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

Simulating the Dedifferentiation Process of Thyroid Cancer: Insights from Mouse Models and Ultrasound Imaging.

Ultrasound in medicine & biology·2026
Same author

Citrus-leaf microemulsion controls postharvest mold through membrane disruption and host defense enhancement.

Food chemistry: X·2026
Same author

An Open Multi-Center Whole-Body FDG PET/CT Foundation Model for Tumor Segmentation.

ArXiv·2026
Same author

Efficacy and cost-effectiveness of intraoperative cell salvage for patients with placenta previa during cesarean section: a retrospective comparison analysis.

Open medicine (Warsaw, Poland)·2026
Same author

Multimodal deep learning fusion model for assessment of fetal lung development in gestational diabetes mellitus and pre-eclampsia.

Frontiers in endocrinology·2026
Same author

Dose-aware diffusion model for 3D PET image denoising: Multi-institutional validation with reader study and real low-dose data.

Medical image analysis·2026

相关实验视频

Updated: Jul 27, 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

2.8K

HAL-IA:一种混合主动学习框架,使用交互式注释来进行医疗图像细分.

Xiaokang Li1, Menghua Xia1, Jing Jiao1

  • 1Department of Electronic Engineering, School of Information Science and Technology, Fudan University, Shanghai, China.

Medical image analysis
|June 9, 2023
PubMed
概括

本研究介绍了一种使用交互注释 (HAL-IA) 的混合主动学习框架,以降低医疗图像细分成本. HAL-IA有效地生成精确的像素智能标签,使用更少的数据和更少的交互.

关键词:
积极学习是指积极学习.附注 降低成本 降低成本交互式细分化 交互式细分化医疗图像细分 医疗图像细分地区一致性 地区一致性

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

447
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.7K

相关实验视频

Last Updated: Jul 27, 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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

447
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.7K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 医疗图像分割的深度学习需要广泛的像素智能注释,这是耗时且昂贵的.
  • 降低注释成本对于医学图像细分的广泛临床应用至关重要.

研究的目的:

  • 开发一个有效的医疗图像细分框架,最大限度地降低注释成本.
  • 为了应对冷启动,样本选择和手动注释负担在分段化主动学习中的挑战.

主要方法:

  • 提出了使用交互式注释 (HAL-IA) 的混合主动学习框架.
  • 引入了一种新的混合样本选择策略,结合像素,区域一致性和图像多样性.
  • 实施了热启动初始化策略,以克服冷启动问题.
  • 开发了一个交互式注释模块,建议使用超级像素来简化标签.

主要成果:

  • HAL-IA框架在像素智能注释和细分模型中实现了高精度.
  • 与现有方法相比,显著减少了标记数据要求和手动交互.
  • 在四个医学图像数据集中超越了最先进的方法.

结论:

  • 在保持高精度的同时,HAL-IA有效降低了医疗图像细分的注释成本.
  • 该框架为医生提供了一种实际的解决方案,以获得用于临床分析和诊断的准确细分结果.
  • 这种方法促进了高效的医学图像分析,并支持改善患者护理.