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

Abstract
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.

Topics

No keywords indexed for this article. Browse by subject →

References

32

[1]

Heart Disease and Stroke Statistics—2017 Update: A Report From the American Heart Association

Emelia J. Benjamin, Michael J. Blaha, Stephanie E. Chiuve et al.

Circulation 2017 10.1161/cir.0000000000000485

[2]

Global and regional burden of stroke during 1990–2010: findings from the Global Burden of Disease Study 2010

Valery L Feigin, Mohammad H Forouzanfar, Rita Krishnamurthi et al.

The Lancet 2014 10.1016/s0140-6736(13)61953-4

[3]

Kwakkel, G., Kollen, B. J., Van der Grond, J. V. & Prevo, A. J. H. Probability of regaining dexterity in the flaccid upper limb: Impact of severity of paresis and time since onset in acute stroke. Stroke 34, 2181–2186 (2003). 10.1161/01.str.0000087172.16305.cd

[4]

Ren, J., Kaplan, P. L., Charette, M. F., Speller, H. & Finklestein, S. P. Time window of intracisternal osteogenic protein-1 in enhancing functional recovery after stroke. Neuropharmacology 39, 860–865 (2000). 10.1016/s0028-3908(99)00261-0

[5]

Association between brain imaging signs, early and late outcomes, and response to intravenous alteplase after acute ischaemic stroke in the third International Stroke Trial (IST-3): secondary analysis of a randomised controlled trial

The Lancet Neurology 2015 10.1016/s1474-4422(15)00012-5

[6]

Burke Quinlan, E. et al. Neural function, injury, and stroke subtype predict treatment gains after stroke. Ann Neurol 77, 132–145 (2015). 10.1002/ana.24309

[7]

Marie-Héléne, M. & Cramer, S. C. Biomarkers of recovery after stroke. Current opinion in neurology 21, 654–659 (2008). 10.1097/wco.0b013e3283186f96

[8]

Nijland, R. H. M., van Wegen, E. E. H., Harmeling-van der Wel, B. C. & Kwakkel, G. Presence of finger extension and shoulder abduction within 72 Hours after stroke predicts functional recovery. Stroke 41, 745–750 (2010). 10.1161/strokeaha.109.572065

[9]

Riley, J. D. et al. Anatomy of stroke injury predicts gains from therapy. Stroke 42, 421–426 (2011). 10.1161/strokeaha.110.599340

[10]

Cramer, S. C. et al. Predicting functional gains in a stroke trial. Stroke 38, 2108–2114 (2007). 10.1161/strokeaha.107.485631

[11]

Jongbloed, L. Y. N. Prediction of function after stroke: a critical review. Stroke 17, 765–776 (1986). 10.1161/01.str.17.4.765

[12]

Nouri, S. & Cramer, S. C. Anatomy and physiology predict response to motor cortex stimulation after stroke. Neurology 77, 1076–1083 (2011). 10.1212/wnl.0b013e31822e1482

[13]

Inter-individual Variability in the Capacity for Motor Recovery After Ischemic Stroke

Shyam Prabhakaran, Eric Zarahn, Claire Riley et al.

Neurorehabilitation and Neural Repair 2007 10.1177/1545968307305302

[14]

Stinear, C. Prediction of recovery of motor function after stroke. The Lancet Neurology 9, 1228–1232 (2010). 10.1016/s1474-4422(10)70247-7

[15]

Lesion Load of the Corticospinal Tract Predicts Motor Impairment in Chronic Stroke

Lin L. Zhu, Robert Lindenberg, Michael P. Alexander et al.

Stroke 2010 10.1161/strokeaha.109.577023

[16]

Fiez, J. A., Damasio, H. & Grabowski, T. J. Lesion segmentation and manual warping to a reference brain: Intra- and interobserver reliability. Human Brain Mapping 9, 192–211 (2000). 10.1002/(sici)1097-0193(200004)9:4<192::aid-hbm2>3.0.co;2-y

[17]

Montaner, J. et al. Plasmatic level of neuroinflammatory markers predict the extent of diffusion-weighted image lesions in hyperacute stroke. Journal of Cerebral Blood Flow & Metabolism 23, 1403–1407 (2003). 10.1097/01.wcb.0000100044.07481.97

[18]

Sakamoto, Y. et al. Early ischaemic diffusion lesion reduction in patients treated with intravenous tissue plasminogen activator: infrequent, but significantly associated with recanalization. International Journal of Stroke 8, 321–326 (2013). 10.1111/j.1747-4949.2012.00902.x

