Ensemble of 3D CNN Regressors with Data Fusion for Fluid Intelligence Prediction

• Published in: Adolescent Brain Cognitive Development Neurocognitive Prediction Vol. 11791; pp. 158 - 166
• Main Authors: Pominova, Marina, Kuzina, Anna, Kondrateva, Ekaterina, Sushchinskaya, Svetlana, Burnaev, Evgeny, Yarkin, Vyacheslav, Sharaev, Maxim
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: 3D convolutional neural networks; Deep learning; Fluid intelligence prediction; MRI analysis; VoxCNN ensemble
• ISBN: 3030319008; 9783030319007
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-31901-4_19

In this work, we aimed at predicting children’s fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health. The target variable was regressed on a data collection site, sociodemographic variables, and brain volume, thus being independent to the potentially informative factors, which were not directly related to the brain functioning. We investigated both feature extraction and deep learning approaches as well as different deep CNN architectures and their ensembles. We proposed an advanced architecture of VoxCNNs ensemble, which yields MSE (92.838) on a blind test.