Segmentation of Infant Hippocampus Using Common Feature Representations Learned for Multimodal Longitudinal Data
Aberrant development of the human brain during the first year after birth is known to cause critical implications in later stages of life. In particular, neuropsychiatric disorders, such as attention deficit hyperactivity disorder (ADHD), have been linked with abnormal early development of the hippocampus. Despite its known importance, studying the hippocampus in infant subjects is very challenging due to the significantly smaller brain size, dynamically varying image contrast, and large across-subject variation. In this paper, we present a novel method for effective hippocampus segmentation by using a multi-atlas approach that integrates the complementary multimodal information from longitudinal T1 and T2 MR images. In particular, considering the highly heterogeneous nature of the longitudinal data, we propose to learn their common feature representations by using hierarchical multi-set kernel canonical correlation analysis (CCA). Specifically, we will learn (1) within-time-point common features by projecting different modality features of each time point to its own modality-free common space, and (2) across-time-point common features by mapping all time-point-specific common features to a global common space for all time points. These final features are then employed in patch matching across different modalities and time points for hippocampus segmentation, via label propagation and fusion. Experimental results demonstrate the improved performance of our method over the state-of-the-art methods.
Unable to display preview. Download preview PDF.
- 2.Li, J., Jin, Y., Shi, Y., Dinov, I.D., Wang, D.J., Toga, A.W., Thompson, P.M.: Voxelwise spectral diffusional connectivity and Its applications to alzheimer’s disease and intelligence prediction. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part I. LNCS, vol. 8149, pp. 655–662. Springer, Heidelberg (2013)CrossRefGoogle Scholar
- 3.Cohen, D.J.: Developmental Psychopathology, 2nd edn. Developmental Neuroscience, vol. 2. Wiley (2006)Google Scholar
- 10.Arora, R., Livescu, K.: Kernel CCA for Multi-view Acoustic Feature Learning using Articulatory Measurements. In: Proceedings of the MLSLP (2012)Google Scholar
- 12.Munoz-Mari, J., et al.: Multiset Kernel CCA for Multitemporal Image Classification. In: MultiTemp 2013, pp. 1–4 (2013)Google Scholar
- 15.Liu, J., et al.: SLEP: Sparse Learning with Efficient Projections. Arizona State University (2009), http://www.public.asu.edu/~jye02/Software/SLEP