Artificial intelligence (AI) for medical imaging is a technology with great potential. An in-depth understanding of the principles and applications of magnetic resonance imaging (MRI), machine learning (ML), and deep learning (DL) is fundamental for developing AI-based algorithms that can meet the requirements of clinical diagnosis and have excellent quality and efficiency. Moreover, a more comprehensive understanding of applications and opportunities would help to implement AI-based methods in an ethical and sustainable manner. This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images. Then, the application of ML and DL methods to six typical neurological and psychiatric diseases is summarized, including Alzheimer’s disease (AD), Parkinson’s disease (PD), major depressive disorder (MDD), schizophrenia (SCZ), attention-deficit/hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Finally, the limitations of the existing research are discussed, and possible future research directions are proposed.

Neuroimaging studies have associated brain changes in children with future reading and language skills, but few studies have investigated the association between language skills and white matter structure in preschool-aged children. Using 208 data sets acquired in 73 healthy children aged 2–7 years, we investigated the relationship between developmental brain microstructure and phonological processing ability as measured using their phonological processing raw score (PPRS). The correlation analysis showed that across the whole age group, with increasing age, PPRS increased, fractional anisotropy (FA) of the internal capsule and inferior fronto-occipital fasciculus and some other regions increased, and mean diffusivity (MD) of the corpus callosum and internal capsule and some other regions decreased. The results of the mediation analysis suggest that increased FA may be the basis of phonological processing ability development during this period, and the increased number of fiber connections between the right inferior parietal lobule and right supramarginal gyrus may be a key imaging feature of phonological processing ability development. Our study reflects the changes in brain microstructure and contributes to understanding the underlying neural mechanisms of language development in preschool children.