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

@article{Liew2017ALO,
  title={A large, open source dataset of stroke anatomical brain images and manual lesion segmentations},
  author={Sook-Lei Liew and Julia Anglin and Nicholas W Banks and Matthew Sondag and Kaori L. Ito and Hosung Kim and Jennifer Chan and Joyce Ito and Connie Jung and Nima Khoshab and Stephanie Lefebvre and William Nakamura and David Saldana and Allie Schmiesing and Cathy Tran and Danny Vo and Tyler Ard and Panthea Heydari and Bokkyu Kim and Lisa Aziz-Zadeh and Steven C. Cramer and Jingchun Liu and Surjo Raphael Soekadar and Jan Egil Nordvik and Lars Tjelta Westlye and Junping Wang and Carolee J. Winstein and Chunshui Yu and Lei Ai and Bonhwang Koo and Richard Cameron Craddock and Michael Peter Milham and Matthew Lakich and Amy Pienta and Alison Stroud},
  journal={Scientific Data},
  year={2017},
  volume={5}
}
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… 
A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms
TLDR
A larger dataset of stroke T1w MRIs and manually segmented lesion masks that includes training, test, and generalizability datasets are presented, anticipating that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke research.
A comparison of automated lesion segmentation approaches for chronic stroke T1-weighted MRI data
TLDR
An exhaustive review of the literature and identified one semi- and three fully automated approaches for segmentation of chronic stroke lesions using T1w MRI within the last ten years: Clusterize, Automated Lesion Identification, Gaussian naïve Bayes lesion detection, and LINDA.
A comparison of automated lesion segmentation approaches for chronic stroke T1‐weighted MRI data
TLDR
An exhaustive review of the literature and identified one semiautomated and three fully automated approaches for segmentation of chronic stroke lesions using T1w MRI within the last 10 years: Clusterize, automated lesion identification (ALI), Gaussian naïve Bayes lesion detection (lesionGnb), and lesions identification with neighborhood data analysis (LINDA).
X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
TLDR
A depthwise separable convolution based X-Net that designs a nonlocal operation namely Feature Similarity Module (FSM) to capture long-range dependencies and provides a more effective, dense contextual information extraction and thus facilitates better segmentation.
A comparison study of automated approaches for brain lesions segmentation in ischemic stroke
TLDR
An ensemble of several approaches to stroke lesion segmentation that are named Lesion Segmentation Toolbox (LST), Automated Lesion Identification (ALI), lesion_Guassian Naïve Bias (GNB), Lesion identification with Neighborhood Data Analysis (LINDA), DeepMedic, and DeepMedic+Conditional Random Fields (CRF) are considered.
Stroke Lesion Segmentation with Visual Cortex Anatomy Alike Neural Nets
TLDR
This work presents a more brain alike model which mimics the anatomical structure of the human visual cortex which is found to be able to perform equally well or better to the de-facto standard U-Net on the stroke lesion segmentation task.
A Novel Modified U-shaped 3-D Capsule Network (MUDCap3) for Stroke Lesion Segmentation from Brain MRI
TLDR
A novel modified U-shaped 3D capsule network (MUDCap3) has been proposed, which has achieved a dice score of 0.67 on the ATLAS dataset and outperformed over several state-of-the-art models in the literature.
Cross-Attention and Deep Supervision UNet for Lesion Segmentation of Chronic Stroke
TLDR
A cross-spatial attention module is proposed, which is different from the usual self-attention module, which interactively selects encode features and decode features to enrich the lost spatial focus in chronic stroke lesions from T1-weighted MR images.
A Review on Image Segmentation Techniques for MRI Brain Stroke Lesion
TLDR
This paper reviewed the techniques for automatic magnetic resonance imaging of brain lesions segmentation to identify more robust and accurate technique in segmenting the brain stroke lesion for computer-aided diagnosis.
...
...

References

SHOWING 1-10 OF 41 REFERENCES
Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis
TLDR
LINDA (Lesion Identification with Neighborhood Data Analysis), an automated segmentation algorithm capable of learning the relationship between existing manual segmentations and a single T1‐weighted MRI, is proposed, establishing a new viewpoint on evaluating automated methods not only with segmentation accuracy but also with brain–behavior relationships.
Semi-automated Robust Quantification of Lesions (SRQL) Toolbox
TLDR
The Semi-automated Robust Quantification of Lesions Toolbox is developed that performs several analysis steps, including a white matter intensity correction that removes healthy white matter voxels from the lesion mask, thereby making lesions slightly more robust to subjective errors.
Lesion segmentation and manual warping to a reference brain: Intra‐ and interobserver reliability
TLDR
The results establish benchmark parameters for expert and automated lesion transfer, and indicate that a high degree of confidence can be placed in the detailed anatomical interpretation of focal brain damage based upon the MAP‐3 technique.
Lesion Load of the Corticospinal Tract Predicts Motor Impairment in Chronic Stroke
TLDR
The results show the degree of functional motor deficit after a stroke is highly dependent on the overlap of the lesion with the CST and not lesion size per se.
Open Neuroimaging Laboratory
TLDR
The framework for an Open Neuroimaging Laboratory that will enable distributed collaboration around annotation, discovery and analysis of publicly available brain imaging data is planned, using browser based applications allowing individuals to work together without having to download any data or install any software.
Apparent diffusion coefficient thresholds and diffusion lesion volume in acute stroke.
  • R. Thomas, G. K. Lymer, J. Wardlaw
  • Medicine
    Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association
  • 2013
Stereotaxic display of brain lesions.
TLDR
This article describes freely available software for presenting stereotaxically aligned patient scans and suggests that this technique of presenting lesions in terms of images normalized to standard stereOTaxic space should become the standard for neuropsychological studies.
Automatic 3D Intersubject Registration of MR Volumetric Data in Standardized Talairach Space
TLDR
A fully automatic registration method to map volumetric data into stereotaxic space that yields results comparable with those of manually based techniques and therefore does not suffer the drawbacks involved in user intervention.
...
...