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. Here we leverage severity-based meta-data on the stages of disease to define a curriculum for training a deep convolutional neural network (CNN). Typically, deep learning networks are trained by randomly selecting samples in each mini-batch. By contrast, curriculum learning is a training strategy that aims to boost classifier performance by starting with examples that are easier to classify. Here we define a curriculum to progressively increase the difficulty of the training data corresponding to the Hoehn and Yahr (H&Y) staging system for PD (total N=1,012; 653 PD patients, 359 controls; age range: 20.0-84.9 years). Even with our multi-task setting using pre-trained CNNs and transfer learning, PD classification based on T1-weighted (T1-w) MRI was challenging (ROC AUC: 0.59-0.65), but curriculum training boosted performance (by 3.9%) compared to our baseline model. Future work with multimodal imaging may further boost performance.
@article{arxiv.2302.13631,
title = {Curriculum Based Multi-Task Learning for Parkinson's Disease Detection},
author = {Nikhil J. Dhinagar and Conor Owens-Walton and Emily Laltoo and Christina P. Boyle and Yao-Liang Chen and Philip Cook and Corey McMillan and Chih-Chien Tsai and J-J Wang and Yih-Ru Wu and Ysbrand van der Werf and Paul M. Thompson},
journal= {arXiv preprint arXiv:2302.13631},
year = {2023}
}
Comments
Accepted for publication at the 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023