Ensemble classification of autism spectrum disorder using structural magnetic resonance imaging features.
Yanli Zhang-JamesJan K Buitelaarnull nullDaan van RooijStephen V FaraonePublished in: JCPP advances (2021)
Our results suggest that sMRI volumetric and cortical thickness data alone may not provide clinically sufficient useful diagnostic biomarkers for ASD. Developing clinically useful imaging classifiers for ASD will benefit from combining other data modalities or feature types, such as functional MRI data and raw images that can leverage other machine learning (ML) techniques such as convolutional neural networks.
Keyphrases
- convolutional neural network
- autism spectrum disorder
- deep learning
- machine learning
- magnetic resonance imaging
- big data
- electronic health record
- attention deficit hyperactivity disorder
- intellectual disability
- artificial intelligence
- contrast enhanced
- optical coherence tomography
- computed tomography
- mass spectrometry
- working memory
- diffusion weighted imaging
- fluorescence imaging
- monte carlo