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

被引:180
作者
Liew, Sook-Lei [1 ]
Anglin, Julia M. [1 ]
Banks, Nick W. [1 ]
Sondag, Matt [1 ]
Ito, Kaori L. [1 ]
Kim, Hosung [1 ]
Chan, Jennifer [1 ]
Ito, Joyce [1 ]
Jung, Connie [1 ]
Khoshab, Nima [2 ]
Lefebvre, Stephanie [1 ]
Nakamura, William [1 ]
Saldana, David [1 ]
Schmiesing, Allie [1 ]
Tran, Cathy [1 ]
Vo, Danny [1 ]
Ard, Tyler [1 ]
Heydari, Panthea [1 ]
Kim, Bokkyu [1 ]
Aziz-Zadeh, Lisa [1 ]
Cramer, Steven C. [2 ]
Liu, Jingchun [3 ]
Soekadar, Surjo [4 ]
Nordvik, Jan-Egil [5 ]
Westlye, Lars T. [6 ,7 ,8 ]
Wang, Junping [3 ]
Winstein, Carolee [1 ]
Yu, Chunshui [3 ]
Ai, Lei [9 ]
Koo, Bonhwang [9 ]
Craddock, R. Cameron [9 ,10 ]
Milham, Michael [9 ,10 ]
Lakich, Matthew [11 ]
Pienta, Amy [12 ]
Stroud, Alison [12 ]
机构
[1] Univ Southern Calif, Los Angeles, CA 90089 USA
[2] Univ Calif Irvine, Irvine, CA 92697 USA
[3] Tianjin Med Univ, Gen Hosp, Tianjin 30051, Peoples R China
[4] Univ Tubingen, D-72076 Tubingen, Germany
[5] Sunnaas Rehabil Hosp HT, N-1453 Nesodden, Norway
[6] Oslo Univ Hosp, NORMENT, N-0372 Oslo, Norway
[7] Oslo Univ Hosp, KG Jebsen Ctr Psychosis Res, Div Mental Hlth & Addict, N-0372 Oslo, Norway
[8] Univ Oslo, Dept Psychol, N-0315 Oslo, Norway
[9] Child Mind Inst, New York, NY 10022 USA
[10] Nathan S Kline Inst Psychiat Res, Orangeburg, NY 10962 USA
[11] Univ Texas Med Branch, Galveston, TX 77555 USA
[12] Univ Michigan, Ann Arbor, MI 48104 USA
关键词
RECOVERY; PREDICT; DISEASE; GAINS; TIME;
D O I
10.1038/sdata.2018.11
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
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.
引用
收藏
页数:11
相关论文
共 31 条
[1]  
Benjamin EJ, 2018, CIRCULATION, V137, pE67, DOI [10.1161/CIR.0000000000000558, 10.1161/CIR.0000000000000485, 10.1161/CIR.0000000000000530]
[2]   AUTOMATIC 3D INTERSUBJECT REGISTRATION OF MR VOLUMETRIC DATA IN STANDARDIZED TALAIRACH SPACE [J].
COLLINS, DL ;
NEELIN, P ;
PETERS, TM ;
EVANS, AC .
JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 1994, 18 (02) :192-205
[3]  
Cox R., 2004, Neuroimage, V22, DOI DOI 10.1016/J.NEUROIMAGE.2004.01.013
[4]   Predicting functional gains in a stroke trial [J].
Cramer, Steven C. ;
Parrish, Todd B. ;
Levy, Robert M. ;
Stebbins, Glenn T. ;
Ruland, Sean D. ;
Lowry, David W. ;
Trouard, Theodore P. ;
Squire, Scott W. ;
Weinand, Martin E. ;
Savage, Cary R. ;
Wilkinson, Steven B. ;
Juranek, Jenifer ;
Leu, Szu-Yun ;
Himes, David M. .
STROKE, 2007, 38 (07) :2108-2114
[5]   Fast semi-automated lesion demarcation in stroke [J].
de Haan, Bianca ;
Clas, Philipp ;
Juenger, Hendrik ;
Wilke, Marko ;
Karnath, Hans-Otto .
NEUROIMAGE-CLINICAL, 2015, 9 :69-74
[6]  
FAZEKAS F, 1987, AM J NEURORADIOL, V8, P421
[7]   Global and regional burden of stroke during 1990-2010: findings from the Global Burden of Disease Study 2010 [J].
Feigin, Valery L. ;
Forouzanfar, Mohammad H. ;
Krishnamurthi, Rita ;
Mensah, George A. ;
Connor, Myles ;
Bennett, Derrick A. ;
Moran, Andrew E. ;
Sacco, Ralph L. ;
Anderson, Laurie ;
Truelsen, Thomas ;
O'Donnell, Martin ;
Venketasubramanian, Narayanaswamy ;
Barker-Collo, Suzanne ;
Lawes, Carlene M. M. ;
Wang, Wenzhi ;
Shinohara, Yukito ;
Witt, Emma ;
Ezzati, Majid ;
Naghavi, Mohsen ;
Murray, Christopher .
LANCET, 2014, 383 (9913) :245-255
[8]  
Fiez JA, 2000, HUM BRAIN MAPP, V9, P192, DOI 10.1002/(SICI)1097-0193(200004)9:4<192::AID-HBM2>3.0.CO
[9]  
2-Y
[10]  
Heuer K., 2016, Res. Ideas Outcomes, V2, pe9113, DOI DOI 10.3897/RIO.2.E9113