Scholarlink

<p>Segmentation of surgical instruments is crucial for enhancing surgeon performance and ensuring patient safety. Conventional techniques share a common drawback: they do not accommodate the parts of instruments obscured by tissues or other instruments. Precisely predicting the full extent of occluded instruments can significantly improve laparoscopic surgeries by providing critical guidance during operations and assisting in the analysis of potential surgical errors, as well as serving educational purposes. In this paper, we introduce amodal segmentation to the realm of surgical instruments in the medical field. We propose a new Amodal Instruments Segmentation (AIS) dataset, which was developed by reannotating each instrument with its complete mask, utilizing the 2017 MICCAI EndoVis Robotic Instrument Segmentation Challenge dataset. It includes 10 videos with a total of 3,000 frames and 7,084 instances. Additionally, we evaluate several typical segmentation methods to establish a benchmark for this new dataset. Data and code are available at https://github.com/EmmaSRH/AIS.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Amodal Segmentation for Laparoscopic Surgery Video Instruments

  • 期刊论文

  • 发表日期：

    2025年6月3日

查看全文
  • Ruohua Shi,
  • Zhaochen Liu,
  • Lingyu Duan,
  • Tingting Jiang

摘要

Segmentation of surgical instruments is crucial for enhancing surgeon performance and ensuring patient safety. Conventional techniques share a common drawback: they do not accommodate the parts of instruments obscured by tissues or other instruments. Precisely predicting the full extent of occluded instruments can significantly improve laparoscopic surgeries by providing critical guidance during operations and assisting in the analysis of potential surgical errors, as well as serving educational purposes. In this paper, we introduce amodal segmentation to the realm of surgical instruments in the medical field. We propose a new Amodal Instruments Segmentation (AIS) dataset, which was developed by reannotating each instrument with its complete mask, utilizing the 2017 MICCAI EndoVis Robotic Instrument Segmentation Challenge dataset. It includes 10 videos with a total of 3,000 frames and 7,084 instances. Additionally, we evaluate several typical segmentation methods to establish a benchmark for this new dataset. Data and code are available at https://github.com/EmmaSRH/AIS.