Call for Papers: Deep Learning Techniques for Understanding Brain Disorders
This PeerJ Computer Science Special Issue will publish the latest research where ideas from deep learning are used to understand brain function.
This Special Issue aims to publish the latest research developments on all facets of deep learning empowered neurological disorders – Special Issue Editor Jyotismita Chaki
The brain is one of the most complex organs of the human body. Modern understanding of brain disorders is shaped by multiple non-invasive modalities of data that can be acquired from the human brain, such as EEG, fMRI, PET and fNIRS. Due to the high dimensional nature of these data, understanding patterns in the data and their discriminability across disorders has been a challenge. The advent of Deep learning (DL) models has begun to address this challenge, through pattern recognition, classification, detection, diagnosis, augmentation and segmentation. The cross-pollination of ideas from neuroscience, neurology, psychiatry, neuroimaging and computer science is required for this budding field to attain its full potential.
This Special Issue focuses on a really hot topic, where there is a lot to explore – Special Issue Editor Jude Hemanth
The purpose of this Special Issue is to showcase research where ideas from deep learning within the field of engineering and computer science are used to understand brain function in the healthy brain (neuroscience) as well as those in neurological and psychiatric brain disorders with the help of neuroimaging data. Applications to neurological disorders include (but are not limited to) Alzheimer’s Disease and Dementia, movement disorders including Parkinson’s Disease, Stroke, Epilepsy, Amyotrophic Lateral Sclerosis, Brain Injury and Brain Tumours while psychiatric disorders include Schizophrenia spectrum, Autism spectrum, ADHD, Depression, PTSD, eating disorders, anxiety disorders, etc.
This Special Issue is timely as it calls for cross-pollination of ideas between engineering and computer science with brain sciences – Special Issue Editor Gopikrishna Deshpande
Researchers are encouraged to submit manuscripts related to classification, regression, detection, diagnosis, prediction of treatment outcomes, augmentation or segmentation methods based on DL for publication. Approaches to explainable AI, which enable a scientific understanding of features in the data (and hence aspects of brain function) that are most important for driving the model’s prediction are very much encouraged. This special issue especially welcomes submissions that depict the end-to-end technological viewpoint that uses automated informatics systems to solve single or multiple cases of healthcare advancements.
To find out more and submit your abstract, visit https://peerj.com/special-issues/116-dl-brain-disorders