Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement

作者
Long Bai,Boyi Ma,Ruohan Wang,Guankun Wang,Beilei Cui,Zhongliang Jiang,Mobarakol Islam,Zhe Min,Jiewen Lai,Nassir Navab,Hongliang Ren
出处
期刊:Cornell University - arXiv [Cornell University]
标识
DOI:10.48550/arxiv.2505.01766
摘要

Surgical workflow recognition is vital for automating tasks, supporting decision-making, and training novice surgeons, ultimately improving patient safety and standardizing procedures. However, data corruption can lead to performance degradation due to issues like occlusion from bleeding or smoke in surgical scenes and problems with data storage and transmission. In this case, we explore a robust graph-based multimodal approach to integrating vision and kinematic data to enhance accuracy and reliability. Vision data captures dynamic surgical scenes, while kinematic data provides precise movement information, overcoming limitations of visual recognition under adverse conditions. We propose a multimodal Graph Representation network with Adversarial feature Disentanglement (GRAD) for robust surgical workflow recognition in challenging scenarios with domain shifts or corrupted data. Specifically, we introduce a Multimodal Disentanglement Graph Network that captures fine-grained visual information while explicitly modeling the complex relationships between vision and kinematic embeddings through graph-based message modeling. To align feature spaces across modalities, we propose a Vision-Kinematic Adversarial framework that leverages adversarial training to reduce modality gaps and improve feature consistency. Furthermore, we design a Contextual Calibrated Decoder, incorporating temporal and contextual priors to enhance robustness against domain shifts and corrupted data. Extensive comparative and ablation experiments demonstrate the effectiveness of our model and proposed modules. Moreover, our robustness experiments show that our method effectively handles data corruption during storage and transmission, exhibiting excellent stability and robustness. Our approach aims to advance automated surgical workflow recognition, addressing the complexities and dynamism inherent in surgical procedures.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
上官若男的应助被芒果采纳,获得10
刚刚
饿饿饿饿发布了新的文献求助10
刚刚
乐观囧完成签到,获得积分10
刚刚
粉色娇嫩完成签到 ,获得积分10
刚刚
不爱吃早饭完成签到 ,获得积分10
刚刚
刚刚
烟花的应助被深林狼采纳,获得100
刚刚
科目三的应助被1101592875采纳,获得30
刚刚
YananLi完成签到,获得积分10
刚刚
沉淀发布了新的文献求助10
1秒前
1秒前
Lizhiiiy完成签到,获得积分10
1秒前
时长两年半完成签到,获得积分10
1秒前
无花果的应助被发嗲的乘云采纳,获得10
1秒前
1秒前
Septvirouo9完成签到,获得积分10
1秒前
俊俊发布了新的文献求助10
2秒前
2秒前
香蕉寒珊完成签到,获得积分10
2秒前
AAA095完成签到,获得积分10
2秒前
zhaoxixi发布了新的文献求助20
2秒前
3秒前
3秒前
3秒前
山石梦沧海完成签到,获得积分10
3秒前
英俊的铭的应助被风月将晚采纳,获得10
4秒前
终梦的应助被Vivi采纳,获得10
4秒前
hua发布了新的文献求助10
4秒前
SciGPT的应助被专注秋尽采纳,获得10
5秒前
小巧的洋葱完成签到,获得积分10
5秒前
Solitary发布了新的文献求助10
5秒前
英俊的铭的应助被张博采纳,获得10
5秒前
物理循州发布了新的文献求助10
6秒前
清水17完成签到 ,获得积分10
6秒前
6秒前
汉堡包的应助被lily采纳,获得10
6秒前
syr111完成签到,获得积分10
6秒前
1900发布了新的文献求助10
7秒前
空空发布了新的文献求助10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8181072
求助须知:如何正确求助?哪些是违规求助? 9571092
关于积分的说明 21816478
捐赠科研通 7777477
什么是DOI,文献DOI怎么找? 3433418
关于科研通互助平台的介绍 2557638
邀请新用户注册赠送积分活动 2479460