# Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment Source: [Semi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal Alignment]() Collection index: [llms.txt]() Data updated: 2026-08-05T05:00:05.796Z Authors: Yuchen Li, Ziru Wei, Zhen Zhao, Yi Liu, Luping Zhou Published: 2026-05-15T08:15:45.000Z ## Abstract Medical referring image segmentation (MRIS) predicts lesion masks from medical images and natural-language referring expressions, but acquiring paired pixel-level annotations and referring texts is costly. Semi-supervised learning (SSL) can alleviate this burden by exploiting unlabeled data, yet its effectiveness depends on preserving image--text alignment under strong perturbations. Existing SSL methods for referring segmentation rely on independent or simple multimodal perturbations (e.g., left--right flips), while stronger augmentations such as CutMix remain largely unexplored because they can disrupt cross-modal correspondence. We propose Semi-MedRef, a teacher--student SSL framework that explicitly preserves alignment between medical images and positional language through three complementary components: T-PatchMix, an alignment-preserving cross-modal augmentation that synchronizes patch mixing with positional-language and pseudo-mask updates; PosAug, a position-aware text augmentation that regularizes reliance on positional expressions; and Positional Affinity Contrastive Learning (PACL), which exploits coarse positional cues to construct region-aware supervision through anatomically weighted soft positives, encouraging anatomically grounded cross-modal representation learning. Experiments on QaTa-COV19 and MosMedData+ demonstrate that Semi-MedRef consistently outperforms state-of-the-art fully supervised and semi-supervised MRIS methods across all label regimes. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Medical Referring Image Segmentation on QaTa-COV19](): Medical Referring Image Segmentation; QaTa-COV19; Dice Score: 91.39. - [Medical Referring Image Segmentation on MosMedData+](): Medical Referring Image Segmentation; MosMedData+; Dice: 78.7. ## Original sources and implementation [Original paper]() [PDF]()