1
|
Kwon H, Kim JI, Son SY, Jang YH, Kim BN, Lee HJ, Lee JM. Sparse Hierarchical Representation Learning on Functional Brain Networks for Prediction of Autism Severity Levels. Front Neurosci 2022; 16:935431. [PMID: 35873817 PMCID: PMC9301472 DOI: 10.3389/fnins.2022.935431] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2022] [Accepted: 06/13/2022] [Indexed: 11/13/2022] Open
Abstract
Machine learning algorithms have been widely applied in diagnostic tools for autism spectrum disorder (ASD), revealing an altered brain connectivity. However, little is known about whether an magnetic resonance imaging (MRI)-based brain network is related to the severity of ASD symptoms in a large-scale cohort. We propose a graph convolution neural network-based framework that can generate sparse hierarchical graph representations for functional brain connectivity. Instead of assigning initial features for each node, we utilized a feature extractor to derive node features and the extracted representations can be fed to a hierarchical graph self-attention framework to effectively represent the entire graph. By incorporating connectivity embeddings in the feature extractor, we propose adjacency embedding networks to characterize the heterogeneous representations of the brain connectivity. Our proposed model variants outperform the benchmarking model with different configurations of adjacency embedding networks and types of functional connectivity matrices. Using this approach with the best configuration (SHEN atlas for node definition, Tikhonov correlation for connectivity estimation, and identity-adjacency embedding), we were able to predict individual ASD severity levels with a meaningful accuracy: the mean absolute error (MAE) and correlation between predicted and observed ASD severity scores resulted in 0.96, and r = 0.61 (P < 0.0001), respectively. To obtain a better understanding on how to generate better representations, we investigate the relationships between the extracted feature embeddings and the graph theory-based nodal measurements using canonical correlation analysis. Finally, we visualized the model to identify the most contributive functional connections for predicting ASD severity scores.
Collapse
Affiliation(s)
- Hyeokjin Kwon
- Department of Electronic Engineering, Hanyang University, Seoul, South Korea
| | - Johanna Inhyang Kim
- Department of Psychiatry, Hanyang University Medical Center, Seoul, South Korea
| | - Seung-Yeon Son
- Department of Artificial Intelligence, Hanyang University, Seoul, South Korea
| | - Yong Hun Jang
- Department of Pediatrics, Hanyang University College of Medicine, Seoul, South Korea
| | - Bung-Nyun Kim
- Division of Child and Adolescent Psychiatry, Department of Psychiatry, Seoul National University College of Medicine, Seoul, South Korea
| | - Hyun Ju Lee
- Department of Pediatrics, Hanyang University College of Medicine, Seoul, South Korea
| | - Jong-Min Lee
- Department of Biomedical Engineering, Hanyang University, Seoul, South Korea
| |
Collapse
|
3
|
Schirmer MD, Venkataraman A, Rekik I, Kim M, Mostofsky SH, Nebel MB, Rosch K, Seymour K, Crocetti D, Irzan H, Hütel M, Ourselin S, Marlow N, Melbourne A, Levchenko E, Zhou S, Kunda M, Lu H, Dvornek NC, Zhuang J, Pinto G, Samal S, Zhang J, Bernal-Rusiel JL, Pienaar R, Chung AW. Neuropsychiatric disease classification using functional connectomics - results of the connectomics in neuroimaging transfer learning challenge. Med Image Anal 2021; 70:101972. [PMID: 33677261 PMCID: PMC9115580 DOI: 10.1016/j.media.2021.101972] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Revised: 11/25/2020] [Accepted: 01/11/2021] [Indexed: 01/26/2023]
Abstract
Large, open-source datasets, such as the Human Connectome Project and the Autism Brain Imaging Data Exchange, have spurred the development of new and increasingly powerful machine learning approaches for brain connectomics. However, one key question remains: are we capturing biologically relevant and generalizable information about the brain, or are we simply overfitting to the data? To answer this, we organized a scientific challenge, the Connectomics in NeuroImaging Transfer Learning Challenge (CNI-TLC), held in conjunction with MICCAI 2019. CNI-TLC included two classification tasks: (1) diagnosis of Attention-Deficit/Hyperactivity Disorder (ADHD) within a pre-adolescent cohort; and (2) transference of the ADHD model to a related cohort of Autism Spectrum Disorder (ASD) patients with an ADHD comorbidity. In total, 240 resting-state fMRI (rsfMRI) time series averaged according to three standard parcellation atlases, along with clinical diagnosis, were released for training and validation (120 neurotypical controls and 120 ADHD). We also provided Challenge participants with demographic information of age, sex, IQ, and handedness. The second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing. Classification methodologies were submitted in a standardized format as containerized Docker images through ChRIS, an open-source image analysis platform. Utilizing an inclusive approach, we ranked the methods based on 16 metrics: accuracy, area under the curve, F1-score, false discovery rate, false negative rate, false omission rate, false positive rate, geometric mean, informedness, markedness, Matthew's correlation coefficient, negative predictive value, optimized precision, precision, sensitivity, and specificity. The final rank was calculated using the rank product for each participant across all measures. Furthermore, we assessed the calibration curves of each methodology. Five participants submitted their method for evaluation, with one outperforming all other methods in both ADHD and ASD classification. However, further improvements are still needed to reach the clinical translation of functional connectomics. We have kept the CNI-TLC open as a publicly available resource for developing and validating new classification methodologies in the field of connectomics.
