arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.00449cs.CV
收藏

剖析用于外科手术计算机视觉的自监督学习方法

Dissecting Self-Supervised Learning Methods for Surgical Computer Vision

University of Strasbourg(斯特拉斯堡大学);CNRS(法国国家科学研究中心);University of Verona(维罗纳大学);Politecnico di Milano(米兰理工大学)
Sanat Ramesh, Vinkle Srivastav, Deepak Alapatt, Tong Yu, Aditya Murali, Luca Sestini, Chinedu Innocent Nwoye, Idris Hamoud, Saurav Sharma, Antoine Fleurentin, G… 展开作者

Sanat Ramesh, Vinkle Srivastav, Deepak Alapatt, Tong Yu, Aditya Murali, Luca Sestini, Chinedu Innocent Nwoye, Idris Hamoud, Saurav Sharma, Antoine Fleurentin, Georgios Exarchakis, Alexandros Karargyris, Nicolas Padoy

AI总结:

本文系统评估了四种自监督学习方法在外科手术视频理解中的表现,提出正确的迁移策略,在阶段识别和工具检测任务上显著超越通用SSL用法及现有半监督方法。

摘要:

近年来,随着基于深度神经网络的方法日益普及,外科手术计算机视觉领域取得了显著突破。然而,训练此类模型的标准全监督方法需要大量标注数据,由此带来了极其高昂的成本,尤其是在临床领域。自监督学习(Self-Supervised Learning,SSL)方法已开始在通用计算机视觉社区中获得关注,它代表了一种解决这些标注成本问题的潜在方案,能够仅从未标注数据中学习有用的表示。尽管如此,SSL方法在医学和外科手术等更复杂且影响更大的领域中的有效性仍然有限且尚未得到充分探索。在本工作中,我们通过在外科手术计算机视觉背景下研究四种最先进的SSL方法(MoCo v2、SimCLR、DINO、SwAV)来满足这一关键需求。我们对这些方法在Cholec80数据集上针对外科手术场景理解中两个基础且流行的任务——阶段识别和工具存在性检测——的性能进行了广泛分析。我们考察了它们的参数化方式,然后研究了它们在半监督设置下相对于训练数据量的行为。如本工作所描述和实施的那样,将这些方法正确迁移到外科手术领域,相较于SSL的通用使用方式能够带来显著的性能提升——在阶段识别上最高提升7.4%,在工具存在性检测上最高提升20%——并且相较于最先进的半监督阶段识别方法最高提升14%。在高度多样化的外科手术数据集上获得的进一步结果展现出强大的泛化性能。代码可在https://github.com/CAMMA-public/SelfSupSurg获取。

英文摘要:

The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity of deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts of annotated data, imposing a prohibitively high cost; especially in the clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction in the general computer vision community, represent a potential solution to these annotation costs, allowing to learn useful representations from only unlabeled data. Still, the effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. In this work, we address this critical need by investigating four state-of-the-art SSL methods (MoCo v2, SimCLR, DINO, SwAV) in the context of surgical computer vision. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection. We examine their parameterization, then their behavior with respect to training data quantities in semi-supervised settings. Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7.4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%. Further results obtained on a highly diverse selection of surgical datasets exhibit strong generalization properties. The code is available at https://github.com/CAMMA-public/SelfSupSurg.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