About this Research Topic
In recent years, the world has witnessed a significant increase in the number of machine learning studies using medical images. The results have consistently demonstrated the potential of machine learning in a variety of clinical settings, such as detection of diabetic retinopathy using retinal fundus photographs, skin cancer classification with dermoscopic images, breast cancer detection and diagnosis with mammography, or polyp detection with virtual colonoscopy. These clinical applications have already made a significant contribution to improving the reliability and accuracy of computer-assisted systems for disease detection and diagnosis.
Recently, machine learning has also demonstrated its great potential in neuroscience. Data from noninvasive neuroimaging techniques, such as structural and functional MRI images, electroencephalography and magnetoencephalography, are traditionally used to investigate brain structure and functions. We are accessing through machine learning models a level of analysis which allows a clearer understanding of how the brain works in healthy and diseased people. Indeed, those models are capable of detecting subtle and complex variations in neuroimaging data, which can provide support for more accurate diagnoses, treatment strategies, and prognosis of neuropsychiatric disorders. Moreover, novel targets for brain stimulation treatments could be identified.
This Research Topic aims to advance our understanding of healthy and diseased brains while contributing to improving diagnosis, treatment, and prognosis of neuropsychiatric disorders. We also hope to facilitate the identification of potential imaging biomarkers.
Specifically, we welcome original research articles and reviews that focus on new methods, and on the applications of novel machine learning approaches and neuroimaging techniques in the following conditions:
- schizophrenia spectrum and other psychotic disorders,
- depressive disorders, bipolar and related disorders,
- autism spectrum disorder, attention-deficit/hyperactivity disorder, etc…
Recently, machine learning has also demonstrated its great potential in neuroscience. Data from noninvasive neuroimaging techniques, such as structural and functional MRI images, electroencephalography and magnetoencephalography, are traditionally used to investigate brain structure and functions. We are accessing through machine learning models a level of analysis which allows a clearer understanding of how the brain works in healthy and diseased people. Indeed, those models are capable of detecting subtle and complex variations in neuroimaging data, which can provide support for more accurate diagnoses, treatment strategies, and prognosis of neuropsychiatric disorders. Moreover, novel targets for brain stimulation treatments could be identified.
This Research Topic aims to advance our understanding of healthy and diseased brains while contributing to improving diagnosis, treatment, and prognosis of neuropsychiatric disorders. We also hope to facilitate the identification of potential imaging biomarkers.
Specifically, we welcome original research articles and reviews that focus on new methods, and on the applications of novel machine learning approaches and neuroimaging techniques in the following conditions:
- schizophrenia spectrum and other psychotic disorders,
- depressive disorders, bipolar and related disorders,
- autism spectrum disorder, attention-deficit/hyperactivity disorder, etc…
Keywords: machine learning, neuroimaging, precision medicine, neurological diseases, psychiatric diseases
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
