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

Deep learning-derived pericardial adipose tissue by electrocardiogram-gated cardiac computed tomography predicts cardiovascular events beyond coronary calcium score.

American journal of preventive cardiology·2026
Same author

A call for action: The need to quantify the "-itis" in primary sclerosing cholangitis.

Journal of hepatology·2026
Same author

MRI Deep Learning for Differentiating Glioblastoma, IDH Wild-type from Central Nervous System Diffuse Large B-cell Lymphoma.

Cancer research communications·2026
Same author

EchoAtlas: A Conversational, Multi-View Vision-Language Foundation Model for Echocardiography Interpretation and Clinical Reasoning.

medRxiv : the preprint server for health sciences·2026
Same author

Approach to Patient: Stalk Lesions of the Pituitary Gland.

The Journal of clinical endocrinology and metabolism·2026
Same author

Systematic Review: Agentic AI in Neuroradiology: Technical Promise with Limited Clinical Evidence.

Journal of imaging informatics in medicine·2026

相关实验视频

Updated: Jun 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

医学图像对象检测框架 (MedYOLO):一个医学图像对象检测框架.

Joseph Sobek1, Jose R Medina Inojosa2,3, Betsy J Medina Inojosa2

  • 1Department of Radiology, Mayo Clinic, Rochester, MN, USA. sobek.joseph@mayo.edu.

Journal of imaging informatics in medicine
|June 6, 2024
PubMed
概括
此摘要是机器生成的。

MedYOLO是一个3D物体检测框架,为医疗成像任务提供了CNN的高效替代方案. 它在各种数据集上实现了高性能,减少了放射学中AI的注释工作.

关键词:
计算机断层扫描 (CT) 是一种计算机断层扫描.卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.磁共振是一种磁共振.医学成像医学成像对象检测检测对象检测对象检测

更多相关视频

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

7.7K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.7K

相关实验视频

Last Updated: Jun 24, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

7.7K
Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment
13:01

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

3.7K

科学领域:

  • 医学成像分析 医学成像分析
  • 放射学中的人工智能
  • 计算机视觉用于医疗保健

背景情况:

  • 卷积神经网络 (CNN) 是医疗图像细分的标准,但需要广泛的专家注释.
  • 对象检测模型为那些不需要voxel级精度的任务提供了较少的注释力.
  • 医疗成像存在有限的通用3D物体检测框架.

研究的目的:

  • 介绍MedYOLO,一个用于医学成像的3D物体检测框架.
  • 评估MedYOLO在各种医疗数据集中的表现.
  • 展示对象检测的潜力,以减少放射学AI中的注释负担.

主要方法:

  • 开发了MedYOLO,这是一个基于YOLO (You Only Look Once) 一次性检测模型的3D物体检测框架.
  • 在四个不同的数据集上测试了MedYOLO:BRaTS,LIDC,腹部CT和ECG-gated心脏CT.
  • 使用0.5.5的合并 (IoU) 值的交叉点的平均平均精度 (mAP) 评估性能.

主要成果:

  • 在没有超参数调整的情况下,MedYOLO在多个数据集中实现了高性能.
  • 获得了0.861 (BRaTS),0.715 (腹部CT) 和0.995 (心脏CT) 的mAP@0.5得分.
  • 该模型在某些结构上遇到了困难,未能在LIDC数据集上收 (mAP@0.5的0.0).

结论:

  • MedYOLO是一个有前途的3D对象检测框架,用于医学成像,提供高效和高性能.
  • 与传统的细分模型相比,该框架显示了减少注释工作的潜力.
  • 需要进一步发展,以应对特定数据集和结构的挑战,如LIDC.