A Large-Scale Manifold Learning Approach for Brain Tumor Progression Prediction
We present a novel manifold learning approach to efficiently identify low-dimensional structures, known as manifolds, embedded in large-scale, high dimensional MRI datasets for brain tumor growth prediction. The datasets consist of a series of MRI scans for three patients with tumor and progressed regions identified. We attempt to identify low dimensional manifolds for tumor, progressed and normal tissues, and most importantly, to verify if the progression manifold exists - the bridge between tumor and normal manifolds. By mapping the bridge manifold back to MRI image space, this method has the potential to predict tumor progression, thereby, greatly benefiting patient management. Preliminary results supported our hypothesis: normal and tumor manifolds are well separated in a low dimensional space and the progressed manifold is found to lie roughly between them but closer to the tumor manifold.
KeywordsDiffusion Tensor Imaging Tumor Region Locally Linear Embedding Fisher Score Nonlinear Dimensionality Reduction
Unable to display preview. Download preview PDF.
- 3.Deshpande, A., Rademacher, L., et al.: Matrix approximation and projective clustering via Volume Sampling. In: Symposium on Discrete Algorithms, vol. (2), pp. 225–247 (2006)Google Scholar
- 6.Silva, V., Tenenbaum, J.B.: Global Versus Local Methods in Nonlinear Dimensionality Reduction. In: NIPS, vol. 15, pp. 721–728 (2003)Google Scholar
- 13.Hartkens, T., Ruechert, D., et al.: VTK CISG Registration Toolkit: An open source software package for affine and non-rigid registration of single- and multimodal 3D images. In: Workshop Bildverarbeitung fur die Medizin, pp. 409–412 (2002)Google Scholar
- 14.Duda, R., Hart, P.: Pattern Classification and Scene Analysis, pp. 114–129 (1973)Google Scholar