Dataset Information

Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction.

ABSTRACT:

Background and objective

Cerebral edema (CED) is a serious complication of acute ischemic stroke (AIS), especially in patients with large hemispheric infarction (LHI). Herein, a deep learning-based approach is implemented to extract CSF from T2-Weighted Imaging (T2WI) and evaluate the relationship between quantified cerebrospinal fluid and outcomes.

Methods

Patients with acute LHI who underwent magnetic resonance imaging (MRI) were included. We used a deep learning algorithm to segment the CSF from T2WI. The hemispheric CSF ratio was calculated to evaluate its relationship with the degree of brain edema and prognosis in patients with LHI.

Results

For the 93 included patients, the left and right cerebrospinal fluid regions were automatically extracted with a mean Dice similarity coefficient of 0.830. Receiver operating characteristic analysis indicated that hemispheric CSF ratio was an accurate marker for qualitative severe cerebral edema (area under receiver-operating-characteristic curve 0.867 [95% CI, 0.781-0.929]). Multivariate logistic regression analysis of functional prognosis showed that previous stroke (OR = 5.229, 95% CI 1.013-26.984), ASPECT≤6 (OR = 13.208, 95% CI 1.136-153.540) and low hemispheric CSF ratio (OR = 0.966, 95% CI 0.937-0.997) were significantly associated with higher chances for unfavorable functional outcome in patients with LHI.

Conclusions

Automated assessment of CSF volume provides an objective biomarker of cerebral edema that can be leveraged to quantify the degree of cerebral edema and confirm its predictive effect on outcomes after LHI.

SUBMITTER: Cui J

PROVIDER: S-EPMC10920171 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction.

Cui Junzhao J Yang Jingyi J Wang Ye Y Ma Meixin M Zhang Ning N Wang Rui R Zhou Biyi B Meng Chaoyue C Yang Peng P Yang Jianing J Xu Lei L Tan Guojun G Liu Lidou L Zhen Junli J Guo Li L Liu Xiaoyun X

Heliyon 20240219 5

<h4>Background and objective</h4>Cerebral edema (CED) is a serious complication of acute ischemic stroke (AIS), especially in patients with large hemispheric infarction (LHI). Herein, a deep learning-based approach is implemented to extract CSF from T2-Weighted Imaging (T2WI) and evaluate the relationship between quantified cerebrospinal fluid and outcomes.<h4>Methods</h4>Patients with acute LHI who underwent magnetic resonance imaging (MRI) were included. We used a deep learning algorithm to se ...[more]

PMID: 38463867

Similar Datasets

Project description:BackgroundMalignant cerebral edema (CED) complicates at least 20 % of large hemispheric infarcts (LHI) and may result in neurological deterioration or death. Midline shift (MLS) is a standard but crude measure of edema severity. We propose that volumetric analysis of shifts in cerebrospinal fluid (CSF) over time provides a reliable means of quantifying the spectrum of edema severity after LHI.MethodsWe identified 38 patients from 2008 to 2014 with NIHSS ≥8, baseline CT <6 h after stroke onset, at least 1 follow-up (FU) CT, and no parenchymal hematoma. The volumes of CSF (sulci, ventricles, and cisterns) ipsilateral (IL) and contralateral (CL) to infarct on baseline and FU CTs were quantified by manually assisted outlining with MIPAV image analysis software, as was infarct volume and MLS on FU CTs. Percentage change in CSF volumes (∆CSF) from baseline to FU scans was correlated with MLS and compared in those with vs. without malignant edema (defined as hemicraniectomy, osmotic therapy, or death/neurological deterioration with MLS ≥5 mm).Results11 of 38 subjects (29 %) developed malignant edema. Neither baseline NIHSS nor CSF volume differed between those with and without edema (median NIHSS 18 vs. 13, p = 0.12, CSF volume 102 vs. 124 ml, p = 0.16). Inter-rater reliability for CSF measurements was excellent (intraclass correlation coefficient 0.97). ∆CSF correlated strongly with MLS at peak edema (r = -0.75), even adjusting for infarct volume (p = 0.009). ∆CSF was also greater in those with malignant edema [-55 % (IQR -49 to -62) vs. -36 % (-27 to -45), p = 0.004]. ∆CSF was the greatest within IL sulci [-97 % (-86 to -99) vs. -71 % (-41 to -79), p = 0.002] but also significantly greater within CL sulci in those with malignant edema [-50 % (-29 to -65) vs. -25 % (0 to -31), p = 0.014]. More than half this CSF volume reduction occurred by the time of first FU CT around 24 h after stroke, while MLS rose later.ConclusionsVolumetric CSF analysis reliably quantifies CED and distinguishes those with malignant edema and MLS from those with a more benign course after LHI. ∆CSF may provide an earlier and more sensitive indicator of edema severity across a broader dynamic range than MLS.

