1
|
Hernandez Petzsche MR, de la Rosa E, Hanning U, Wiest R, Valenzuela W, Reyes M, Meyer M, Liew SL, Kofler F, Ezhov I, Robben D, Hutton A, Friedrich T, Zarth T, Bürkle J, Baran TA, Menze B, Broocks G, Meyer L, Zimmer C, Boeckh-Behrens T, Berndt M, Ikenberg B, Wiestler B, Kirschke JS. ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset. Sci Data 2022; 9:762. [PMID: 36496501 PMCID: PMC9741583 DOI: 10.1038/s41597-022-01875-5] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2022] [Accepted: 11/28/2022] [Indexed: 12/13/2022] Open
Abstract
Magnetic resonance imaging (MRI) is an important imaging modality in stroke. Computer based automated medical image processing is increasingly finding its way into clinical routine. The Ischemic Stroke Lesion Segmentation (ISLES) challenge is a continuous effort to develop and identify benchmark methods for acute and sub-acute ischemic stroke lesion segmentation. Here we introduce an expert-annotated, multicenter MRI dataset for segmentation of acute to subacute stroke lesions ( https://doi.org/10.5281/zenodo.7153326 ). This dataset comprises 400 multi-vendor MRI cases with high variability in stroke lesion size, quantity and location. It is split into a training dataset of n = 250 and a test dataset of n = 150. All training data is publicly available. The test dataset will be used for model validation only and will not be released to the public. This dataset serves as the foundation of the ISLES 2022 challenge ( https://www.isles-challenge.org/ ) with the goal of finding algorithmic methods to enable the development and benchmarking of automatic, robust and accurate segmentation methods for ischemic stroke.
Collapse
Affiliation(s)
- Moritz R Hernandez Petzsche
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany.
| | - Ezequiel de la Rosa
- icometrix, Leuven, Belgium
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Uta Hanning
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Roland Wiest
- Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland
| | - Waldo Valenzuela
- Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland
| | - Mauricio Reyes
- ARTORG Center for Biomedical Engineering Research, Univ. of Bern, Bern, Switzerland
| | | | - Sook-Lei Liew
- Chan Division of Occupational Science and Occupational Therapy, University of Southern California, Los Angeles, CA, USA
| | - Florian Kofler
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
- Department of Informatics, Technical University of Munich, Munich, Germany
- TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich, Munich, Germany
- Helmholtz AI, Helmholtz Zentrum Munich, Munich, Germany
| | - Ivan Ezhov
- Department of Informatics, Technical University of Munich, Munich, Germany
- TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich, Munich, Germany
| | | | - Alexandre Hutton
- Chan Division of Occupational Science and Occupational Therapy, University of Southern California, Los Angeles, CA, USA
| | - Tassilo Friedrich
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Teresa Zarth
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Johannes Bürkle
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - The Anh Baran
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Björn Menze
- Department of Informatics, Technical University of Munich, Munich, Germany
- Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
| | - Gabriel Broocks
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Lukas Meyer
- Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany
| | - Claus Zimmer
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Tobias Boeckh-Behrens
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Maria Berndt
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Benno Ikenberg
- Department of Neurology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
| | - Benedikt Wiestler
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
- TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich, Munich, Germany
| | - Jan S Kirschke
- Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany
- TranslaTUM - Central Institute for Translational Cancer Research, Technical University of Munich, Munich, Germany
| |
Collapse
|
2
|
Lehrieder D, Layer K, Müller HP, Rücker V, Kassubek J, Juettler E, Neugebauer H. Association of Infarct Volume Before Hemicraniectomy and Outcome After Malignant Infarction. Neurology 2021; 96:e2704-e2713. [PMID: 33875557 DOI: 10.1212/wnl.0000000000011987] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2020] [Accepted: 02/26/2021] [Indexed: 11/15/2022] Open
Abstract
ObjectiveTo determine the impact of infarct volume before hemicraniectomy in malignant middle cerebral artery infarction (MMI) as an independent predictor for patient selection and outcome prediction, we retrospectively analyzed data of 140 patients from a prospective multi-center study.MethodsPatients from the DESTINY-Registry that underwent hemicraniectomy after ischemic infarction of >50% of the middle cerebral artery territory were included. Functional outcome according to the modified Rankin Scale (mRS) was assessed at 12 months. Unfavorable outcome was defined as mRS 4-6. Infarct size was quantified semi-automatically from computed tomography or magnetic resonance imaging before hemicraniectomy. Subgroup analyses in patients fulfilling inclusion criteria of randomized trials in younger patients (age≤60y) were predefined.ResultsAmong 140 patients with complete datasets (34% female, mean (SD) age 54 (11) years), 105 (75%) had an unfavorable outcome (mRS > 3). Mean (SD) infarct volume was 238 (63) ml. Multivariable logistic regression identified age (OR 1.08 per 1 year increase; 95%-CI 1.02-1.13; p=0.004), infarct size (OR 1.27 per 10ml increase; 95%-CI 1.12-1.44; p<0.001) and NIHSS (OR 1.10; 95%-CI 1.01-1.20; p=0.030) before hemicraniectomy as independent predictors for unfavorable outcome. Findings were reproduced in patients fulfilling inclusion criteria of randomized trials in younger patients. Infarct volume thresholds for prediction of unfavorable outcome with high specificity (94% in overall cohort and 92% in younger patients) were more than 258 ml before hemicraniectomy.ConclusionOutcome in MMI strongly depends on age and infarct size before hemicraniectomy. Standardized volumetry may be helpful in the process of decision making concerning hemicraniectomy.
Collapse
Affiliation(s)
| | | | | | - Viktoria Rücker
- Institute of Clinical Epidemiology and Biometry, University of Würzburg, Würzburg
| | - Jan Kassubek
- Department of Neurology, University Hospital of Ulm, Ulm
| | - Eric Juettler
- Department of Neurology, Ostalb-Klinikum Aalen, Aalen
| | | | | |
Collapse
|
3
|
Mrosk F, Hecht N, Vajkoczy P. Decompressive hemicraniectomy in ischemic stroke. J Neurosurg Sci 2020; 65:249-258. [PMID: 33252206 DOI: 10.23736/s0390-5616.20.05103-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
Malignant hemispheric stroke (MHS) is a life-threatening event, associated with high morbidity and mortality. Decompressive hemicraniectomy (DHS) is the treatment of choice to relieve the emerging space-occupying brain edema. This review details the pathophysiological and scientific background, considerations for clinical decision making, surgical treatment and impact on the patients' outcome. Although surgery reduces mortality significantly, the probability for unfavorable outcome is still high in selected cases. While former randomized controlled studies aimed for the prevention of the primary cause, the current research focuses on the treatment and prevention of secondary neurological injury.
Collapse
Affiliation(s)
- Friedrich Mrosk
- Department of Neurosurgery, Center for Stroke Research Berlin (CSB), Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Nils Hecht
- Department of Neurosurgery, Center for Stroke Research Berlin (CSB), Charité - Universitätsmedizin Berlin, Berlin, Germany -
| | - Peter Vajkoczy
- Department of Neurosurgery, Center for Stroke Research Berlin (CSB), Charité - Universitätsmedizin Berlin, Berlin, Germany
| |
Collapse
|