Collapse
Affiliation(s)
- Markus D Schirmer
- Massachusetts General Hospital, Harvard Medical School, Boston, USA; German Center for Neurodegenerative Diseases, Bonn, Germany; Clinic for Neuroradiology, University Hospital Bonn, Germany; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA.
| | - Archana Venkataraman
- Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Islem Rekik
- BASIRA lab, Faculty of Computer and Informatics, Istanbul Technical University, Istanbul, Turkey; School of Science and Engineering, Computing, University of Dundee, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Minjeong Kim
- Department of Computer Science, University of North Carolina at Greensboro, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Stewart H Mostofsky
- Center for Neurodevelopmental and Imaging Research, Kennedy Krieger Institute, Baltimore, USA; Department of Neurology, Johns Hopkins School of Medicine, USA; Department of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Mary Beth Nebel
- Center for Neurodevelopmental and Imaging Research, Kennedy Krieger Institute, Baltimore, USA; Department of Neurology, Johns Hopkins School of Medicine, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Keri Rosch
- Center for Neurodevelopmental and Imaging Research, Kennedy Krieger Institute, Baltimore, USA; Department of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA; Department of Radiology, Boston Children's Hospital,Harvard Medical School, Boston, MA, USA
| | - Karen Seymour
- Center for Neurodevelopmental and Imaging Research, Kennedy Krieger Institute, Baltimore, USA; Department of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Deana Crocetti
- Center for Neurodevelopmental and Imaging Research, Kennedy Krieger Institute, Baltimore, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Hassna Irzan
- Department of Medical Physics and Biomedical Engineering, University College London, UK; School of Biomedical Engineering and Imaging Sciences, King's College London, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Michael Hütel
- School of Biomedical Engineering and Imaging Sciences, King's College London, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Sebastien Ourselin
- School of Biomedical Engineering and Imaging Sciences, King's College London, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Neil Marlow
- Institute for Women's Health, University College London, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Andrew Melbourne
- School of Biomedical Engineering and Imaging Sciences, King's College London, UK; Department of Medical Physics and Biomedical Engineering, University College London, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Egor Levchenko
- Institute for Cognitive Neuroscience, Higher School of Economics, Moscow, Russia; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Shuo Zhou
- Department of Computer Science, The University of Sheffield, Sheffield, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Mwiza Kunda
- Department of Computer Science, The University of Sheffield, Sheffield, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Haiping Lu
- Department of Computer Science, The University of Sheffield, Sheffield, UK; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Nicha C Dvornek
- Department of Radiology & Biomedical Imaging, Yale University, New Haven, CT, USA; Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Juntang Zhuang
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Gideon Pinto
- Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Sandip Samal
- Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Jennings Zhang
- Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Jorge L Bernal-Rusiel
- Teradyte LLC, Coral Gables, FL, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Rudolph Pienaar
- Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA; Department of Radiology, Boston Children's Hospital,Harvard Medical School, Boston, MA, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA
| | - Ai Wern Chung
- Fetal-Neonatal Neuroimaging and Developmental Science Center, Division of Newborn Medicine, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA; Department of Pediatrics, Boston Children's Hospital, Harvard Medical School, Boston, MA, USA; Department of Neuropsychology, Kennedy Krieger Institute, Baltimore, USA.
| |
Collapse
|