Transfer learning on structural brain age models to decode cognition in MS: a federated learning approach
Denissen, S.; Grothe, M.; Vaneckova, M.; Uher, T.; Laton, J.; Kudrna, M.; Horakova, D.; Kirsch, M.; Motyl, J.; De Vos, M.; Chen, O. Y.; Van Schependom, J.; Sima, D. M.; Nagels, G.
Show abstract
BackgroundFederated learning (FL) could boost deep learning in neuroimaging but is rarely deployed in a real-world scenario, where its true potential lies. Here, we propose FLightcase, a new FL toolbox tailored for brain research. We tested FLightcase on a real-world FL network to predict the cognitive status of patients with multiple sclerosis (MS) from brain magnetic resonance imaging (MRI). MethodsWe first trained a DenseNet neural network to predict age from T1-weighted brain MRI on three open-source datasets, IXI (586 images), SALD (491 images) and CamCAN (653 images). These were distributed across the three centres in our FL network, Brussels (BE), Greifswald (DE) and Prague (CZ). We benchmarked this federated model with a centralised version. The best-performing brain age model was then fine-tuned to predict performance on the Symbol Digit Modalities Test (SDMT) of patients with MS (Brussels: 96 images, Greifswald: 756 images, Prague: 2424 images). Shallow transfer learning (TL) was compared with deep transfer learning, updating weights in the last layer or the entire network respectively. ResultsCentralised training outperformed federated training, predicting age with a mean absolute error (MAE) of 6.00 versus 9.02. Federated training yielded a Pearson correlation (all p < .001) between true and predicted age of .78 (IXI, Brussels), .78 (SALD, Greifswald) and .86 (CamCAN, Prague). Fine-tuning of the centralised model to SDMT was most successful with a deep TL paradigm (MAE = 9.12) compared to shallow TL (MAE = 14.08), and respectively on Brussels, Greifswald and Prague predicted SDMT with an MAE of 11.50, 9.64 and 8.86, and a Pearson correlation between true and predicted SDMT of .10 (p = .668), .42 (p < .001) and .51 (p < .001). ConclusionReal-world federated learning using FLightcase is feasible for neuroimaging research in MS, enabling access to a large MS imaging database without sharing this data. The federated SDMT-decoding model is promising and could be improved in the future by adopting FL algorithms that address the non-IID data issue and consider other imaging modalities. We hope our detailed real-world experiments and open-source distribution of FLightcase will prompt researchers to move beyond simulated FL environments.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Machine-learning-based prediction of disability progression in multiple sclerosis: an observational, international, multi-center study 94%
- Enhancing Fairness in Disease Prediction by Optimizing Multiple Domain Adversarial Networks 91%
- Uncovering the effects of model initialization on deep model generalization: A study with adult and pediatric chest X-ray images 90%
Similar papers in this journal
Similar papers in this journal
- Estimated connectivity networks outperform observed connectivity networks when classifying people with multiple sclerosis into disability groups 93%
- Stable Biomarker Identification For Predicting Schizophrenia in the Human Connectome 92%
- LST-AI: a Deep Learning Ensemble for Accurate MS Lesion Segmentation 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.