A team of scientists at the University of Southern California (USC) in the US have compiled and shared a database of brain scans with the goal of helping researchers and clinicians around the world improve rehabilitation for stroke patients.
The database, referred to as Anatomical Tracings of Lesion After Stroke (ATLAS), includes hundreds of brain scans from patients that show lesions from stroke damage.
Typically, neuroanatomy experts manually draw boundaries around the lesions (segmentation) to assess the damage and determine the best form of rehabilitation. However, this method is labour intensive and requires anatomical expertise. With ATLAS, the researchers hope to automate and essentially revolutionise this practice.
In a study published in Scientific Data, a Nature journal, the researchers describe ATLAS is an open-source dataset of 304 T1-weighted MRIs with manually segmented lesions and metadata. This large, diverse dataset can be used to train and test lesion segmentation algorithms and provides a standardised dataset for comparing the performance of different segmentation methods.
“One of our goals is to meta-analyse thousands of stroke MRIs from around the world to understand how the lesions impact recovery,” said Dr Sook-Lei Liew, lead author of the study and Assistant Professor with joint appointments at the Mark and Mary Stevens Neuroimaging and Informatics Institute (INI) within the Keck School of Medicine of USC, the Chan Division of Occupational Science and Occupational Therapy, the Division of Biokinesiology and Physical Therapy and the USC Viterbi School of Engineering.
“We can’t do it by hand at the scale of thousands, so we are really interested in helping find better automated ways, using machine learning and computer vision, to identify the lesions and have machines draw those boundaries,” continued Liew.
The ATLAS team includes Assistant Professor of Neurology at INI, Hosung Kim, who used a neuroimaging analysis pipeline he developed to help standardise the images in the data set. Assistant Professor of Research, Tyler Ard, created custom software for advanced visualisation of the lesioned data set, rendering it into several high-resolution videos and images. 17 other co-authors across USC assisted with analysis, clinical characterisation and the collection and storage of data.
Data from the project are stored by the International Neuroimaging Data-Sharing Initiative (INDI), housed at the Child Mind Institute, and by the Inter-University Consortium for Political and Social Research (ICPSR), housed at the University of Michigan.
So far, 33 research groups around the world, including from Finland, Iran and Australia, have downloaded the ATLAS data set, which contains 304 manually-segmented MRI scans.
The research was funded by the National Institutes of Health-funded Center for Large Data Research and Data Sharing in Rehabilitation and by a National Institutes of Health K01 award from the National Center for Medical Rehabilitation Research.