A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms

Liew, Sook‐Lei; Lo, Bethany; Donnelly, Miranda R; Zavaliangos‐Petropulu, Artemis; Jeong, Jessica N.; Barisano, Giuseppe; Hutton, Alexandre; Simon, Julia Pia; Juliano, Julia M.; Suri, Anisha; Ard, Tyler; Banaj, Nerisa; Borich, Michael R.; Boyd, Lara A.; Brodtmann, Amy; Buetefisch, Cathrin M.; Cao, Lei; Cassidy, Jessica M.; Ciullo, Valentina; Conforto, Adriana Bastos; Cramer, Steven C.; Dacosta-Aguayo, Rosalía; Rosa, Ezequiel de la; Domín, Martin; Dula, Adrienne N.; Feng, Wuwei; Franco, Alexandre R.; Geranmayeh, Fatemeh; Gramfort, Alexandre; Gregory, Chris; Hanlon, Colleen A.; Kautz, Steven A.; Khlif, Mohamed Salah; Kim, Ho‐Sung; Kirschke, Jan S.; Liu, Jingchun; Lotze, Martín; MacIntosh, Bradley J.; Mataró, María; Mohamed, Feroze B.; Nordvik, Jan Egil; Park, Gilsoon; Pienta, Amy; Piras, Fabrizio; Redman, Shane M.; Revill, Kate; Robertson, Andrew D.; Seo, Na Jin; Soekadar, Surjo R.; Spalletta, Gianfranco; Sweet, Alison; Teleńczuk, Maria; Thielman, Gregory; Winstein, Carolee J.; Wittenberg, George F.; Wong, Kristin A; Yu, Chunshui

doi:10.1101/2021.12.09.21267554

Cited by 7 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a subset of the data for which we received raw T1-weighted MRIs and could identify observable lesions (n=748), lesion masks were manually segmented by trained research team members based on a previously published lesion segmentation protocol. 28,29 Lesions were preprocessed as detailed previously. 29 Briefly, preprocessing included intensity non-uniformity correction, intensity standardization, and registration to the MNI-152 template.…”

Section: Lesion Analysesmentioning

confidence: 99%

“…28,29 Lesions were preprocessed as detailed previously. 29 Briefly, preprocessing included intensity non-uniformity correction, intensity standardization, and registration to the MNI-152 template. Lesion volume (measured in voxels) and percent of CST-LL, or overlap, were calculated using the open-source Pipeline for Analyzing Lesions after Stroke toolbox.…”

Section: Lesion Analysesmentioning

confidence: 99%

“…The CST region of interest atlas 31 can be freely accessed from: http://lrnlab.org/. Our T1w MRI data and accompanying lesion masks are publicly available here: 29 http://fcon_1000.projects.nitrc.org/indi/retro/atlas.html. Additional summary data and code from this study are available upon reasonable request from the corresponding author.…”

Section: Data Availabilitymentioning

confidence: 99%

See 2 more Smart Citations

Global brain health modulates the impact of lesion damage on post-stroke sensorimotor outcomes

Liew

Schweighofer

Cole

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Sensorimotor performance after stroke is strongly related to focal injury measures such as corticospinal tract lesion load. However, the role of global brain health is less clear. Here, we examined the impact of brain age, a measure of neurobiological aging derived from whole brain structural neuroimaging, on sensorimotor outcomes. We hypothesized that stroke lesion damage would result in older brain age, which would in turn be associated with poorer sensorimotor outcomes. We also expected that brain age would mediate the impact of lesion damage on sensorimotor outcomes and that these relationships would be driven by post-stroke secondary atrophy (e.g., strongest in the ipsilesional hemisphere in chronic stroke). We further hypothesized that structural brain resilience, which we define in the context of stroke as the brain’s ability to maintain its global integrity despite focal lesion damage, would differentiate people with better versus worse outcomes.We analyzed cross-sectional high-resolution brain MRI and outcomes data from 963 people with stroke from 38 cohorts worldwide using robust linear mixed-effects regressions to examine the relationship between sensorimotor behavior, lesion damage, and brain age. We used a mediation analysis to examine whether brain age mediates the impact of lesion damage on stroke outcomes and if associations are driven by ipsilesional measures in chronic (≥180 days) stroke. We assessed the impact of brain resilience on sensorimotor outcome using logistic regression with propensity score matching on lesion damage.Stroke lesion damage was associated with older brain age, which in turn was associated with poorer sensorimotor outcomes. Brain age mediated the impact of corticospinal tract lesion load on sensorimotor outcomes most strongly in the ipsilesional hemisphere in chronic stroke. Greater brain resilience, as indexed by younger brain age, explained why people have better versus worse sensorimotor outcomes when lesion damage was fixed.We present novel evidence that global brain health is associated with superior post-stroke sensorimotor outcomes and modifies the impact of focal damage. This relationship appears to be due to post-stroke secondary degeneration. Brain resilience provides insight into why some people have better outcomes after stroke, despite similar amounts of focal injury. Inclusion of imaging-based assessments of global brain health may improve prediction of post-stroke sensorimotor outcomes compared to focal injury measures alone. This investigation is important because it introduces the potential to apply novel therapeutic interventions to prevent or slow brain aging from other fields (e.g., Alzheimer’s disease) to stroke.

