Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

A systematic approach to standardizing the visual appearance of endometriotic lesions for artificial intelligence recognition.

Acta obstetricia et gynecologica Scandinavica·2026
Same author

Camera augmentation: enabling uncalibrated stereo matching of minimally invasive surgery images by training from the wealth of public synthetic image datasets.

International journal of computer assisted radiology and surgery·2026
Same author

Tumour-focused 3D-2D registration in liver laparoscopy.

International journal of computer assisted radiology and surgery·2026
Same author

Do MRI radiomic models truly generalize? External validation of three studies in parotid lesion characterization.

European radiology·2026
Same author

Hidden Tumour Visualization in Augmented Monocular Liver Laparoscopy.

Healthcare technology letters·2026
Same author

Author's reply.

Journal of minimally invasive gynecology·2026

相关实验视频

Updated: Jun 28, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.0K

手术计算机视觉可以从大规模视觉基础模型中受益吗?

Navid Rabbani1, Adrien Bartoli2

  • 1DIA2M, DRCI, CHU Clermont-Ferrand, Clermont-Ferrand, France. navid_rabbani@yahoo.com.

International journal of computer assisted radiology and surgery
|April 12, 2024
PubMed
概括

像DINO和SAM这样的基础模型显示了外科计算机视觉的巨大潜力,在仪器和子宫细分方面取得了最先进的结果,特别是在数据有限的场景中.

科学领域:

  • 计算机视觉 计算机视觉
  • 医疗成像医学成像
  • 手术技术 手术技术

背景情况:

  • 在各种视觉数据上预训练的基础模型越来越多地被用于专业领域.
  • 手术计算机视觉任务,如仪器和子宫细分,需要强大而准确的模型.

研究的目的:

  • 调查外科计算机视觉基础模型的有效性.
  • 在仪器和子宫细分任务中开发和评估这些模型的新型适应方法.

主要方法:

  • 使用了DINOv1,DINOv2和SAM背骨与ART-Net和SurgAI3.8K数据集.
  • 实施监督,无监督和少量学习适应,包括DINO-UNet和SAM适应.
  • 根据现有方法对17种仪器和7种子宫细分模型进行了评估.

主要成果:

  • 使用线性解码器进行少量射击学习证明是可行的.
  • 无监督和线性解码方法在数据稀缺的环境中显示出实用性.
  • 拟议的DPT和DINO-UNet调整实现了新的最先进的性能,以显著的利率超过了以前的最佳表现 (例如,仪器细分5.6pp).

结论:

  • 视觉基础模型,特别是DINO和SAM,对外科计算机视觉有很大的前景.
关键词:
微创手术是一种微创手术.分段化 分段化 分段化 分段化视觉基础模型的模型

更多相关视频

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.8K
Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication
07:47

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication

Published on: December 15, 2023

684

相关实验视频

Last Updated: Jun 28, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.0K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.8K
Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication
07:47

Author Spotlight: 3D Scanning and Augmented Reality for Enhanced Cancer Surgery Communication

Published on: December 15, 2023

684
  • 这些模型在医学图像分析场景中特别有价值,这些场景的特点是有限或复杂的数据.