1. A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms
- Author
-
Sook-Lei Liew, Bethany P. Lo, Miranda R. Donnelly, Artemis Zavaliangos-Petropulu, Jessica N. Jeong, Giuseppe Barisano, Alexandre Hutton, Julia P. Simon, Julia M. Juliano, Anisha Suri, Zhizhuo Wang, Aisha Abdullah, Jun Kim, Tyler Ard, Nerisa Banaj, Michael R. Borich, Lara A. Boyd, Amy Brodtmann, Cathrin M. Buetefisch, Lei Cao, Jessica M. Cassidy, Valentina Ciullo, Adriana B. Conforto, Steven C. Cramer, Rosalia Dacosta-Aguayo, Ezequiel de la Rosa, Martin Domin, Adrienne N. Dula, Wuwei Feng, Alexandre R. Franco, Fatemeh Geranmayeh, Alexandre Gramfort, Chris M. Gregory, Colleen A. Hanlon, Brenton G. Hordacre, Steven A. Kautz, Mohamed Salah Khlif, Hosung Kim, Jan S. Kirschke, Jingchun Liu, Martin Lotze, Bradley J. MacIntosh, Maria Mataró, Feroze B. Mohamed, Jan E. Nordvik, Gilsoon Park, Amy Pienta, Fabrizio Piras, Shane M. Redman, Kate P. Revill, Mauricio Reyes, Andrew D. Robertson, Na Jin Seo, Surjo R. Soekadar, Gianfranco Spalletta, Alison Sweet, Maria Telenczuk, Gregory Thielman, Lars T. Westlye, Carolee J. Winstein, George F. Wittenberg, Kristin A. Wong, Chunshui Yu, University of Southern California (USC), University of Pittsburgh (PITT), Pennsylvania Commonwealth System of Higher Education (PCSHE), Clinical and Behavioral Neurology - Neuroscienze e riabilitazione, IRCCS Fondazione Santa Lucia [Roma], Emory University School of Medicine, Emory University [Atlanta, GA], University of British Columbia [Vancouver], University of Melbourne, Child Mind Institute, Department Biostatistics University of North Carolina, University of North Carolina [Chapel Hill] (UNC), University of North Carolina System (UNC)-University of North Carolina System (UNC), Universidade de São Paulo = University of São Paulo (USP), University of California (UC), University of Barcelona, Technische Universität München = Technical University of Munich (TUM), Universität Greifswald - University of Greifswald, University of Texas at Austin [Austin], Duke University [Durham], Nathan S. Kline Institute for Psychiatric Research (NKI), New York State Office of Mental Health, New York University School of Medicine (NYU Grossman School of Medicine), Imperial College London, Modèles et inférence pour les données de Neuroimagerie (MIND), IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Medical University of South Carolina [Charleston] (MUSC), Wake Forest School of Medicine [Winston-Salem], Wake Forest Baptist Medical Center, University of South Australia [Adelaide], The Florey Institute of Neuroscience and Mental Health, Tianjin University (TJU), University of Toronto, Universitat de Barcelona (UB), Oslo Metropolitan University (OsloMet), University of Michigan [Ann Arbor], University of Michigan System, University of Bern, University of Waterloo [Waterloo], Charité - UniversitätsMedizin = Charité - University Hospital [Berlin], Oslo University Hospital [Oslo], Supported by The European Research Council under the European Union’s Horizon 2020 research and Innovation program (ERC StG, Grant 802998)., Liew, Sook-Lei, Lo, Bethany P, Donnelly, Miranda R, Zavaliangos-Petropulu, Artemis, Hordacre, Brenton G, and Winstein, Carolee J
- Subjects
accurate image processing ,Statistics and Probability ,Image Processing ,610 Medicine & health ,Neuroimaging ,Bioengineering ,[STAT.OT]Statistics [stat]/Other Statistics [stat.ML] ,Library and Information Sciences ,Education ,Computer-Assisted ,Image Processing, Computer-Assisted ,[INFO.INFO-IM]Computer Science [cs]/Medical Imaging ,Humans ,stroke rehabilitation ,[STAT.AP]Statistics [stat]/Applications [stat.AP] ,segmented lesion ,Neurosciences ,Brain ,ATLAS ,Magnetic Resonance Imaging ,Computer Science Applications ,Stroke ,Networking and Information Technology R&D (NITRD) ,570 Life sciences ,biology ,Statistics, Probability and Uncertainty ,Algorithms ,Information Systems - Abstract
Accurate lesion segmentation is critical in stroke rehabilitation research for the quantification of lesion burden and accurate image processing. Current automated lesion segmentation methods for T1-weighted (T1w) MRIs, commonly used in stroke research, lack accuracy and reliability. Manual segmentation remains the gold standard, but it is time-consuming, subjective, and requires neuroanatomical expertise. We previously released an open-source dataset of stroke T1w MRIs and manually-segmented lesion masks (ATLAS v1.2, N = 304) to encourage the development of better algorithms. However, many methods developed with ATLAS v1.2 report low accuracy, are not publicly accessible or are improperly validated, limiting their utility to the field. Here we present ATLAS v2.0 (N = 1271), a larger dataset of T1w MRIs and manually segmented lesion masks that includes training (n = 655), test (hidden masks, n = 300), and generalizability (hidden MRIs and masks, n = 316) datasets. Algorithm development using this larger sample should lead to more robust solutions; the hidden datasets allow for unbiased performance evaluation via segmentation challenges. We anticipate that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke research.
- Published
- 2022
- Full Text
- View/download PDF