Video and Synthetic MRI Pre-training of 3D Vision Architectures for Neuroimage Analysis

no code implementations • 9 Sep 2023 • Nikhil J. Dhinagar, Amit Singh, Saket Ozarkar, Ketaki Buwa, Sophia I. Thomopoulos, Conor Owens-Walton, Emily Laltoo, Yao-Liang Chen, Philip Cook, Corey McMillan, Chih-Chien Tsai, J-J Wang, Yih-Ru Wu, Paul M. Thompson

The resulting pre-trained models can be adapted to a range of downstream neuroimaging tasks, even when training data for the target task is limited.

Transfer Learning

Few-Shot Classification of Autism Spectrum Disorder using Site-Agnostic Meta-Learning and Brain MRI

no code implementations • 14 Mar 2023 • Nikhil J. Dhinagar, Vignesh Santhalingam, Katherine E. Lawrence, Emily Laltoo, Paul M. Thompson

Inspired by the effectiveness of meta-learning for optimizing a model across multiple tasks, here we propose a framework to adapt it to learn across multiple sites.

Meta-Learning Transfer Learning

Efficiently Training Vision Transformers on Structural MRI Scans for Alzheimer's Disease Detection

no code implementations • 14 Mar 2023 • Nikhil J. Dhinagar, Sophia I. Thomopoulos, Emily Laltoo, Paul M. Thompson

In our experiments, two vision transformer architecture variants achieved an AUC of 0. 987 for sex and 0. 892 for AD classification, respectively.

Alzheimer's Disease Detection Data Augmentation

Curriculum Based Multi-Task Learning for Parkinson's Disease Detection

no code implementations • 27 Feb 2023 • Nikhil J. Dhinagar, Conor Owens-Walton, Emily Laltoo, Christina P. Boyle, Yao-Liang Chen, Philip Cook, Corey McMillan, Chih-Chien Tsai, J-J Wang, Yih-Ru Wu, Ysbrand van der Werf, Paul M. Thompson

There is great interest in developing radiological classifiers for diagnosis, staging, and predictive modeling in progressive diseases such as Parkinson's disease (PD), a neurodegenerative disease that is difficult to detect in its early stages.

Multi-Task Learning