Connectomics in NeuroImaging



Program - Sun 13th Oct 2019




CNI will comprise of Keynotes, oral presentations from both the Workshop and Challenge, posters, and prizes from our sponsors.

Schedule CONNECTOMICS IN NEUROIMAGING - WORKSHOP
12:30 - 12:40 Welcome and Opening remarks
12:40 - 13:25 Keynote: Consistent white matter tractography parcellation across the lifespan to study the brain's connections in health and disease
Dr Fan Zhang Laboratory of Mathematics in Imaging, Harvard Medical School, USA

Abstract: Diffusion MRI (dMRI) is the only modality that can non-invasively trace the human brain's white matter connections. dMRI allows the analysis of individual white matter fiber tracts in the brain via a process called tractography, which has been widely used for understanding neurological development, brain function, and brain disease. White matter tract parcellation, i.e. dividing the massive number of tractography fibers into multiple fiber parcels (or fiber fascicles), is the first and essential step to enable tract quantification and visualization. This talk will focus on an introduction to dMRI tractography parcellation and describe our recent work, including computational methods to enable consistent white matter parcellation across the lifespan and tractography analysis of the brain's connections in health and disease.

13:25 - 13:37 Oral 1: Covariance Shrinkage for Dynamic Functional Connectivity
Nicolas Honnorat, Ehsan Adeli, Qingyu Zhao, Adolf Pfefferbaum, Edith V. Sullivan, Kilian Pohl
13:37 - 13.49 Oral 2: Rapid Acceleration of the Permutation Test via Transpositions
Moo Chung, Linhui Xie, Shih-Gu Huang, Yixian Wang, Jingwen Yan, Li Shen
13.49 - 14.01 Oral 3: A Machine Learning Framework for Accurate Functional Connectome Fingerprinting and an Application of a Siamese Network
Ali Shojaee, Kendrick Li, Gowtham Atluri
14.01 - 14:13 Oral 4: Unsupervised Feature Selection via Adaptive Embedding and Sparse Learning for Parkinson’s Disease Diagnosis
Zhongwei Huang, Haijun Lei, Guoliang Chen, Shiqi Li, Hancong Li, Ahmed Elazab, Baiying Lei
14:13 - 14:25 Oral 5: A Novel Graph Neural Network to Localize Eloquent Cortex in Brain Tumor Patients from Resting-State fMRI Connectivity
Naresh Nandakumar, Komal Manzoor, Jay J. Pillai, Sachin K. Gujar, Haris I. Sair, Archana Venkataraman
14:25 - 15:10 Keynote: Developmental Connectomics from Infancy through Early Childhood
Prof. Yong He
Beijing Key Laboratory of Brain Imaging & Connectomics, Beijing Normal University, China

Abstract: The human brain undergoes rapid growth in both structure and function from infancy through early childhood, and this significantly influences cognitive and behavioral development in later life. Developmental connectomics provides unprecedented opportunities for exploring the developing brain through non-invasive mapping of structural and functional connectivity patterns. In this talk, I will describe the methodological framework of developmental connectomics and our recent works in connectome development from infancy to early childhood. Specifically, I will highlight five fundamental principles of brain network development during the critical first years of life, emphasizing strengthened segregation and integration balance, a remarkable hierarchical order from primary to higher-order regions, unparalleled structural and functional maturations, substantial individual variability, and high vulnerability to developmental disorders.

15:10 - 16:00 Posters and Coffee break
CONNECTOMICS IN NEUROIMAGING - TRANSFER LEARNING CHALLENGE
18:00 - 18:30CNI-Transfer Learning Challenge Opening remarks
18:30 - 18:33 Participant 1: Linear support vector machine framework to predict abnormal functional connectivity
Team MEINTERNATIONAL - Hassna Irzan; Michael Hütel, Sebastien Ourselin, Neil Marlow, Andrew Melbourne
18:33 - 18:36Participant 2: Classification ADHD disorder against healthy based on spectra of the normalized Laplacians
Egor Levchenko
18:36 - 18:39Participant 3: Domain Independent SVM for CNI challenge
Shuo Zhou, Mwiza Kunda, Haiping Lu
18:39 - 18:42Participant 4: Ensemble model for CNI Challenge
Shuo Zhou, Mwiza Kunda, Haiping Lu
18:42 - 18:45Participant 5: Learning generalizable recurrent neural networks from small task-fMRI datasets
Nicha C. Dvornek, Juntang Zhuang
18:45 - 19:45CNI-Evaluation & Discussion
19:45 - 20:00Awards and Closing remarks


