相关实验视频

Updated: Jul 8, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

BrainMass:推进大脑网络分析以诊断大规模自主监督学习

Yanwu Yang, Chenfei Ye, Guinan Su

IEEE transactions on medical imaging

|June 14, 2024

概括

我们开发了BrainMass,这是使用自主监督学习进行大脑网络的新型基础模型. 它在神经科学任务和疾病诊断方面表现出强大的表现和适应性.

科学领域:

神经科学是一个神经科学.
人工智能的人工智能
医学图像分析医学图像分析

背景情况:

基础模型在各种任务的自我监督学习中表现出色.
医疗数据的异质性和收集挑战从基础模型中受益.
关于大脑网络基础模型的研究有限,这阻碍了它们的应用.

研究的目的:

解决大脑网络基础模型中的差距.
提高神经科学研究中的适应性和通用性.
开发一种用于分析大脑网络的多功能框架.

主要方法:

从30个来源策划了一个大型数据集 (70,781个样本,46,686名参与者).
引入伪功能连接 (pFC) 用于数据增强.
提出了BrainMass框架与面具-ROI建模 (MRM) 和隐性表示对齐 (LRA) 进行自我监督学习.

主要成果:

在八个内部和七个外部的大脑疾病诊断任务中,BrainMass实现了卓越的性能.
在各种神经科学应用中表现出显著的概括性和适应性.
展示了强大的少数/零射击学习能力.

结论:

BrainMass为大脑网络分析提供了一个强大的基础模型.
该框架具有临床应用的潜力,因为它可以在疾病背景下进行解释.
突出了自我监督学习对推进神经科学研究的有效性.

更多相关视频

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

相关概念视频

Metacognition

Metacognition

Metacognition is a conscious process where individuals are aware of their cognitive and executive processes, such as planning before solving a problem or self-monitoring during reading. For instance, a writer may need help with composing a piece. The situation involves a writer who is working on a piece of writing, but while doing so, they realize that something is missing. They notice that their characters lack depth or details. This realization occurs because the writer is reflecting on their...