Predictive Subnetwork Extraction with Structural Priors for Infant Connectomes
We present a new method to identify anatomical subnetworks of the human white matter connectome that are predictive of neurodevelopmental outcomes. We employ our method on a dataset of 168 preterm infant connectomes, generated from diffusion tensor images (DTI) taken shortly after birth, to discover subnetworks that predict scores of cognitive and motor development at 18 months. Predictive subnetworks are extracted via sparse linear regression with weights on each connectome edge. By enforcing novel backbone network and connectivity based priors, along with a non-negativity constraint, the learned subnetworks are simultaneously anatomically plausible, well connected, positively weighted and reasonably sparse. Compared to other state-of-the-art subnetwork extraction methods, we found that our approach extracts subnetworks that are more integrated, have fewer noisy edges and that are also better predictive of neurodevelopmental outcomes.
We thank NSERC, CIHR (MOP-79262: S.P.M. and MOP-86489: R.E.G.), the Canadian Child Health Clinician Scientist Program and the Michael Smith Foundation for Health Research for their financial support.
- 1.World Health Organization. Preterm birth fact sheet no. 363. http://www.who.int/mediacentre/factsheets/fs363/en/. Accessed 03 Mar 2015
- 6.Brown, C.J., et al.: Prediction of motor function in very preterm infants using connectome features and LSI. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 69–76. Springer, Heidelberg (2015)Google Scholar
- 7.Munsell, B.C., Wee, C.-Y., Keller, S.S., Weber, B., Elger, C., da Silva, L.A.T., Nesland, T., Styner, M., Shen, D., Bonilha, L.: Evaluation of machine learning algorithms for treatment outcome prediction in patients with epilepsy based on structural connectome data. NeuroImage 118, 219–230 (2015)CrossRefGoogle Scholar
- 8.Zhu, D., Shen, D., Jiang, X., Liu, T.: Connectomics signature for characterizaton of MCI and schizophrenia. In: ISBI, pp. 325–328. IEEE (2014)Google Scholar
- 9.Ghanbari, Y., Smith, A.R., Schultz, R.T., Verma, R.: Identifying group discriminative and age regressive sub-nets from DTI-based connectivity via a unified framework of NMF and graph embedding. MIA 18(8), 1337–1348 (2014)Google Scholar
- 10.Li, H., Xue, Z., Ellmore, T.M., Frye, R.E., Wong, S.T.: Identification of faulty DTI-based sub-networks in autism using network regularized SVM. In: Proceedings of ISBI, vol. 6, pp. 550–553 (2012)Google Scholar
- 12.Bayley, N.: Manual for the Bayley Scales of Infant Development, 3rd edn. Harcourt, San Antonio (2006)Google Scholar
- 14.Schmidt, M.: Graphical model structure learning with l1-regularization. Ph.D. thesis, University of British Columbia (Vancouver) 2010Google Scholar
- 18.Bi, J., Bennett, K.P.: Regression error characteristic curves. In: Proceedings of ICML-2003, pp. 43–50 (2003)Google Scholar