Abstract
This paper addresses the issue of fusing datasets coming from different imaging protocols or scanners to boost the performance of computer aided diagnostic system. We present novel contributions in the field of subspace alignment methods that are part of domain adaptation framework. We first introduce a simple approach based on scaling the features of the different distribution and accounting for the class information. We also extend an unsupervised landmark based approach that has been recently developed to the supervised setting. These methods are evaluated in the context of prostate cancer screening based on two patient MRI databases acquired on different scanners. We demonstrate promising performance of the scaling based method when both databases contain similar number of annotated samples, and stable performance of the landmark based method even with unbalanced datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hong, S.J.J., Kim, H., Schrader, D., Bernasconi, N., Bernhardt, B.C., Bernasconi, A.: Automated detection of cortical dysplasia type II in MRI-negative epilepsy. Neurology 83(1), 48–55 (2014)
Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: Proceedings of the 15th International Conference on Multimedia, Multimedia 2007, pp. 188–197. ACM, New York (2007)
Lehaire, J., Flamary, R., Rouviere, O., Lartizien, C.: Computer-aided diagnostic system for prostate cancer detection and characterization combining learned dictionaries and supervised classification. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 2251–2255. IEEE, October 2014
Niaf, E., Rouvière, O., Mège-Lechevallier, F., Bratan, F., Lartizien, C.: Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI. Phys. Med. Biol. 57(12), 3833–3851 (2012)
van Opbroek, A., Ikram, M.A., Vernooij, M.W., de Bruijne, M.: Transfer learning improves supervised image segmentation across imaging protocols. IEEE Trans. Med. Imaging 34(5), 1018–1030 (2015)
Becker, C., Christoudias, C.M., Fua, P.: Domain adaptation for microscopy imaging. IEEE Trans. Med. Imaging 34(5), 1125–1139 (2015)
Guerrero, R., Ledig, C., Rueckert, D.: Manifold alignment and transfer learning for classification of Alzheimer’s disease. In: Wu, G., Zhang, D., Zhou, L. (eds.) MLMI 2014. LNCS, vol. 8679, pp. 77–84. Springer, Heidelberg (2014)
Jie, B., Zhang, D., Cheng, B., Shen, D.: Manifold regularized multi-task feature selection for multi-modality classification in Alzheimer’s disease. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol. 8149, pp. 275–283. Springer, Heidelberg (2013)
Daumé, H.: Frustratingly easy domain adaptation. CoRR arXiv preprint arXiv:0907.1815 (2009)
Wang, C.: A geometric framework for transfer learning using manifold alignment. Ph.D. thesis (2010)
Wu, P., Dietterich, T.G.: Improving svm accuracy by training on auxiliary data sources. In: Proceedings of the Twenty-first International Conference on Machine Learning, ICML 2004, p. 110. ACM, New York (2004)
Aljundi, R., Emonet, R., Muselet, D., Sebban, M.: Landmarks-based kernelized subspace alignment for unsupervised domain adaptation, June 2015
Rakotomamonjy, A.: Variable selection using svm based criteria. J. Mach. Learn. Res. 3, 1357–1370 (2003)
Bratan, F., Niaf, E., Melodelima, C., Chesnais, A.L.L., Souchon, R., Mège-Lechevallier, F., Colombel, M., Rouvière, O.: Influence of imaging and histological factors on prostate cancer detection and localisation on multiparametric MRI: a prospective study. Eur. Radiol. 23(7), 2019–2029 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Aljundi, R., Lehaire, J., Prost-Boucle, F., Rouvière, O., Lartizien, C. (2015). Transfer Learning for Prostate Cancer Mapping Based on Multicentric MR Imaging Databases. In: Bhatia, K., Lombaert, H. (eds) Machine Learning Meets Medical Imaging. MLMMI 2015. Lecture Notes in Computer Science(), vol 9487. Springer, Cham. https://doi.org/10.1007/978-3-319-27929-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-27929-9_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27928-2
Online ISBN: 978-3-319-27929-9
eBook Packages: Computer ScienceComputer Science (R0)