arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.09360cs.CVcs.AI

LACOSTE：利用立体与时序上下文进行手术器械分割

LACOSTE: Exploiting stereo and temporal contexts for surgical instrument segmentation

School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC)（中国科学技术大学生命科学与医学部生物医学工程学院）；Suzhou Institute for Advanced Research, USTC（中国科学技术大学苏州研究院）；Key Laboratory of Precision and Intelligent Chemistry, USTC（中国科学技术大学精准与智能化学重点实验室）

Qiyuan Wang, Shang Zhao, Zikang Xu, S Kevin Zhou

备注：
Preprint submitted to Medical Image Analysis
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有手术器械分割方法忽略视频时序与立体属性、鲁棒性差的问题，提出LACOSTE模型，通过三个模块利用立体与时序上下文，在多个数据集上取得了优于或比肩现有SOTA的性能。

摘要：

手术器械分割对微创手术及相关应用至关重要。以往大多数方法将该任务建模为基于单帧的实例分割，忽略了手术视频天然的时序与立体属性，导致这类方法对时序运动和视角变化带来的外观变化鲁棒性较差。本文提出一种新型LACOSTE模型，利用立体与时序图像中的位置无关上下文来改进手术器械分割效果。该模型以基于查询的分割模型为核心，设计了三个性能提升模块：首先，设计视差引导的特征传播模块，显式增强深度感知特征；为了即使在单目视频下也能良好泛化，采用伪立体方案生成互补的右视图。其次，提出立体-时序集合分类器，以通用方式聚合立体-时序上下文以生成整合预测，缓解瞬时失效问题。最后，提出位置无关分类器，将位置偏差与掩码预测解耦，增强特征语义。我们在三个公开手术视频数据集上广泛验证了所提方法，包括两个来自EndoVis挑战赛的基准数据集和一个真实根治性前列腺切除术数据集GraSP。实验结果表明，该方法性能优异，始终能取得与以往最先进方法相当或更优的结果。

英文摘要：

Surgical instrument segmentation is instrumental to minimally invasive surgeries and related applications. Most previous methods formulate this task as single-frame-based instance segmentation while ignoring the natural temporal and stereo attributes of a surgical video. As a result, these methods are less robust against the appearance variation through temporal motion and view change. In this work, we propose a novel LACOSTE model that exploits Location-Agnostic COntexts in Stereo and TEmporal images for improved surgical instrument segmentation. Leveraging a query-based segmentation model as core, we design three performance-enhancing modules. Firstly, we design a disparity-guided feature propagation module to enhance depth-aware features explicitly. To generalize well for even only a monocular video, we apply a pseudo stereo scheme to generate complementary right images. Secondly, we propose a stereo-temporal set classifier, which aggregates stereo-temporal contexts in a universal way for making a consolidated prediction and mitigates transient failures. Finally, we propose a location-agnostic classifier to decouple the location bias from mask prediction and enhance the feature semantics. We extensively validate our approach on three public surgical video datasets, including two benchmarks from EndoVis Challenges and one real radical prostatectomy surgery dataset GraSP. Experimental results demonstrate the promising performances of our method, which consistently achieves comparable or favorable results with previous state-of-the-art approaches.

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。

↑