Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Multimodal machine learning for distinguishing pediatric multiple sclerosis from non-inflammatory conditions using optical coherence tomography.

Frontiers in neurology·2026

Same author

Multiclass Radiomics-Based Prediction of BRAF Mutation Status in Pediatric Low-Grade Gliomas Using Multisequence MRI.

AJNR. American journal of neuroradiology·2026

Same author

Federated Learning in Neurology: Bridging Data Privacy and Artificial Intelligence for Brain Health.

Seminars in neurology·2025

Same author

Canadian Spine Society: 25th Annual Scientific Conference, February 25 to 28, 2025, Fairmont Le Manoir Richelieu, La Malbaie, Charlevoix, Que., Canada.

Canadian journal of surgery. Journal canadien de chirurgie·2025

Same author

Segmentation-free pretherapeutic assessment of BRAF-status in pediatric low-grade gliomas.

Communications medicine·2025

Same author

Multiclass machine learning models for molecular subtype identification of pediatric low-grade glioma using bi-institutional MRIs for precision medicine.

NPJ precision oncology·2025

Search research articles

相关实验视频

Updated: Jul 21, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

相关性地图:MRI中3D脑瘤的弱监督细分方法.

Sajith Rajapaksa^1,2, Farzad Khalvati^{1,3,2,4,5,6,7}

¹Neurosciences and Mental Health, The Hospital for Sick Children, Toronto, ON, Canada.

Frontiers in radiology

|July 26, 2023

概括

本研究介绍了一种使用深度学习用于医疗图像细分的弱监督方法. 它有效地从MRI扫描中提取瘤区域,提高诊断准确度,而不需要大量的手动注释.

关键词:

美国有线电视新闻网 - 卷积神经网络这就是为什么MRI是MRI.大脑瘤脑瘤可以解释性的解释性.细分化细分化的细分化超级像素是一个超级像素.监管能力较弱的监管机构.

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

相关实验视频

Last Updated: Jul 21, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

科学领域:

医学成像分析医学成像分析
医疗保健中的人工智能
计算病理学计算病理学

背景情况:

深度卷积神经网络 (CNN) 对于医学图像分析至关重要,但需要大量的注释数据集.
弱监督的方法通过从全球标签中提取本地信息来提供解决方案.
精确细分像质瘤这样的大脑瘤对于诊断和治疗规划至关重要.

研究的目的:

开发一个弱监督的管道,从3D医疗图像生成相关性地图.
为了实现兴趣区域的自动细分,特别是脑瘤,仅使用分类标签.
为了提高医疗图像细分的准确性和可视化分辨率.

主要方法:

提出了一个弱监督的管道,利用预训练的3D CNNs上的局部干扰来提取相关性地图.
引入了利用3D超像素和U-net架构的最佳扰动生成方法.
采用扰动损失函数来最大限度地提高未被扰动和被扰动输入之间的预测差异.

主要成果:

在MRI扫描中成功应用了该方法来细分质瘤脑瘤.
拟议的方法表现出优越的性能,与现有的技术相比,在子相似系数的细分.
在可视化中实现了更高的分辨率,有助于更清晰地解释细分区域.

结论:

开发的弱监督管道有效地提取医疗图像中的关键区域,促进自动细分.
这种方法显著减少了在医学成像AI中广泛细粒度注释的需要.
该方法有望改善计算机辅助诊断管道,特别是在脑瘤细分方面.