ConCeptCNN: A novel multi‐filter convolutional neural network for the prediction of neurodevelopmental disorders using brain connectome

• Published in: Medical physics (Lancaster) Vol. 49; no. 5; pp. 3171 - 3184
• Main Authors: Chen, Ming, Li, Hailong, Fan, Howard, Dillman, Jonathan R., Wang, Hui, Altaye, Mekibib, Zhang, Bin, Parikh, Nehal A., He, Lili
• Format: Journal Article
• Language: English
• Published: United States 01-05-2022
• Subjects: Adolescent; Brain - diagnostic imaging; brain connectome; Connectome - methods; convolutional neural network; deep learning; Humans; Infant; Infant, Newborn; Infant, Premature; medical image analysis; MRI; Neural Networks, Computer; Neurodevelopmental Disorders - diagnostic imaging; deep learning; brain connectome; MRI; convolutional neural network; medical image analysis
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1002/mp.15545

Background
Deep convolutional neural network (CNN) and its derivatives have recently shown great promise in the prediction of brain disorders using brain connectome data. Existing deep CNN methods using single global row and column convolutional filters have limited ability to extract discriminative information from brain connectome for prediction tasks.
Purpose
This paper presents a novel deep Connectome–Inception CNN (ConCeptCNN) model, which is developed based on multiple convolutional filters. The proposed model is used to extract topological features from brain connectome data for neurological disorders classification and analysis.
Methods
The ConCeptCNN uses multiple vector‐shaped filters extract topological information from the brain connectome at different levels for complementary feature embeddings of brain connectome. The proposed model is validated using two datasets: the Neuro Bureau ADHD‐200 dataset and the Cincinnati Early Prediction Study (CINEPS) dataset.
Results
In a cross‐validation experiment, the ConCeptCNN achieved a prediction accuracy of 78.7% for the detection of attention deficit hyperactivity disorder (ADHD) in adolescents and an accuracy of 81.6% for the prediction of cognitive deficits at 2 years corrected age in very preterm infants. In addition to the classification tasks, the ConCeptCNN identified several brain regions that are discriminative to neurodevelopmental disorders.
Conclusions
We compared the ConCeptCNN with several peer CNN methods. The results demonstrated that proposed model improves overall classification performance of neurodevelopmental disorders prediction tasks.