Modeling 4D Changes in Pathological Anatomy Using Domain Adaptation: Analysis of TBI Imaging Using a Tumor Database
- 1.5k Downloads
Analysis of 4D medical images presenting pathology (i.e., lesions) is significantly challenging due to the presence of complex changes over time. Image analysis methods for 4D images with lesions need to account for changes in brain structures due to deformation, as well as the formation and deletion of new structures (e.g., edema, bleeding) due to the physiological processes associated with damage, intervention, and recovery. We propose a novel framework that models 4D changes in pathological anatomy across time, and provides explicit mapping from a healthy template to subjects with pathology. Moreover, our framework uses transfer learning to leverage rich information from a known source domain, where we have a collection of completely segmented images, to yield effective appearance models for the input target domain. The automatic 4D segmentation method uses a novel domain adaptation technique for generative kernel density models to transfer information between different domains, resulting in a fully automatic method that requires no user interaction. We demonstrate the effectiveness of our novel approach with the analysis of 4D images of traumatic brain injury (TBI), using a synthetic tumor database as the source domain.
Unable to display preview. Download preview PDF.
- 1.Beijbom, O.: Domain adaptations for computer vision applications. Tech. rep., University of California San Diego, arXiv:1211.4860 (April 2012)Google Scholar
- 3.Faul, M., Xu, L., Wald, M., Coronado, V.: Traumatic brain injury in the United States: Emergency department visits, hospitalizations and deaths, 2002-2006. CDC, National Center for Injury Prevention and Control, Atlanta, GA (2010)Google Scholar
- 4.Irimia, A., Wang, B., Aylward, S., Prastawa, M., Pace, D., Gerig, G., Hovda, D., Kikinis, R., Vespa, P., Van Horn, J.: Neuroimaging of structural pathology and connectomics in traumatic brain injury: Toward personalized outcome prediction. NeuroImage: Clinical 1(1), 1–17 (2012)CrossRefGoogle Scholar
- 8.Pele, O., Werman, M.: Fast and robust earth mover’s distances. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 460–467. IEEE (2009)Google Scholar
- 10.Prastawa, M., Awate, S., Gerig, G.: Building spatiotemporal anatomical models using joint 4-D segmentation, registration, and subject-specific atlas estimation. In: 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA), pp. 49–56. IEEE (2012)Google Scholar
- 12.Sugiyama, M., Nakajima, S., Kashima, H., Von Buenau, P., Kawanabe, M.: Direct importance estimation with model selection and its application to covariate shift adaptation. In: Advances in Neural Information Processing Systems, vol. 20, pp. 1433–1440 (2008)Google Scholar
- 14.Wang, B., Prastawa, M., Awate, S., Irimia, A., Chambers, M., Vespa, P., van Horn, J., Gerig, G.: Segmentation of serial MRI of TBI patients using personalized atlas construction and topological change estimation. In: 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1152–1155 (2012)Google Scholar