CNI POSTERS (15:10 - 16:00)
Poster 1: Unsupervised Feature Selection via Adaptive Embedding and Sparse Learning for Parkinson’s Disease Diagnosis
Zhongwei Huang, Haijun Lei, Guoliang Chen, Shiqi Li, Hancong Li, Ahmed Elazab, Baiying Lei
Poster 2: A Novel Graph Neural Network to Localize Eloquent Cortex in Brain Tumor Patients from Resting-State fMRI Connectivity
Naresh Nandakumar, Komal Manzoor, Jay Pillai, Sachin Gujar, Haris Sair, Archana Venkataraman
Poster 3: Graph Morphology-Based Genetic Algorithm for Classifying Late Dementia States
Oumaima Ben Khelifa, Islem Rekik
Poster 4: Covariance Shrinkage for Dynamic Functional Connectivity
Nicolas Honnorat, Ehsan Adeli, Qingyu Zhao, Adolf Pfefferbaum, Edith Sullivan, Kilian Pohl
Poster 5: Rapid Acceleration of the Permutation Test via Transpositions
Moo Chung, Linhui Xie, Shih-Gu Huang, Yixian Wang, Jingwen Yan, Li Shen
Poster 6: Heat Kernels with Functional Connectomes Reveal Atypical Energy Transport in Peripheral Subnetworks in Autism
Markus D. Schirmer, Ai Wern Chung
Poster 7: A Mass Multivariate, Edge-wise Approach for Combining Multiple Connectomes to Improve the Detection of Group Differences
Javid Dadashkarimi, Siyuan Gao, Erin Yeagle, Stephanie Noble, Dustin Scheinost
Poster 8: Adversarial Connectome Embedding for Mild Cognitive Impairment Identification using Cortical Morphological Networks
Alin Banka, Islem Rekik
Poster 9: A Machine Learning Framework for Accurate Functional Connectome Fingerprinting and an Application of a Siamese Network
Ali Shojaee, Kendrick Li, Gowtham Atluri
Poster 10: Test-Retest Reliability of Functional Networks for Evaluation of Data-Driven Parcellation
Jianfeng Zeng, Anh The Dang, Gowtham Atluri
Poster 11: Constraining Disease Progression Models Using Subject Specific Connectivity Priors
Anvar Kurmukov, Yuji Zhao, Ayagoz Mussabaeva, Boris Gutman
Poster 12: Hemodynamic Matrix Factorization for Functional Magnetic Resonance Imaging
Michael Hütel, Michela Antonelli, Jinendra Ekanayake, Sebastien Ourselin, Andrew Melbourne
Poster 13: Network Dependency Index Stratified Subnetwork Analysis of Functional Connectomes: An application to autism
Ai Wern Chung, Markus D. Schirmer


Sponsored Awards



CNI Workshop Best Paper and Poster awards will be sponsored by the International Neuroinformatics Coordinating Facility, INCF!
Each INCF award includes a KeepCup and one free registration to their next NeuroInformatics conference in 2020 for winners who are students or Postdocs that submit and present an abstract. Senior researchers will get a 40% discounted rate. More information on NeuroInformatics 2019 can be found here.
INCF promotes the field of neuroinformatics and aims to advance data reuse and reproducibility in global brain research.



CNI-TLC Best Challenger award will be sponsored by RedHat! The prize will be a "swag-bag" and includes a textbook by Olaf Sporns for all your connectomic inspirational needs.