Zusammenfassung
Training deep learning networks is very data intensive. Especially in fields with a very limited number of annotated datasets, such as diffusion MRI, it is of great importance to develop approaches that can cope with a limited amount of data. It was previously shown that transfer learning can lead to better results and more stable training in various medical applications. However, the use of off-the-shelf transfer learning tools in high angular resolution diffusion MRI is not straightforward, as such 3D approaches are commonly designed for scalar data. Here, an extension of self-supervised pretraining to diffusion MRI data is presented, and enhanced with a modality-specific procedure, where artifacts encountered in diffusion MRI need to be removed. We pretrained on publicly available data from the Human Connectome Project and evaluated the success on data from a local hospital with three modality-related experiments: segmentation of brain microstructure, detection of fiber crossings, and regression of nerve fiber spatial orientation. The results were compared against a setting without pretraining, and against classical autoencoder pretraining. We find that it is possible to achieve both improved metrics and a more stable training with the proposed diffusion MRI specific pretraining procedure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literatur
Descoteaux M. High angular resolution diffusion imaging (HARDI).Wiley Encyclopedia of Electrical and Electronics Engineering. American Cancer Society, 2015:1–25.
Zhou Z, Sodha V, Pang J, Gotway MB, Liang J. Models genesis. Med Image Anal. 2021;67:101840.
Taleb A, Loetzsch W, Danz N, Severin J, Gaertner T, Bergner B et al. 3D self-supervised methods for medical imaging. NeurIPS. Vol. 33. Curran Associates, Inc., 2020:18158–72.
Li Y, Qin Y, Liu Z, Ye C. Pretraining improves deep learning based tissue microstructure estimation. MICCAI CDMRI. Springer, 2021:173–85.
van Essen DC, Smith SM, Barch DM, Behrens TEJ, Yacoub E, Ugurbil K. The WU-Minn human connectome project: an overview. NeuroImage. 2013;80:62–79.
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. MICCAI. Springer, 2015:234–41.
Pérez-García F, Sparks R, Ourselin S. TorchIO: a python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput Methods Programs Biomed. 2021;208:106236.
Andersson JL. Chapter 4 - geometric distortions in diffusion MRI. Diffusion MRI (Second Edition). Ed. by Johansen-Berg H, Behrens TE. Second Edition. Academic Press, 2014:63–85.
Zhang Y, Brady M, Smith S. Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans Med Imaging. 2001;20(1):45–57.
Tournier JD, Calamante F, Connelly A. Robust determination of the fibre orientation distribution in diffusion MRI: non-negativity constrained super-resolved spherical deconvolution. NeuroImage. 2007;35(4):1459–72.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Weninger, L., Ecke, J., Na, CH., Jütten, K., Merhof, D. (2022). Diffusion MRI Specific Pretraining by Self-supervision on an Auxiliary Dataset. In: Maier-Hein, K., Deserno, T.M., Handels, H., Maier, A., Palm, C., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2022. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-36932-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-658-36932-3_32
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-36931-6
Online ISBN: 978-3-658-36932-3
eBook Packages: Computer Science and Engineering (German Language)