show abstract

Section: Lesion Analysesmentioning

confidence: 99%

Section: Lesion Analysesmentioning

confidence: 99%

Section: Data Availabilitymentioning

confidence: 99%

See 1 more Smart Citation

Global brain health modulates the impact of lesion damage on post-stroke sensorimotor outcomes

Liew

Schweighofer

Cole

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To further evaluate the generalization to unseen sites, we use data from Sites 38, 40, and 48 from ATLAS v2.0 [51]. The new version contains more new unseen sites that could serve as external datasets for further evaluation of generalisability.…”

Section: E Generalization To Unseen External Sitesmentioning

confidence: 99%

SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization

Yu¹,

Huang²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as strokes are the main cause of various cerebrovascular diseases. Although deep learning-based models have been proposed for this task, generalizing these models to unseen sites is difficult due to not only the large intersite discrepancy among different scanners, imaging protocols, and populations but also the variations in stroke lesion shape, size, and location. Thus, we propose a U-net-based segmentation network termed SG-Net to improve unseen site generalization for stroke lesion segmentation on MR images. Specifically, we first propose masked adaptive instance normalization (MAIN) to minimize intersite discrepancies, standardizing input MR images from different sites into a site-unrelated style by dynamically learning affine parameters from the input. Then, we leverage a gradient reversal layer to force the U-net encoder to learn site-invariant representation, which further improves the model generalization in conjunction with MAIN. Finally, inspired by the "pseudosymmetry" of the human brain, we introduce a simple, yet effective data augmentation technique that can be embedded within SG-Net to double the sample size while halving memory consumption. As a result, stroke lesions from the whole brain can be easily identified within a hemisphere, improving the simplicity of training. Experimental results on the benchmark Anatomical Tracings of Lesions After Stroke (ATLAS) dataset, which includes MR images from 9 different sites, demonstrate that under the "leave-one-site-out" setting, the proposed SG-Net substantially outperforms recently published methods in terms of quantitative metrics and qualitative comparisons.

show abstract

“…In this quest, automatic lesion segmentation has emerged as a crucial tool [2]. Automatic image segmentation refers to the assignment of non-overlapping boundaries in an image to regions that are dissimilar in core features such as intensity or texture [3].…”

Section: Introductionmentioning

confidence: 99%

Automatic Segmentation and Quantitative Assessment of Stroke Lesions on MR images

Verma¹,

Kumar²,

Paydarfar³

2022

Preprint

View full text Add to dashboard Cite

Lesion studies are crucial in establishing brain-behavior relationships, and accurately segmenting the lesion represents the first step in achieving this. Manual lesion segmentation is the gold standard for chronic strokes. However, it is labor-intensive, subject to bias, and limits sample size. Therefore, our objective is to develop an automatic segmentation algorithm for chronic stroke lesions on T1-weighted MR images. Methods: To train our model, we utilized an open-source dataset: ATLAS v2.0 (Anatomical Tracings of Lesions After Stroke). We partitioned the dataset of 655 T1 images with manual segmentation labels into five subsets and performed a 5-fold cross-validation to avoid overfitting of the model. We used a deep neural network (DNN) architecture for model training. Results: To evaluate the model performance, we used three metrics that pertain to diverse aspects of volumetric segmentation including shape, location, and size. The Dice similarity coefficient (DSC) compares the spatial overlap between manual and machine segmentation. The average DSC was 0.65 (0.61- 0.67; 95% bootstrapped CI). Average symmetric surface distance (ASSD) measures contour distances between the two segmentations. ASSD between manual and automatic segmentation was 12mm. Finally, we compared the total lesion volumes and the Pearson correlation coefficient (ρ) between the manual and automatically segmented lesion volumes, which was 0.97(p-value &lt; 0.001). Conclusions: We present the first automated segmentation model trained on a large multicentric dataset. This model will enable automated on-demand processing of MRI scans and quantitative chronic stroke lesion assessment.

show abstract

A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms

Cited by 7 publications

References 37 publications

Global brain health modulates the impact of lesion damage on post-stroke sensorimotor outcomes

Global brain health modulates the impact of lesion damage on post-stroke sensorimotor outcomes

SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization

Automatic Segmentation and Quantitative Assessment of Stroke Lesions on MR images

Contact Info

Product

Resources

About