[19]

Thomas, R. G. R. et al. Apparent diffusion coefficient thresholds and diffusion lesion volume in acute stroke. Journal of Stroke and Cerebrovascular Diseases 22, 906–909 (2013). 10.1016/j.jstrokecerebrovasdis.2012.09.018

[20]

Wittsack, H.-J. et al. MR Imaging in Acute Stroke: Diffusion-weighted and Perfusion Imaging Parameters for Predicting Infarct Size. Radiology 222, 397–403 (2002). 10.1148/radiol.2222001731

[21]

Pustina, D. et al. Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis. Human Brain Mapping 37, 1405–1421 (2016). 10.1002/hbm.23110

[22]

de Haan, B., Clas, P., Juenger, H., Wilke, M. & Karnath, H.-O. Fast semi-automated lesion demarcation in stroke. NeuroImage. Clinical 9, 69–74 (2015). 10.1016/j.nicl.2015.06.013

[23]

Maier, O. et al. ISLES 2015—A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Medical Image Analysis 35, 250–269 (2017). 10.1016/j.media.2016.07.009

[24]

Rorden, C. & Brett, M. Stereotaxic display of brain lesions. Behav Neurol 12, 191–200 (2000). 10.1155/2000/421719

[25]

Fazekas, F., Chawluk, J., Alavi, A., Hurtig, H. & Zimmerman, R. MR signal abnormalities at 1.5 T in Alzheimer's dementia and normal aging. American Journal of Roentgenology 149, 351–356 (1987). 10.2214/ajr.149.2.351

[26]

Sled, J. G., Zijdenbos, A. P. & Evans, A. C. A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Transactions on Medical Imaging 17, 87–97 (1998). 10.1109/42.668698

[27]

Automatic 3D Intersubject Registration of MR Volumetric Data in Standardized Talairach Space

D. Louis Collins, Peter Neelin, Terrence M. Peters et al.

Journal of Computer Assisted Tomography 1994 10.1097/00004728-199403000-00005

[28]

Cox, R. W. et al. A (sort of) new image data format standard: Nifti-1. Neuroimage 22, e1440 (2004).

[29]

Heuer, K., Ghosh, S., Robinson Sterling, A. & Toro, R. Open Neuroimaging Laboratory. Research Ideas and Outcomes 2, e9113 (2016). 10.3897/rio.2.e9113

[30]

Ito, K., Anglin, J. & Liew, S.-L. Semi-automated Robust Quantification of Lesions (SRQL) Toolbox. Research Ideas and Outcomes 3, e12259 (2017). 10.3897/rio.3.e12259

[31]

Liew, S.-L. ICPSR—Interuniversity Consortium for Political and Social Research https://doi.org/10.3886/ICPSR36684.v1 (2017) 10.3886/icpsr36684.v1

[32]

Liew, S.-L. Child Mind Institute https://doi.org/10.15387/fcp_indi.atlas (2017) 10.15387/fcp_indi.atlas

Cited By

230

Suboptimal capability of individual machine learning algorithms in modeling small-scale imbalanced clinical data of local hospital

Gang Li, Chenbi Li · 2024

PLoS ONE

Metrics

230

Citations

32

References

Details

Published: Feb 20, 2018
Vol/Issue: 5(1)
License: View

Authors

Autonomous and Intelligent Robotics Laboratory (AIRLab), Lehigh University, Bethlehem, PA, USA

Department of Physical Therapy Education and Department of Neurology, SUNY Upstate Medical University, Syracuse, NY (B.K.)

and 3Department of Neurology, University of California, Irvine, California 92697-3975;

Department of Psychiatry (Guintivano, Bauer, Watson, Krohn, Rubinow, Meltzer-Brody, Sullivan), Department of Genetics (Raffield, Li, Sullivan), and Department of Biostatistics (Li), University of North Carolina at Chapel Hill; Child Health Research Centre (Byrne, Kiewa), Institute for Molecular Bioscience (Byrne, Walker), Frazer Institute (Olsen), School of Public Health (Whiteman), and Queensland Brain Institute (Wray), University of Queensland, Brisbane, Australia; Department of Medical Epidemiology...

Biokinesiology and Physical Therapy, University of Southern California, Los Angeles, CA, USA

Cite This Article

Sook-Lei Liew, Julia M. Anglin, Nick W. Banks, et al. (2018). A large, open source dataset of stroke anatomical brain images and manual lesion segmentations. Scientific Data, 5(1). https://doi.org/10.1038/sdata.2018.11

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

You May Also Like