Improved multi-site Parkinson’s disease classification using neuroimaging data with counterfactual inference

Vibujithan Vigneshwaran, Matthias Wilms, Milton Ivan Camacho Camacho, Raissa Souza, Nils Forkert
Medical Imaging with Deep Learning, PMLR 227:1304-1317, 2024.

Abstract

Deep learning has led to many advances in medical image analysis for various clinical problems. However, most deep learning models are known to be sensitive to differences in the training and test data distributions, which can lead to a decrease in accuracy when applied in real-life scenarios. Thus far, various techniques have been developed to tackle this problem, primarily focusing on harmonizing feature representations from different datasets. Due to the recent increased interest in causal approaches in deep learning, explainable harmonization techniques have gained momentum lately but have not been applied broadly yet. Our study proposes a causal flow-based technique to overcome the problem of different feature distributions in multi-site data used for Parkinson’s disease (PD) classification. Feature distributions from six different sites, with a total of 415 subjects (PD: 263, healthy controls: 152), were used for the experiments. A counterfactual approach to answer the question, How would brain MRI features appear if they were obtained at a different site?" was developed using a causal normalizing flow. When tested on features from a previously unseen site, the counterfactual-based classifier demonstrated superior performance (weighted f1 = 0.68) compared to a classifier trained on purely observational data (weighted f1 = 0.36) and improved accuracy compared to a harmonization technique typically used in neurological settings (weighted f1 = 0.5). These results show that the proposed technique can effectively correct differences in multi-site feature distributions to facilitate generalizable deep-learning models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v227-vigneshwaran24a, title = {Improved multi-site Parkinson’s disease classification using neuroimaging data with counterfactual inference}, author = {Vigneshwaran, Vibujithan and Wilms, Matthias and Camacho, Milton Ivan Camacho and Souza, Raissa and Forkert, Nils}, booktitle = {Medical Imaging with Deep Learning}, pages = {1304--1317}, year = {2024}, editor = {Oguz, Ipek and Noble, Jack and Li, Xiaoxiao and Styner, Martin and Baumgartner, Christian and Rusu, Mirabela and Heinmann, Tobias and Kontos, Despina and Landman, Bennett and Dawant, Benoit}, volume = {227}, series = {Proceedings of Machine Learning Research}, month = {10--12 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v227/vigneshwaran24a/vigneshwaran24a.pdf}, url = {https://proceedings.mlr.press/v227/vigneshwaran24a.html}, abstract = {Deep learning has led to many advances in medical image analysis for various clinical problems. However, most deep learning models are known to be sensitive to differences in the training and test data distributions, which can lead to a decrease in accuracy when applied in real-life scenarios. Thus far, various techniques have been developed to tackle this problem, primarily focusing on harmonizing feature representations from different datasets. Due to the recent increased interest in causal approaches in deep learning, explainable harmonization techniques have gained momentum lately but have not been applied broadly yet. Our study proposes a causal flow-based technique to overcome the problem of different feature distributions in multi-site data used for Parkinson’s disease (PD) classification. Feature distributions from six different sites, with a total of 415 subjects (PD: 263, healthy controls: 152), were used for the experiments. A counterfactual approach to answer the question, How would brain MRI features appear if they were obtained at a different site?" was developed using a causal normalizing flow. When tested on features from a previously unseen site, the counterfactual-based classifier demonstrated superior performance (weighted f1 = 0.68) compared to a classifier trained on purely observational data (weighted f1 = 0.36) and improved accuracy compared to a harmonization technique typically used in neurological settings (weighted f1 = 0.5). These results show that the proposed technique can effectively correct differences in multi-site feature distributions to facilitate generalizable deep-learning models.} }
Endnote
%0 Conference Paper %T Improved multi-site Parkinson’s disease classification using neuroimaging data with counterfactual inference %A Vibujithan Vigneshwaran %A Matthias Wilms %A Milton Ivan Camacho Camacho %A Raissa Souza %A Nils Forkert %B Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ipek Oguz %E Jack Noble %E Xiaoxiao Li %E Martin Styner %E Christian Baumgartner %E Mirabela Rusu %E Tobias Heinmann %E Despina Kontos %E Bennett Landman %E Benoit Dawant %F pmlr-v227-vigneshwaran24a %I PMLR %P 1304--1317 %U https://proceedings.mlr.press/v227/vigneshwaran24a.html %V 227 %X Deep learning has led to many advances in medical image analysis for various clinical problems. However, most deep learning models are known to be sensitive to differences in the training and test data distributions, which can lead to a decrease in accuracy when applied in real-life scenarios. Thus far, various techniques have been developed to tackle this problem, primarily focusing on harmonizing feature representations from different datasets. Due to the recent increased interest in causal approaches in deep learning, explainable harmonization techniques have gained momentum lately but have not been applied broadly yet. Our study proposes a causal flow-based technique to overcome the problem of different feature distributions in multi-site data used for Parkinson’s disease (PD) classification. Feature distributions from six different sites, with a total of 415 subjects (PD: 263, healthy controls: 152), were used for the experiments. A counterfactual approach to answer the question, How would brain MRI features appear if they were obtained at a different site?" was developed using a causal normalizing flow. When tested on features from a previously unseen site, the counterfactual-based classifier demonstrated superior performance (weighted f1 = 0.68) compared to a classifier trained on purely observational data (weighted f1 = 0.36) and improved accuracy compared to a harmonization technique typically used in neurological settings (weighted f1 = 0.5). These results show that the proposed technique can effectively correct differences in multi-site feature distributions to facilitate generalizable deep-learning models.
APA
Vigneshwaran, V., Wilms, M., Camacho, M.I.C., Souza, R. & Forkert, N.. (2024). Improved multi-site Parkinson’s disease classification using neuroimaging data with counterfactual inference. Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 227:1304-1317 Available from https://proceedings.mlr.press/v227/vigneshwaran24a.html.

Related Material