Hierarchical manifold learning for regional image analysis

Bhatia KK, Rao A, Price AN, Wolz R, Hajnal JV, Rueckert D (2014)

Publication Type: Journal article

Publication year: 2014

Journal

IEEE Transactions on Medical Imaging Institute of Electrical and Electronics Engineers (IEEE)

Book Volume: 33

Pages Range: 444-461

Article Number: 6646293

Journal Issue: 2

DOI: 10.1109/TMI.2013.2287121

Abstract

We present a novel method of hierarchical manifold learning which aims to automatically discover regional properties of image datasets. While traditional manifold learning methods have become widely used for dimensionality reduction in medical imaging, they suffer from only being able to consider whole images as single data points. We extend conventional techniques by additionally examining local variations, in order to produce spatially-varying manifold embeddings that characterize a given dataset. This involves constructing manifolds in a hierarchy of image patches of increasing granularity, while ensuring consistency between hierarchy levels. We demonstrate the utility of our method in two very different settings: 1) to learn the regional correlations in motion within a sequence of time-resolved MR images of the thoracic cavity; 2) to find discriminative regions of 3-D brain MR images associated with neurodegenerative disease. © 1982-2012 IEEE.

Involved external institutions

Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB) King’s College London GB United Kingdom (GB)

How to cite

APA:

Bhatia, K.K., Rao, A., Price, A.N., Wolz, R., Hajnal, J.V., & Rueckert, D. (2014). Hierarchical manifold learning for regional image analysis. IEEE Transactions on Medical Imaging, 33(2), 444-461. https://doi.org/10.1109/TMI.2013.2287121

MLA:

Bhatia, Kanwal K., et al. "Hierarchical manifold learning for regional image analysis." IEEE Transactions on Medical Imaging 33.2 (2014): 444-461.

BibTeX: Download