Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic Surgery

• URL: http://arxiv.org/abs/2509.16618v1
• Date: Sat, 20 Sep 2025 10:42:29 GMT
• Title: Surgical-MambaLLM: Mamba2-enhanced Multimodal Large Language Model for VQLA in Robotic Surgery
• Authors: Pengfei Hao, Hongqiu Wang, Shuaibo Li, Zhaohu Xing, Guang Yang, Kaishun Wu, Lei Zhu,
• Abstract summary: We propose a novel method, Surgical-MambaLLM, which is the first to combine Mamba2 with Large Language Models (LLMs) in the surgical domain.<n>Specifically, we propose the Cross-modal Bidirectional Mamba2 Integration (CBMI) module to leverage Mamba2 for effective multimodal fusion.<n>We also design the Surgical Instrument Perception (SIP) scanning mode for Mamba2 to scan the surgical images, enhancing the model's spatial understanding of the surgical scene.
• Score: 22.806353035660056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, Visual Question Localized-Answering in robotic surgery (Surgical-VQLA) has gained significant attention for its potential to assist medical students and junior doctors in understanding surgical scenes. Recently, the rapid development of Large Language Models (LLMs) has provided more promising solutions for this task. However, current methods struggle to establish complex dependencies between text and visual details, and have difficulty perceiving the spatial information of surgical scenes. To address these challenges, we propose a novel method, Surgical-MambaLLM, which is the first to combine Mamba2 with LLM in the surgical domain, that leverages Mamba2's ability to effectively capture cross-modal dependencies and perceive spatial information in surgical scenes, thereby enhancing the LLMs' understanding of surgical images. Specifically, we propose the Cross-modal Bidirectional Mamba2 Integration (CBMI) module to leverage Mamba2 for effective multimodal fusion, with its cross-modal integration capabilities. Additionally, tailored to the geometric characteristics of surgical scenes, we design the Surgical Instrument Perception (SIP) scanning mode for Mamba2 to scan the surgical images, enhancing the model's spatial understanding of the surgical scene. Extensive experiments demonstrate that our Surgical-MambaLLM model outperforms the state-of-the-art methods on the EndoVis17-VQLA and EndoVis18-VQLA datasets, significantly improving the performance of the Surgical-VQLA task.

Related papers

• SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding [75.00667948967848]
  The SurgLLM framework is a large multimodal model tailored for versatile surgical video understanding tasks.<n>To empower the spatial focus of surgical videos, we first devise Surgical Context-aware Multimodal Pretraining (Surg-Pretrain) for the video encoder of SurgLLM.<n>To incorporate surgical temporal knowledge into SurgLLM, we further propose Temporal-aware Multimodal Tuning (TM-Tuning) to enhance temporal reasoning with interleaved multimodal embeddings.
  arXiv  Detail & Related papers  (2025-08-30T04:36:41Z)
• SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement [8.337819078911405]
  SurgVisAgent is an end-to-end intelligent surgical vision agent built on multimodal large language models (MLLMs)<n>It dynamically identifies distortion categories and severity levels in endoscopic images, enabling it to perform a variety of enhancement tasks.<n>We construct a benchmark simulating real-world surgical distortions, on which extensive experiments demonstrate that SurgVisAgent surpasses traditional single-task models.
  arXiv  Detail & Related papers  (2025-07-03T03:00:26Z)
• SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model [55.13206879750197]
  SurgVidLM is the first video language model designed to address both full and fine-grained surgical video comprehension.<n>We introduce the StageFocus mechanism which is a two-stage framework performing the multi-grained, progressive understanding of surgical videos.<n> Experimental results demonstrate that SurgVidLM significantly outperforms state-of-the-art Vid-LLMs in both full and fine-grained video understanding tasks.
  arXiv  Detail & Related papers  (2025-06-22T02:16:18Z)
• SurgXBench: Explainable Vision-Language Model Benchmark for Surgery [4.068223793121694]
  Vision-Language Models (VLMs) have brought transformative advances in reasoning across visual and textual modalities.<n>Existing models show limited performance, highlighting the need for benchmark studies to assess their capabilities and limitations.<n>We benchmark the zero-shot performance of several advancedVLMs on two public robotic-assisted laparoscopic datasets for instrument and action classification.
  arXiv  Detail & Related papers  (2025-05-16T00:42:18Z)
• EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery [52.992415247012296]
  We introduce EndoChat to address various dialogue paradigms and subtasks in surgical scene understanding.<n>Our model achieves state-of-the-art performance across five dialogue paradigms and eight surgical scene understanding tasks.
  arXiv  Detail & Related papers  (2025-01-20T09:12:06Z)
• Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation [51.222684687924215]
  Surgical video-language pretraining faces unique challenges due to the knowledge domain gap and the scarcity of multi-modal data.<n>We propose a hierarchical knowledge augmentation approach and a novel Procedure-Encoded Surgical Knowledge-Augmented Video-Language Pretraining framework to tackle these issues.
  arXiv  Detail & Related papers  (2024-09-30T22:21:05Z)
• VS-Assistant: Versatile Surgery Assistant on the Demand of Surgeons [29.783300422432763]
  We propose a Versatile Surgery Assistant (VS-Assistant) that can accurately understand the surgeon's intention. We devise a surgical-Calling Tuning strategy to enable the VS-Assistant to understand surgical intentions.
  arXiv  Detail & Related papers  (2024-05-14T02:05:36Z)
• Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery [15.47190687192761]
  We introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios.<n>We demonstrate the effectiveness of Surgical-LVLM on several benchmarks, including EndoVis-17-VQLA, EndoVis-18-VQLA, and a newly introduced EndoVis Conversations dataset.
  arXiv  Detail & Related papers  (2024-03-22T08:38:27Z)
• MedMamba: Vision Mamba for Medical Image Classification [0.0]
  Vision transformers (ViTs) and convolutional neural networks (CNNs) have been extensively studied and widely used in medical image classification tasks. Recent studies have shown that state space models (SSMs) represented by Mamba can effectively model long-range dependencies. We propose MedMamba, the first Vision Mamba for generalized medical image classification.
  arXiv  Detail & Related papers  (2024-03-06T16:49:33Z)
• Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures [50.09187683845788]
  Recent advancements in surgical computer vision applications have been driven by vision-only models.<n>These methods rely on manually annotated surgical videos to predict a fixed set of object categories.<n>In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals.
  arXiv  Detail & Related papers  (2023-07-27T22:38:12Z)
• Multimodal Semantic Scene Graphs for Holistic Modeling of Surgical Procedures [70.69948035469467]
  We take advantage of the latest computer vision methodologies for generating 3D graphs from camera views. We then introduce the Multimodal Semantic Graph Scene (MSSG) which aims at providing unified symbolic and semantic representation of surgical procedures.
  arXiv  Detail & Related papers  (2021-06-09T14:35:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.