Abstract
A new automatic method for multiple sclerosis (MS) lesion segmentation in multi-channel 3D MR images is presented. The main novelty of the method is that it learns the spatial image features needed for training a supervised classifier entirely from unlabeled data. This is in contrast to other current supervised methods, which typically require the user to preselect or design the features to be used. Our method can learn an extensive set of image features with minimal user effort and bias. In addition, by separating the feature learning from the classifier training that uses labeled (pre-segmented data), the feature learning can take advantage of the typically much more available unlabeled data. Our method uses deep learning for feature learning and a random forest for supervised classification, but potentially any supervised classifier can be used. Quantitative validation is carried out using 1450 T2-weighted and PD-weighted pairs of MRIs of MS patients, with 1400 pairs used for feature learning (100 of those for labeled training), and 50 for testing. The results demonstrate that the learned features are highly competitive with hand-crafted features in terms of segmentation accuracy, and that segmentation performance increases with the amount of unlabeled data used, even when the number of labeled images is fixed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
GarcÃa-Lorenzo, et al.: Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Med. Image Anal. 17(1), 1–18 (2013)
Geremia, E., et al.: Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. NeuroImage 57(2), 378–390 (2011)
Morra, J., et al.: Automatic segmentation of MS lesions using a contextual model for the MICCAI grand challenge. In: MS Lesion Segmentation Challenge (MICCAI Workshop), pp. 1–7 (2008)
Shiee, N., et al.: A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions. NeuroImage 49(2), 1524–1535 (2010)
Montillo, A., Shotton, J., Winn, J., Iglesias, J.E., Metaxas, D., Criminisi, A.: Entangled decision forests and their application for semantic segmentation of CT images. In: Székely, G., Hahn, H.K. (eds.) IPMI 2011. LNCS, vol. 6801, pp. 184–196. Springer, Heidelberg (2011)
Yaqub, M., Javaid, M.K., Cooper, C., Noble, J.A.: Improving the classification accuracy of the classic RF method by intelligent feature selection and weighted voting of trees with application to medical image segmentation. In: Suzuki, K., Wang, F., Shen, D., Yan, P. (eds.) MLMI 2011. LNCS, vol. 7009, pp. 184–192. Springer, Heidelberg (2011)
Sled, J.G., et al.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE T. Med. Imaging 17(1), 87–97 (1998)
Smith, S.M.: Fast robust automated brain extraction. Human Brain Mapping 17(3), 143–155 (2002)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. University of Toronto, Tech. Rep. (2009)
Hinton, G.: A practical guide to training restricted Boltzmann machines. University of Toronto, Tech. Rep. (2010)
Hinton, G., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)
Weiss, N., Rueckert, D., Rao, A.: Multiple sclerosis lesion segmentation using dictionary learning and sparse coding. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol. 8149, pp. 735–742. Springer, Heidelberg (2013)
Souplet, J.C., et al.: An automatic segmentation of T2-FLAIR multiple sclerosis lesions. In: MS Lesion Segmentation Challenge, MICCAI Workshop (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Yoo, Y., Brosch, T., Traboulsee, A., Li, D.K.B., Tam, R. (2014). Deep Learning of Image Features from Unlabeled Data for Multiple Sclerosis Lesion Segmentation. In: Wu, G., Zhang, D., Zhou, L. (eds) Machine Learning in Medical Imaging. MLMI 2014. Lecture Notes in Computer Science, vol 8679. Springer, Cham. https://doi.org/10.1007/978-3-319-10581-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-10581-9_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10580-2
Online ISBN: 978-3-319-10581-9
eBook Packages: Computer ScienceComputer Science (R0)