通过转移学习优化大脑年龄估计:一套预训练的基础模型,用于改善临床环境中的性能和通用性
David A Wood1, Matthew Townend1, Emily Guilhem2
1School of Biomedical Engineering and Imaging Sciences, Rayne Institute, King's College London, London, UK.
Human brain mapping
|March 4, 2024
概括
这项研究开发了深度学习模型,以使用常规临床MRI数据准确预测大脑年龄. 这些多功能模型可以直接应用或微调各种MRI序列,提高临床适用性.
科学领域:
- 神经成像是一种神经成像.
- 人工智能的人工智能
- 生物标志物开发 生物标志物开发
背景情况:
- 通过MRI估计大脑年龄是一个有前途的神经健康生物标志物.
- 挑战包括有限的大型,多样化的数据集和临床模型的数据异质性.
- 需要准确和可通用的模型才能在临床上得到广泛采用.
研究的目的:
- 利用常规临床MRI数据开发和验证用于大脑年龄预测的深度学习模型.
- 创建可适应各种MRI序列和临床场景的多功能基础模型.
- 以有限的数据来证明转移学习对模型改进的有效性.
主要方法:
- 在一大数据集 (N=18,890,年龄18-96) 上训练了五个深度学习模型,这些数据是常规的临床MRI扫描.
- 使用了五种不同的MRI序列:T2加权,T2-FLAIR,T1加权,扩散加权和GRE T2*加权.
- 员工将学习转移到微调不同MRI序列和方向的基础模型.
主要成果:
- 在所有五种模型中实现了准确的大脑年龄预测,平均绝对误差≤4.0年,R2≥0.86.
- 通过转移学习,证明了基础模型成功适应多种MRI序列和扫描方向.
- 即使使用小微调数据集 (N=25),也证实了模型的可行性,这表明其广泛适用性.
结论:
- 开发了强大的,可适应的深度学习模型,用于从临床MRI中估计大脑年龄.
- 该框架支持直接临床应用和微调各种序列,提高效用.
- 公开发布这些模型将促进临床神经科学中的更广泛的研究和应用.
更多相关视频
07:01Working Memory Training for Older Participants: A Control Group Training Regimen and Initial Intellectual Functioning Assessment
Published on: September 20, 2020
4.7K
09:47Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.0K
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
