Diagnosing autism spectrum disorder in children using conventional MRI and apparent diffusion coefficient based deep learning algorithms.
Xiang GuoJiehuan WangXiaoqiang WangWenjing LiuHao YuLi XuHengyan LiJiangfen WuMengxing DongWeixiong TanWeijian ChenYunjun YangYueqin ChenPublished in: European radiology (2021)
• Deep learning models based on conventional MRI and ADC can be used to diagnose ASD. • The model (DSM) based on the FLAIR and ADC sequence achieved the best diagnostic performance with an AUC of 0.836 in the independent test sets. • The attention mechanism further improved the diagnostic performance of the models.
Keyphrases
- diffusion weighted imaging
- deep learning
- autism spectrum disorder
- contrast enhanced
- magnetic resonance imaging
- machine learning
- artificial intelligence
- convolutional neural network
- diffusion weighted
- intellectual disability
- attention deficit hyperactivity disorder
- working memory
- young adults
- magnetic resonance
- computed tomography