In this week’s edition of our Who’s who in the Zoo series, meet Yassine Benhajali, who runs Brain Match.
Project: Brain Match
Researcher: Yassine Benhajali
Location: Anthropology Department, Université de Montréal, Canada.
What are your main research interests?
How nature and nurture interact to influence brain functioning.
Who else is in your project team? What are their roles?
Sebastian Urchs, Aman Badhwar and Pierre Bellec (Project Supervisor).
Tell us more about the data used in your project
Brain Match uses images of brain that have been made freely available thanks to the efforts of The Neuro Bureau (http://www.neurobureau.org/) and the ADHD-200 consortium (http://fcon_1000.projects.nitrc.org/indi/adhd200/index.html).
How do Zooniverse volunteers contribute to your research?
In general, manual quality control of brain images is very subjective and time consuming task. Zooniverse volunteers are helping us in two key ways; firstly, they are helping to validate our brain image quality control procedure, and secondly, to produce enough rated images to train computers to perform the quality control automatically.
What have been the biggest challenges in setting up your project?
Our biggest challenge was to build simple and comprehensive instructions.
What discoveries, and other outputs, has your project led to so far?
To date, with the help of Zooniverse, we have developed the first quality control procedure on brain imaging that could be performed by both novice or expert neuroscience raters. They both agree on most of the ratings. We are hoping to present this work at a conference soon (http://www.neuroinformatics2018.org/abstracts/).
Once you’ve finished collecting data, what research questions do you hope to be able to answer?
The next step will be to train machine learning model based on the information from Zooniverse raters, and to test if this model can perform as well as human rater.
What’s in store for your project in the future?
More data to rate, and other brain imaging modalities.
What are your favourite other citizen research projects and why?
I like all wildlife protection projects.
What guidance would you give to other researchers considering creating a citizen research project?
Make your tutorial clear and concise.
And finally, when not at work, where are we most likely to find you?
Biking, running and swimming.