenge of reliable case similarity for clinicians in a rare, heterogeneous disease, though it is incremental as it builds on existing foundation models and multimodal techniques.
The paper tackled the problem of finding clinically similar cases for recessive dystrophic epidermolysis bullosa (RDEB) using images and text, where off-the-shelf foundation models fail, by proposing TriDerm, a multimodal framework that integrates wound imagery, masks, and expert reports to learn interpretable representations; it achieved 73.5% agreement with experts, outperforming the best single-modality model by over 5.6 percentage points.
Recessive dystrophic epidermolysis bullosa (RDEB) is a rare genetic skin disorder for which clinicians greatly benefit from finding similar cases using images and clinical text. However, off-the-shelf foundation models do not reliably capture clinically meaningful features for this heterogeneous, long-tail disease, and structured measurement of agreement with experts is challenging. To address these gaps, we propose evaluating embedding spaces with expert ordinal comparisons (triplet judgments), which are fast to collect and encode implicit clinical similarity knowledge. We further introduce TriDerm, a multimodal framework that learns interpretable wound representations from small cohorts by integrating wound imagery, boundary masks, and expert reports. On the vision side, TriDerm adapts visual foundation models to RDEB using wound-level attention pooling and non-contrastive representation learning. For text, we prompt large language models with comparison queries and recover medically meaningful representations via soft ordinal embeddings (SOE). We show that visual and textual modalities capture complementary aspects of wound phenotype, and that fusing both modalities yields 73.5% agreement with experts, outperforming the best off-the-shelf single-modality foundation model by over 5.6 percentage points. We make the expert annotation tool, model code and representative dataset samples publicly available.