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

Latent representations of early brain development: A multivariate normative model of brain structure and behaviour.

Developmental cognitive neuroscience·2026

Same author

From early to contemporary normative modeling: Mapping individual differences in neurophysiological signals.

Imaging neuroscience (Cambridge, Mass.)·2026

Same author

A critical perspective on finite sample conformal prediction theory in medical applications.

Artificial intelligence in medicine·2026

Same author

Lamellar Normative Modelling of the Hippocampus Across the Human Lifespan.

bioRxiv : the preprint server for biology·2026

Same author

Cerebellar growth is associated with domain-specific cerebral maturation and socio-linguistic behavior.

Nature communications·2026

Same author

Understanding Benefits and Pitfalls of Current Methods for the Segmentation of Undersampled MRI Data.

IEEE transactions on bio-medical engineering·2026

Search research articles

相关实验视频

Updated: Jan 8, 2026

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

在医学成像中使用聚合规范扩散来检测无监督的异常.

Alexander Frotscher¹, Jaivardhan Kapoor², Thomas Wolfers¹

¹University Hospital Tübingen, Tübingen, 72074, Baden-Württemberg, Germany.

Medical image analysis

|December 20, 2025

概括

一种新的无监督异常检测 (UAD) 方法,聚合规范扩散 (ANDi),显示在MRI扫描中识别大脑异常的性能有所改善. ANDi超越了现有的方法,特别是用于检测多发性硬化病变.

关键词:

脑子脑子大脑脑子计算机辅助检测和诊断机器学习机器学习磁共振成像技术磁共振成像技术基于分数的生成模型

更多相关视频

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

相关实验视频

Last Updated: Jan 8, 2026

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging

Published on: December 15, 2014

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

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
神经科学研究神经科学研究

背景情况:

早期发现脑磁共振成像 (MRI) 异常对于医学诊断和治疗至关重要.
用于异常检测的监督机器学习受限于对特定病理学的广泛标记数据的需求.
无监督异常检测 (UAD) 是一种有希望的方法,可以通过检测正常模式的偏差来识别更广泛的异常.

研究的目的:

为了解决现有的UAD方法的局限性,以对多模式脑MRI数据中的各种异常进行概括.
引入和评估一种名为聚合规范扩散 (ANDi) 的新型UAD方法.

主要方法:

在Denoising Diffusion Probabilistic Models (DDPMs) 中,ANDi汇总了预测的Denoising步骤和地面真相向后转换之间的差异.
在ANDi中使用的DDPM被训练在金字塔式高斯噪声上.
拟议的方法与三个不同的大脑MRI数据集的四个最近的UAD基线进行了验证.

主要成果:

与现有的UAD基线相比,ANDi在检测大脑MRI异常方面取得了实质性的改进.
该方法对各种类型的异常具有更高的稳定性.
具体来说,ANDi在检测多发性硬化症 (MS) 病变的精度回忆曲线 (AUPRC) 下面面积方面取得了高达44%的改善.

结论:

聚合规范扩散 (ANDi) 代表了多模态大脑MRI无监督异常检测的重大进展.
开发的方法提供了更高的准确性和稳定性,特别有利于识别神经系统疾病,如MS.
ANDi有可能改善早期检测和诊断更广泛的大脑异常的范围.