MedSAM-2 Large Model-Driven Medical Image Semantic Communication for Telemedicine

The boom in telemedicine and digital healthcare has spurred a surge in demand for medical image transmission, especially in remote areas with limited bandwidth, imposing a heavy burden on communication systems. To address the challenge of efficient transmission of massive medical images, this paper proposes a semantic communication-based solution called medical image joint source channel coding (Med-JSCC). Our motivation stems from the fact that during clinical diagnosis, medical professionals predominantly focus on regions of interest (ROI), i.e., critical regions, while paying relatively less attention to non-region of interest (NROI). This inspires us to adopt a differentiated processing strategy. Specifically, we first design a mask-guided feature processing module, where the mask generated by the large medical image segmentation model (e.g., MedSAM-2) identifies ROI-relevant and ROI-irrelevant semantic features. On this basis, a differentiated processing strategy is proposed to balance transmission efficiency and diagnostic reliability. Furthermore, the proposed Med-JSCC integrates an adaptive transmission module, including variable-length coding and a channel adaptive unit (CAU). The former can assign transmission rates to semantic features based on a learned entropy model, while the latter improves the robustness against channel variations by recalibrating semantic features based on channel parameters. Experimental results on dental and chest X-ray datasets demonstrate that our method effectively improves transmission efficiency while preserving diagnostically critical information in medical images.