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

Query-driven generative AI synthesizes multi-modal spatial omics from histology.

bioRxiv : the preprint server for biology·2025
Same author

The hope and the hype of artificial intelligence for syncope management.

European heart journal. Digital health·2025
Same author

CelloType: a unified model for segmentation and classification of tissue images.

Nature methods·2024
Same author

CelloType: A Unified Model for Segmentation and Classification of Tissue Images.

bioRxiv : the preprint server for biology·2024
Same author

Deep learning from latent spatiotemporal information of the heart: Identifying advanced bioimaging markers from echocardiograms.

Biophysics reviews·2024
Same author

Kernel-weighted contribution: a method of visual attribution for 3D deep learning segmentation in medical imaging.

Journal of medical imaging (Bellingham, Wash.)·2023

相关实验视频

Updated: Jul 16, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.8K

补丁式3D细分质量评估,将重建和回归网络结合起来.

Fahim Ahmed Zaman1, Tarun Kanti Roy2, Milan Sonka1

  • 1University of Iowa, Department of Electrical and Computer Engineering, Iowa City, Iowa, United States.

Journal of medical imaging (Bellingham, Wash.)
|September 11, 2023
PubMed
概括

这项研究引入了一个深度学习框架,用于检测3D医学图像细分中的不准确性,而不需要地面真相数据. 该方法准确地识别出错误的细分区域,有助于疾病诊断.

关键词:
3D医学成像 3D医学成像卷积神经网络是一种卷积神经网络.生成性的对抗性网络.分段化质量评估分段化质量评估

更多相关视频

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
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K

相关实验视频

Last Updated: Jul 16, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.8K
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
Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands
10:59

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

14.5K

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:

  • 基于深度学习 (DL) 的语义细分方法通常因复杂的结构和有限的基准真相数据而与3D医疗图像扎.
  • 准确的细分质量对于局部疾病区域至关重要,而不仅仅是全球平均值,以有效诊断.

研究的目的:

  • 开发一个DL框架,用于预测分段质量和识别3D医疗图像中的不准确区域,而不需要地面真相.
  • 通过使可靠的细分质量评估,解决快速诊断的需要.

主要方法:

  • 提出了一个框架,结合了3D生成对抗网络 (GAN) 和卷积回归网络.
  • 条件GAN重建了被细分结果掩盖的输入图像,回归网络根据细分预测了基于补丁的子相似系数 (DSC).
  • 该方法利用了细分衍生的特征,消除了推理过程中对基本真相的需求.

主要成果:

  • 该方法在3D膝盖MRI和肺CT数据集上进行了评估.
  • 补丁智能的DSC预测实现了膝盖MR的0.01和肺CT的0.04的平均绝对误差.
  • 该框架成功地局部化了细分不准确性.

结论:

  • 拟议的DL框架有效地识别了3D医学图像中错误的细分区域.
  • 这种能力可以显著帮助下游疾病诊断和预后预测.
  • 该方法为医疗图像细分中的质量控制提供了有希望的方法.