Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery

Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simp...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Wang, Guankun, Long, Bai, Nah, Wan Jun, Wang, Jie, Zhang, Zhaoxi, Chen, Zhen, Wu, Jinlin, Islam, Mobarakol, Liu, Hongbin, Ren, Hongliang
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 22.03.2024
Subjects
Automation
Customization
Language
Modules
Performance standards
Questions
Robotic surgery
Task complexity
Vision
Visual perception
Visual tasks
Online AccessGet full text

Cover

More Information
Summary:Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simple structured answers and struggle with complex scenarios due to their limited capability in recognizing long-range dependencies and aligning multimodal information. In this paper, we introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios. Leveraging the pre-trained large vision-language model and specialized Visual Perception LoRA (VP-LoRA) blocks, our model excels in understanding complex visual-language tasks within surgical contexts. In addressing the visual grounding task, we propose the Token-Interaction (TIT) module, which strengthens the interaction between the grounding module and the language responses of the Large Visual Language Model (LVLM) after projecting them into the latent space. We demonstrate the effectiveness of Surgical-LVLM on several benchmarks, including EndoVis-17-VQLA, EndoVis-18-VQLA, and a newly introduced EndoVis Conversations dataset, which sets new performance standards. Our work contributes to advancing the field of automated surgical mentorship by providing a context-aware solution.
ISSN:2331-8422