A large, open source dataset of stroke anatomical brain images and manual lesion segmentations

• Published in: Scientific data Vol. 5; no. 1; p. 180011
• Main Authors: Liew, Sook-Lei, Anglin, Julia M., Banks, Nick W., Sondag, Matt, Ito, Kaori L., Kim, Hosung, Chan, Jennifer, Ito, Joyce, Jung, Connie, Khoshab, Nima, Lefebvre, Stephanie, Nakamura, William, Saldana, David, Schmiesing, Allie, Tran, Cathy, Vo, Danny, Ard, Tyler, Heydari, Panthea, Kim, Bokkyu, Aziz-Zadeh, Lisa, Cramer, Steven C., Liu, Jingchun, Soekadar, Surjo, Nordvik, Jan-Egil, Westlye, Lars T., Wang, Junping, Winstein, Carolee, Yu, Chunshui, Ai, Lei, Koo, Bonhwang, Craddock, R. Cameron, Milham, Michael, Lakich, Matthew, Pienta, Amy, Stroud, Alison
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 20.02.2018; Nature Publishing Group
• Subjects: 692/617/375/534; 692/698/1688/64; 692/700/1421/1628; 692/700/1421/65; Adult; Algorithms; Brain - diagnostic imaging; Brain - pathology; Data Descriptor; Datasets; Humanities and Social Sciences; Humans; Image processing; Learning algorithms; Magnetic Resonance Imaging; multidisciplinary; Neuroimaging; Rehabilitation; Science; Segmentation; Stroke; Stroke - diagnostic imaging; Stroke - pathology
• DOI: 10.1038/sdata.2018.11
• ISSN: 2052-4463

Stroke is the leading cause of adult disability worldwide, with up to two-thirds of individuals experiencing long-term disabilities. Large-scale neuroimaging studies have shown promise in identifying robust biomarkers (e.g., measures of brain structure) of long-term stroke recovery following rehabilitation. However, analyzing large rehabilitation-related datasets is problematic due to barriers in accurate stroke lesion segmentation. Manually-traced lesions are currently the gold standard for lesion segmentation on T1-weighted MRIs, but are labor intensive and require anatomical expertise. While algorithms have been developed to automate this process, the results often lack accuracy. Newer algorithms that employ machine-learning techniques are promising, yet these require large training datasets to optimize performance. Here we present ATLAS (Anatomical Tracings of Lesions After Stroke), 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 standardized dataset for comparing the performance of different segmentation methods. We hope ATLAS release 1.1 will be a useful resource to assess and improve the accuracy of current lesion segmentation methods. Design Type(s) parallel group design Measurement Type(s) nuclear magnetic resonance assay Technology Type(s) MRI Scanner Factor Type(s) regional part of brain • cerebral hemisphere • Clinical Diagnosis Sample Characteristic(s) Homo sapiens • brain Machine-accessible metadata file describing the reported data (ISA-Tab format)