Vision-Language Models (VLMs) have shown significant potential in surgical scene analysis, yet existing models are limited by frame-level datasets and lack high-quality video data with procedural surgical knowledge. To address these challenges, we make the following contributions: (i) SurgPub-Video, a comprehensive dataset of over 3,000 surgical videos and 25 million annotated frames across 11 specialities, sourced from peer-reviewed clinical journals, (ii) SurgLLaVA-Video, a specialized VLM for surgical video understanding, built upon the TinyLLaVA-Video architecture that supports both video-level and frame-level inputs, and (iii) a video-level surgical Visual Question Answering (VQA) benchmark, covering diverse 11 surgical specialities, such as vascular, cardiology, and thoracic. Extensive experiments, conducted on the proposed benchmark and three additional surgical downstream tasks (action recognition, skill assessment, and triplet recognition), show that SurgLLaVA-Video significantly outperforms both general-purpose and surgical-specific VLMs with only three billion parameters.

Clinically, bi-parametric MRI (bp-MRI), including T2-weighted imaging, diffusion-weighted imaging, and apparent diffusion coefficient map, offers essential prior localization of biopsy and focal therapy for suspicious clinically significant prostate cancer (csPCa), and accurate csPCa delineation from bp-MRI is crucial for better outcomes. However, due to the complexity and high variability in appearance, size, shape, and indistinct boundaries, delineating csPCa remains challenging, time-consuming, and heavily relies on the clinician's experience. To address these issues, we propose MT-SAM, a novel framework that enhances SAM with higher-quality feature extraction and a prior-guided automatic prompting strategy. Specifically, we introduce a mamba-transformer network to extract multi-stage multi-modal features from bp-MRI and fuse them into the SAM encoder via cross-mamba modules. Moreover, we propose a prior-guided pyramid-mamba prompting strategy to strengthen the model's attention on the targets. We extensively evaluate our method on both public and private datasets, and the experimental results show that our method achieves up to 5.6-34.1% higher Dice scores than state-of-the-art methods. Code is available at https://github.com/LuckLT/MT-SAM.