Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset

Moritz Roman Hernandez Petzsche, Ezequiel de la Rosa, Uta Hanning, Roland Wiest, Waldo Enrique Valenzuela Pinilla, Mauricio Reyes, Maria Ines Meyer, Sook-Lei Liew, Florian Kofler, Ivan Ezhov, David Robben, Alexander Hutton, Tassilo Friedrich, Teresa Zarth, Johannes Bürkle, The Anh Baran, Bjoern Menze, Gabriel Broocks, Lukas Meyer, Claus Zimmer, Tobias Boeckh-Behrens, Maria Berndt, Benno Ikenberg, Benedikt Wiestler, Jan S. Kirschke

TL;DR

ISLES 2022 introduces a large, multicenter MRI dataset for ischemic stroke lesion segmentation, addressing acute-to-subacute presentations and including pre- and post-interventional images. The dataset comprises 400 cases (250 training, 150 test) with ground-truth segmentations produced by a hybrid human-algorithm workflow and validated by experienced neuroradiologists, using DWI, ADC, and FLAIR sequences. It provides detailed data records, ethical safeguards, and accessible code to facilitate robust benchmarking of segmentation algorithms across centers and scanners. By enabling cross-center generalization and post-revascularization analysis, ISLES 2022 aims to advance automated stroke lesion segmentation and, ultimately, clinical decision support.

Abstract

Magnetic resonance imaging (MRI) is a central modality for stroke imaging. It is used upon patient admission to make treatment decisions such as selecting patients for intravenous thrombolysis or endovascular therapy. MRI is later used in the duration of hospital stay to predict outcome by visualizing infarct core size and location. Furthermore, it may be used to characterize stroke etiology, e.g. differentiation between (cardio)-embolic and non-embolic stroke. Computer based automated medical image processing is increasingly finding its way into clinical routine. Previous iterations of the Ischemic Stroke Lesion Segmentation (ISLES) challenge have aided in the generation of identifying 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. 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 will be made 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 with the goal of finding algorithmic methods to enable the development and benchmarking of robust and accurate segmentation algorithms for ischemic stroke.

ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset

TL;DR

ISLES 2022 introduces a large, multicenter MRI dataset for ischemic stroke lesion segmentation, addressing acute-to-subacute presentations and including pre- and post-interventional images. The dataset comprises 400 cases (250 training, 150 test) with ground-truth segmentations produced by a hybrid human-algorithm workflow and validated by experienced neuroradiologists, using DWI, ADC, and FLAIR sequences. It provides detailed data records, ethical safeguards, and accessible code to facilitate robust benchmarking of segmentation algorithms across centers and scanners. By enabling cross-center generalization and post-revascularization analysis, ISLES 2022 aims to advance automated stroke lesion segmentation and, ultimately, clinical decision support.

Abstract

Magnetic resonance imaging (MRI) is a central modality for stroke imaging. It is used upon patient admission to make treatment decisions such as selecting patients for intravenous thrombolysis or endovascular therapy. MRI is later used in the duration of hospital stay to predict outcome by visualizing infarct core size and location. Furthermore, it may be used to characterize stroke etiology, e.g. differentiation between (cardio)-embolic and non-embolic stroke. Computer based automated medical image processing is increasingly finding its way into clinical routine. Previous iterations of the Ischemic Stroke Lesion Segmentation (ISLES) challenge have aided in the generation of identifying 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. 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 will be made 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 with the goal of finding algorithmic methods to enable the development and benchmarking of robust and accurate segmentation algorithms for ischemic stroke.
Paper Structure (9 sections, 2 figures, 2 tables)

This paper contains 9 sections, 2 figures, 2 tables.

Table of Contents

  1. Background & Summary
  2. Methods
  3. Ethical Statement
  4. Subject selection
  5. Ground truth stroke lesion segmentation
  6. Post-annotation Data Pre-processing
  7. Data Records
  8. Technical Validation
  9. Data and Code Availability

Figures (2)

  • Figure 1: Exemplary 3D Snapshots through the ischemic center of mass. Axial FLAIR and DWI images are displayed in the top leftmost columns. The 3rd column from the left shows the maximum intensity projection (MIP) of the mask (Msk). The three rightmost columns show DWI with mask overlay (without MIP) in the three anatomical planes. Top row: Larger left-sided infarct with bilateral punctiform, likely embolic satellite ischemias. 2$^{nd}$ row: Infarct of the entire right sided middle cerebral artery territory. 3$^{rd}$ row: Bilateral cerebellar and occipital infarcts after posterior circulation ischemia. Bottom row: Bilateral punctiform infarcts, likely resulting from multiple micro-embolic occlusions.
  • Figure 2: Workflow of the hybrid human-algorithm stroke lesion segmentation applied in this dataset.