Ming Chen1,2, Hailong Li1,3, Howard Fan2, Jonathan R Dillman1,4, Hui Wang1,5, Mekibib Altaye6,7, Bin Zhang6,7, Nehal A Parikh3,7, Lili He1,3,4. 1. Imaging Research Center, Department of Radiology, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA. 2. Department of Electrical, Engineering and Computer Science, University of Cincinnati, Cincinnati, Ohio, USA. 3. Center for Prevention of Neurodevelopmental Disorders, Perinatal Institute, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA. 4. Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, Ohio, USA. 5. MR Clinical Science, Philips, Cincinnati, Ohio, USA. 6. Division of Biostatistics and Epidemiology, Department of Pediatrics, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA. 7. Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, Ohio, USA.
Abstract
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.
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.
Authors: Tong He; Ru Kong; Avram J Holmes; Minh Nguyen; Mert R Sabuncu; Simon B Eickhoff; Danilo Bzdok; Jiashi Feng; B T Thomas Yeo Journal: Neuroimage Date: 2019-10-11 Impact factor: 6.556
Authors: Jeremy Kawahara; Colin J Brown; Steven P Miller; Brian G Booth; Vann Chau; Ruth E Grunau; Jill G Zwicker; Ghassan Hamarneh Journal: Neuroimage Date: 2016-09-28 Impact factor: 6.556
Authors: Brent C Munsell; Chong-Yaw Wee; Simon S Keller; Bernd Weber; Christian Elger; Laura Angelica Tomaz da Silva; Travis Nesland; Martin Styner; Dinggang Shen; Leonardo Bonilha Journal: Neuroimage Date: 2015-06-06 Impact factor: 6.556