Author:
Thottupattu Alphin J.,Sivaswamy Jayanthi,Krishnan Venkateswaran P.
Abstract
AbstractNormative aging trends of the brain can serve as an important reference in the assessment of neurological structural disorders. Such models are typically developed from longitudinal brain image data—follow-up data of the same subject over different time points. In practice, obtaining such longitudinal data is difficult. We propose a method to develop an aging model for a given population, in the absence of longitudinal data, by using images from different subjects at different time points, the so-called cross-sectional data. We define an aging model as a diffeomorphic deformation on a structural template derived from the data and propose a method that develops topology preserving aging model close to natural aging. The proposed model is successfully validated on two public cross-sectional datasets which provide templates constructed from different sets of subjects at different age points.
Publisher
Springer Science and Business Media LLC
Reference43 articles.
1. Sedgwick, P. Cross sectional studies: Advantages and disadvantages. BMJ 348, g2276. https://doi.org/10.1136/bmj.g2276 (2014).
2. Ziegler, G. Models of the aging brain structure and individual decline. Front. Neuroinform. 6, 3. https://doi.org/10.3389/fninf.2012.00003 (2012).
3. Miller, M. I. Computational anatomy: Shape, growth, and atrophy comparison via diffeomorphisms. Neuroimage 23, S19–S33. https://doi.org/10.1016/j.neuroimage.2004.07.021 (2004).
4. Fishbaugh, J. & Gerig, G. Acceleration controlled diffeomorphisms for nonparametric image regression. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 1488–1491. https://doi.org/10.1109/ISBI.2019.8759583 (2019).
5. Chevallier, J., Oudard, S. & Allassonnière, S. Learning spatiotemporal piecewise-geodesic trajectories from longitudinal manifold-valued data. InNeural Information Processing Systems, Vol. 2017 (2017).