Call for papers: Special issue on: Benchmarks for Machine Learning in Neuroimaging.
Guest Editors: Thomas Yeo, Jean-François Mangin, Alexandre Gramfort, Janaina Mourao-Miranda, Juan Helen Zhou
Machine learning is an essential tool in almost every niche of neuroimaging. It is now crucial to draw on the lessons learned from experience in other fields. The underlying enthusiasm has overshadowed a great deal of challenges that are usually addressed through community-building based on appropriate benchmarks. Gauging the potential of new algorithms requires objectively interpretable, comparable, and reproducible benchmarks. Good benchmarks serve a number of different purposes and groups. For newcomers, benchmarks provide a summary that helps them orient in a maze of new terms, algorithms, and data. For sophisticates, benchmarks provide a baseline. Benchmarks encapsulate expert opinions about what’s important, initiating a cycle of optimization for all members of a community and providing a counterweight to biased hype.
This special issue aims to collect a set of such benchmarks to help the field grow. Each benchmark study shall propose a neuroimaging dataset together with a machine learning task to perform, such as classification or clustering and a quantitative evaluation method. Datasets shall be either open access or reachable via cloud-based procedure. We will only consider benchmark proposals endowed with a dataset allowing well-powered studies, unless an opportunity to explore new issues or a rare disease requires working in a more constrained environment.
The NeuroImage’s submission system will be open for submissions to our Special Issue from 01 Sep 2020. When submitting your manuscript please select the article type “VSI: Neuroimaging ML Benchmarking”. Please submit your manuscript before 30 Mar 2021.
All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production, and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles.
Please see an example here: https://www.sciencedirect.com/journal/neuroimage/special-issue/10S14SQ48ND
Please ensure you read the Guide for Authors before writing your manuscript. The Guide for Authors and link to submit your manuscript is available on the Journal’s homepage at:
Inquiries, including questions about appropriate topics, may be sent electronically to Dr.