Advertisement

Progressive Infant Brain Connectivity Evolution Prediction from Neonatal MRI Using Bidirectionally Supervised Sample Selection

  • Olfa Ghribi
  • Gang Li
  • Weili Lin
  • Dinggang Shen
  • Islem RekikEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11843)

Abstract

The early postnatal developmental period is highly dynamic, where brain connections undergo both growth and pruning processes. Understanding typical brain connectivity evolution would enable us to spot abnormal connectional development patterns. However, this generally requires the acquisition of longitudinal neuroimaging datasets that densely cover the first years of postnatal development. This might not be easily investigated since neonatal follow-up scans are rarely acquired in a clinical setting. Furthermore, waiting for the acquisition of later brain scans would hinder early neurodevelopmental disorder diagnosis. To solve this problem, we unprecedentedly propose a bidirectionally supervised sample selection framework, while leveraging the time-dependency between consecutive observations, for predicting neonatal brain connectome evolution from a single structural magnetic resonance imaging (MRI) acquired around birth. Specifically, we propose to learn how to select the best training samples by supervisedly training a bidirectional ensemble of regressors from the space of pairwise neonatal connectome disparities to their expected prediction scores resulting from using one training connectome to predict another training connectome. The proposed supervised ensemble learning is time-dependent and has a recall memory anchored at the ground truth baseline observation, allowing to progressively pass over previous predictions through the connectome evolution trajectory. We then rank training samples at current timepoint \(t_{i-1}\) based on their expected prediction scores by the ensemble and average their connectomes at follow-up timepoint \(t_{i}\) to predict the testing connectome at \(t_{i}\). Our framework significantly outperformed comparison methods in leave-one-out cross-validation.

References

  1. 1.
    Hazlett, H.C., et al.: Early brain development in infants at high risk for autism spectrum disorder. Nature 542, 348 (2017)CrossRefGoogle Scholar
  2. 2.
    Meng, Y., Li, G., Gao, Y., Lin, W., Shen, D.: Learning-based subject-specific estimation of dynamic maps of cortical morphology at missing time points in longitudinal infant studies. Hum. Brain Mapp. 37, 4129–4147 (2016)CrossRefGoogle Scholar
  3. 3.
    Dean III, D.C., et al.: Estimating the age of healthy infants from quantitative myelin water fraction maps. Hum. Brain Mapp. 36, 1233–1244 (2015)CrossRefGoogle Scholar
  4. 4.
    Howell, B.R., et al.: The UNC/UMN baby connectome project (BCP): an overview of the study design and protocol development. NeuroImage 185, 891–905 (2019)CrossRefGoogle Scholar
  5. 5.
    Rekik, I., Li, G., Lin, W., Shen, D.: Predicting infant cortical surface development using a 4D varifold-based learning framework and local topography-based shape morphing. Med. Image Anal. 28, 1–12 (2016)CrossRefGoogle Scholar
  6. 6.
    Rekik, I., Li, G., Yap, P.T., Chen, G., Lin, W., Shen, D.: Joint prediction of longitudinal development of cortical surfaces and white matter fibers from neonatal MRI. NeuroImage 152, 411–424 (2017)CrossRefGoogle Scholar
  7. 7.
    Rekik, I., Li, G., Wu, G., Lin, W., Shen, D.: Prediction of infant MRI appearance and anatomical structure evolution using sparse patch-based metamorphosis learning framework. In: Wu, G., Coupé, P., Zhan, Y., Munsell, B., Rueckert, D. (eds.) Patch-MI 2015. LNCS, vol. 9467, pp. 197–204. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-28194-0_24CrossRefGoogle Scholar
  8. 8.
    Li, G., Wang, L., Shi, F., Lin, W., et al.: Simultaneous and consistent labeling of longitudinal dynamic developing cortical surfaces in infants. Med. Image Anal. 18, 1274–1289 (2014)CrossRefGoogle Scholar
  9. 9.
    Rekik, I., Li, G., Lin, W., Shen, D.: Estimation of brain network atlases using diffusive-shrinking graphs: application to developing brains. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 385–397. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-59050-9_31CrossRefGoogle Scholar
  10. 10.
    Dhifallah, S., Rekik, I., Alzheimer’s Disease Neuroimaging Initiative and others: Clustering-based multi-view network fusion for estimating brain network atlases of healthy and disordered populations. J. Neurosci. Methods 311, 426–435 (2019)CrossRefGoogle Scholar
  11. 11.
    Gafuroğlu, C., Rekik, I., Authorinst for the Alzheimer’s Disease Neuroimaging Initiative: Joint Prediction and Classification of Brain Image Evolution Trajectories from Baseline Brain Image with Application to Early Dementia. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 437–445. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00931-1_50CrossRefGoogle Scholar
  12. 12.
    Gafuroğlu, C., Rekik, I.: Image evolution trajectory prediction and classification from baseline using learning-based patch atlas selection for early diagnosis. arXiv preprint arXiv:1907.06064 (2019)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Olfa Ghribi
    • 1
    • 2
  • Gang Li
    • 3
  • Weili Lin
    • 3
  • Dinggang Shen
    • 3
  • Islem Rekik
    • 2
    Email author
  1. 1.BASIRA Lab, Faculty of Computer and InformaticsIstanbul Technical UniversityIstanbulTurkey
  2. 2.National School of Engineering of SfaxUniversity of SfaxSfaxTunisia
  3. 3.Department of Radiology and BRICUniversity of North Carolina at Chapel HillChapel HillUSA

Personalised recommendations