Deep learning on brain images in autism: What do large samples reveal of its complexity?

• Autores: Matthew Fleming, John Suckling
• Localización: Understanding the Brain Function and Emotions: 8th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2019 Almería, Spain, June 3–7, 2019 Proceedings, Part I / José Manuel Ferrández Vicente (dir. congr.), José Ramón Álvarez Sánchez (dir. congr.), Félix de la Paz López (dir. congr.), Francisco Javier Toledo Moreo (dir. congr.), Hojjat Adeli (dir. congr.), 2019, ISBN 978-3-030-19591-5, págs. 389-402
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Deep learning models for image classification face two recurring problems: they are typically limited by low sample size and areabstracted by their own complexity (the “black box problem”). Weaddress these problems with the largest functional MRI connectome dataset ever compiled, classifying it across gender and Task vs rest (no task) to ascertain its performance, and then apply the model to a cross-sectional comparison of autism vs typically developing (TD) controls that has proved difficult to characterise with inferential statistics.Employing class-balancing to build a training set, a convolutional neural network was classified fMRI connectivity with overall accuracies of 76.35% (AUROC 0.8401), 90.71% (AUROC 0.9573), and 67.65% (AUROC 0.7162) for gender, task vs rest, and autism vs TD, respectively. Salience maps demonstrated that the deep learning model is capable of distinguishing complex patterns across either wide networks or localized areas of the brain, and, by analyzing maximal activations of the hidden layers, that the deep learning model partitions data at an early stage in its classification.