An augmentation strategy to mimic multi-scanner variability in MRI
Abstract
Most publicly available brain MRI datasets are very homogeneous in terms of scanner and protocols, and it is difficult for models that learn from such data to generalize to multi-center and multi-scanner data. We propose a novel data augmentation approach with the aim of approximating the variability in terms of intensities and contrasts present in real world clinical data. We use a Gaussian Mixture Model based approach to change tissue intensities individually, producing new contrasts while preserving anatomical information. We train a deep learning model on a single scanner dataset and evaluate it on a multi-center and multi-scanner dataset. The proposed approach improves the generalization capability of the model to other scanners not present in the training data.
Keywords
Cite
@article{arxiv.2103.12595,
title = {An augmentation strategy to mimic multi-scanner variability in MRI},
author = {Maria Ines Meyer and Ezequiel de la Rosa and Nuno Barros and Roberto Paolella and Koen Van Leemput and Diana M. Sima},
journal= {arXiv preprint arXiv:2103.12595},
year = {2021}
}
Comments
5 pages, 2 figures. accepted for presentation at the International Symposium on Biomedical Imaging (ISBI) 2021. Code available at https://github.com/icometrix/gmm-augmentation