期刊
NATURE COMPUTATIONAL SCIENCE
卷 2, 期 5, 页码 298-+出版社
SPRINGERNATURE
DOI: 10.1038/s43588-022-00250-z
关键词
-
类别
资金
- Department of Biotechnology-Wellcome Trust India Alliance Intermediate fellowship [IA/I/15/2/502089]
- Science and Engineering Research Board Early Career award [ECR/2016/000403]
- Department of Biotechnology-Indian Institute of Science Partnership Program
- India Trento Partnership Program
- Pratiksha Trust Intramural grant
- NSF [IIS-1636893, BCS-1734853, OAC-1916518, IIS-1912270]
- NIH [NIBIB R01EB029272, NIMH R01MH126699, NIBIB R01EB030896]
- Microsoft Investigator Fellowship
- Ministry of Human Resource Development, Government of India
Different tractography algorithms can produce widely varying connectivity estimates. This study introduces a GPU-based implementation that achieves significantly faster speeds and improved accuracy in generating brain connectomes. The implementation also has potential applications in various real-world problems.
Diffusion magnetic resonance imaging and tractography enable the estimation of anatomical connectivity in the human brain, in vivo. Yet, without ground-truth validation, different tractography algorithms can yield widely varying connectivity estimates. Although streamline pruning techniques mitigate this challenge, slow compute times preclude their use in big-data applications. We present 'Regularized, Accelerated, Linear Fascicle Evaluation' (ReAl-LiFE), a GPU-based implementation of a state-of-the-art streamline pruning algorithm (LiFE), which achieves >100x speedups over previous CPU-based implementations. Leveraging these speedups, we overcome key limitations with LiFE's algorithm to generate sparser and more accurate connectomes. We showcase ReAl-LiFE's ability to estimate connections with superlative test-retest reliability, while outperforming competing approaches. Moreover, we predicted inter-individual variations in multiple cognitive scores with ReAl-LiFE connectome features. We propose ReAl-LiFE as a timely tool, surpassing the state of the art, for accurate discovery of individualized brain connectomes at scale. Finally, our GPU-accelerated implementation of a popular non-negative least-squares optimization algorithm is widely applicable to many real-world problems.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据