Computational Methods in Neuroimaging: Advances and Challenges

Dear Colleagues,

All brain imaging modalities actually provide visualizations of the effects of diseases with greater sensitivity than clinical observations. Therefore, imaging modalities offer significant capacities for the early detection of  diseases at their early stages that improve the effectiveness of disease management. Computational neuroscience has had significant impacts on neuroimaging over the last decade. Computational neuroscience integrates models of the brain functions (like perception, action and cognition) and computational (biophysical) models of neuronal dynamics. Neural networks inspired by brain nature and dynamics Modeling of neurological disorders have shown great potentials in medicine including diagnosis, disease monitoring, and treatment. These models have different applications such as  face recognition, image processing, voice recognition, medical diagnosis, and signal processing. However, the main challenge to the modeling and simulation of brain functions and neural networks is the growing amount of big data and its processing. Efficient processing of big data and developing appropriate neural biomarkers from abundant data require advanced methodologies to generate biological neural parameters from abundant data.

Artificial intelligence (AI) and machine learning (ML) techniques, especially deep learning, have shown great promise in feature extraction, trait classification, and function fitting in imaging and visual recognition.

These techniques have been employed to address many complex problems in object detection and other fields. The ML strategies offer a robust approach to identifying and recognizing complex patterns and conducting different regression analyses to avoid the need for building the underlying physical models. Therefore, these technologies contribute significantly to the construction and optimization of computational neural models for imaging modalities.

This thematic issue will discuss recent advances, challenges, and future perspectives about computational models and methods along with neural networks used in neuroimaging for different applications. Researchers are invited to contribute original work related to this thematic issue, exploiting recent methodology using computational and mathematical techniques in neuroimaging, and addressing the challenges in developing dedicated systems for various clinical applications, while proposing new ideas and directions for future development. 

We welcome original research and review articles from systems/cognitive and computational neuroscience, to neuroimaging and neural signal processing. Original and review studies on the below topics are welcomed in this thematic issue:

• Computational models and methods for the analysis of brain activities in any form, including signals recorded by any anatomical or functional imaging modalities (EEG, MEG, fNIRS, Eps, MRI, fMRI, SPECT, PET, ultrasound, event-related optical signal (EROS), diffusion optical imaging (DOI), etc.
• Brain–computer/machine interfaces (all paradigms, transfer learning, multi-modal BCI, Neural Prostheses) powered by Fuzzy Systems and computational methods.
• Neuro-robotics, Internet of Brain Things and Neuro-rehabilitation.
• Computational methods for Neuroscience applications and the understanding of brain processes, Deep Computational Methods.

Dr. Ali Yadollahpour
Dr. Samaneh Rashidi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Brain Sciences is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• computational neuroscience
• neuroimaging
• modelling
• neural networks
• artificial intelligence
• machine learning
• deep learning
• biomarkers