ISLES 2015 - A public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI

By Oskar Maier, Bjoern H Menze, J. Gablentz, Levin Häni, Mattias Paul Heinrich, M. Liebrand, S. Winzeck, A. Basit, Paul Bentley, Liang Chen and 12 more. Medical Image Anal., 2016

525 citations recorded by the source corpus.

&NA; Ischemic stroke is the most common cerebrovascular disease, and its diagnosis, treatment, and study relies on non‐invasive imaging. Algorithms for stroke lesion segmentation from magnetic resonance imaging (MRI) volumes are intensely researched, but the reported results are largely incomparable due to different datasets and evaluation schemes. We approached this urgent problem of comparability with the Ischemic Stroke Lesion Segmentation (ISLES) challenge organized in conjunction with the MICCAI 2015 conference. In this paper we propose a common evaluation framework, describe the publicly available datasets, and present the results of the two sub‐challenges: Sub‐Acute Stroke Lesion Segmentation (SISS) and Stroke Perfusion Estimation (SPES). A total of 16 research groups participated with a wide range of state‐of‐the‐art automatic segmentation algorithms. A thorough analysis of the obtained data enables a critical evaluation of the current state‐of‐the‐art, recommendations for further developments, and the identification of remaining challenges. The segmentation of acute perfusion lesions addressed in SPES was found to be feasible. However, algorithms applied to sub‐acute lesion segmentation in SISS still lack accuracy. Overall, no algorithmic characteristic of any method was found to perform superior to the others. Instead, the characteristics of stroke lesion appearances, their evolution, and the observed challenges should be studied in detail. The annotated ISLES image datasets continue to be publicly available through an online evaluation system to serve as an ongoing benchmarking resource (www.isles‐challenge.org). HighlightsEvaluation framework for automatic stroke lesion segmentation from MRIPublic multi‐center, multi‐vendor, multi‐protocol databases releasedOngoing fair and automated benchmark with expert created ground truth setsComparison of 14+7 groups who responded to an open challenge in MICCAISegmentation feasible in acute and unsolved in sub‐acute cases Graphical abstract Figure. No caption available.

Subfields: Epidemiology, Neurology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/9999184caaa7e4ca36fbc3fe9d65028fae8f2e42

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Epidemiology

Qi-Yan Dou

In Neurology

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Medical Image Segmentation Using Deep Learning: A Survey (2020, unknown): “Thus there are many datasets on the brain and abdomen such as BRATS [3] [153] [154], ISLES [155], KITS [156], LITS [157], CHAOS [158], etc.”
Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis (2020, methodology): “In addition, we also evaluate the performance for synthesizing T2 modality images using T1 and Flair images on the ischemic stroke lesion segmentation challenge 2015 (ISLES2015) dataset [49].”
MRI Augmentation via Elastic Registration for Brain Lesions Segmentation (2017, methodology): “ISLES is a dataset from the Ischemic Stroke Lesion Segmentation (2015) challenge [15] In this paper we used the subset from the Sub-acute Ischemic Stroke lesion Segmentation (SISS) case, because, according to the results of the competition, this is a more challenging task, allowing us observe the…”
Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks (2017, unknown): “of the tasks in ISLES 2015 [32], which attracted many entries.”
VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation (2016, methodology): “ucture segmentation task [20] and four imaging modalities are used in brain tumor (T1, T1 contrastenhanced, T2, and T2-FLAIR MRI) [21] and lesion studies (T1-weighted, T2-weighted, DWI and FLAIR MRI) [19]. The main reason for acquiring multi-modality images is that the information from multi-modalit”
The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge (2019, background): “Despite these challenges, recent work in this area has demonstrated impressive performance on the 3D segmentation of a wide variety of anatomical structures and lesions in cross-sectional imaging (Maier et al., 2017; Bakas et al., 2018; Bilic et al., 2019; Zhuang et al., 2019).”
Understanding Deep Learning Techniques for Image Segmentation (2019, unknown): “Natural Berkeley Segmentation Dataset [140] Scenes PASCAL VOC [54] Stanford Background Dataset [72] Microsoft COCO [122] MIT Scene parsing data(ADE20K) [222, 223] Semantic Boundaries Dataset [75] Microsoft Research Cambridge Object Recognition Image Database (MSRC) [188] Video Densely Annotated Vide”
VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images (2017, unknown): “, 2016) or caused by various lesions (Menze et al., 2015; Maier et al., 2017), the confounding appearance of different”
Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation (2016, methodology): “That method perfomed less well on this challenging task (Maier et al. (2017)).”
Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation (2022, background): “[73] 3D MRI Longitudinal Multiple Sclerosis Lesion Segmentation [91], ISLES 2015 [92], BraTS 2018 [23] fm Multi-scale features”