Project description:Glyburide (also known as glibenclamide) is a second-generation sulfonylurea drug that inhibits sulfonylurea receptor 1 (Sur1) at nanomolar concentrations. Long used to target KATP (Sur1-Kir6.2) channels for the treatment of diabetes mellitus type 2, glyburide was recently repurposed to target Sur1-transient receptor potential melastatin 4 (Trpm4) channels in acute central nervous system injury. Discovered nearly two decades ago, SUR1-TRPM4 has emerged as a critical target in stroke, specifically in large hemispheric infarction, which is characterized by edema formation and life-threatening brain swelling. Following ischemia, SUR1-TRPM4 channels are transcriptionally upregulated in all cells of the neurovascular unit, including neurons, astrocytes, microglia, oligodendrocytes and microvascular endothelial cells. Work by several independent laboratories has linked SUR1-TRPM4 to edema formation, with blockade by glyburide reducing brain swelling and death in preclinical models. Recent work showed that, following ischemia, SUR1-TRPM4 co-assembles with aquaporin-4 to mediate cellular swelling of astrocytes, which contributes to brain swelling. Additionally, recent work linked SUR1-TRPM4 to secretion of matrix metalloproteinase-9 (MMP-9) induced by recombinant tissue plasminogen activator in activated brain endothelial cells, with blockade of SUR1-TRPM4 by glyburide reducing MMP-9 and hemorrhagic transformation in preclinical models with recombinant tissue plasminogen activator. The recently completed GAMES (Glyburide Advantage in Malignant Edema and Stroke) clinical trials on patients with large hemispheric infarctions treated with intravenous glyburide (RP-1127) revealed promising findings with regard to brain swelling (midline shift), MMP-9, functional outcomes and mortality. Here, we review key elements of the basic science, preclinical experiments and clinical studies, both retrospective and prospective, on glyburide in focal cerebral ischemia and stroke.

Project description:BackgroundSegmenting the whole heart over the cardiac cycle in 4D flow MRI is a challenging and time-consuming process, as there is considerable motion and limited contrast between blood and tissue.PurposeTo develop and evaluate a deep learning-based segmentation method to automatically segment the cardiac chambers and great thoracic vessels from 4D flow MRI.Study typeRetrospective.SubjectsA total of 205 subjects, including 40 healthy volunteers and 165 patients with a variety of cardiac disorders were included. Data were randomly divided into training (n = 144), validation (n = 20), and testing (n = 41) sets.Field strength/sequenceA 3 T/time-resolved velocity encoded 3D gradient echo sequence (4D flow MRI).AssessmentA 3D neural network based on the U-net architecture was trained to segment the four cardiac chambers, aorta, and pulmonary artery. The segmentations generated were compared to manually corrected atlas-based segmentations. End-diastolic (ED) and end-systolic (ES) volumes of the four cardiac chambers were calculated for both segmentations.Statistical testsDice score, Hausdorff distance, average surface distance, sensitivity, precision, and miss rate were used to measure segmentation accuracy. Bland-Altman analysis was used to evaluate agreement between volumetric parameters.ResultsThe following evaluation metrics were computed: mean Dice score (0.908 ± 0.023) (mean ± SD), Hausdorff distance (1.253 ± 0.293 mm), average surface distance (0.466 ± 0.136 mm), sensitivity (0.907 ± 0.032), precision (0.913 ± 0.028), and miss rate (0.093 ± 0.032). Bland-Altman analyses showed good agreement between volumetric parameters for all chambers. Limits of agreement as percentage of mean chamber volume (LoA%), left ventricular: 9.3%, 13.5%, left atrial: 12.4%, 16.9%, right ventricular: 9.9%, 15.6%, and right atrial: 18.7%, 14.4%; for ED and ES, respectively.Data conclusionThe addition of this technique to the 4D flow MRI assessment pipeline could expedite and improve the utility of this type of acquisition in the clinical setting.Evidence level4 TECHNICAL EFFICACY: Stage 1.

Project description:ObjectiveTo develop a deep learning (DL) model for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI and further develop a DL model for classifying axial spondyloarthritis (axSpA) and non-axSpA.Materials and methodsThis study retrospectively collected 706 patients with FM who underwent SIJ MRI from center 1 (462 axSpA and 186 non-axSpA) and center 2 (37 axSpA and 21 non-axSpA). Patients from center 1 were divided into the training, validation, and internal test sets (n = 455, 64, and 129). Patients from center 2 were used as the external test set. We developed a UNet-based model to segment FM. Based on segmentation results, a classification model was built to distinguish axSpA and non-axSpA. Dice Similarity Coefficients (DSC) and area under the curve (AUC) were used for model evaluation. Radiologists' performance without and with model assistance was compared to assess the clinical utility of the models.ResultsOur segmentation model achieved satisfactory DSC of 81.86% ± 1.55% and 85.44% ± 6.09% on the internal cross-validation and external test sets. The classification model yielded AUCs of 0.876 (95% CI: 0.811-0.942) and 0.799 (95% CI: 0.696-0.902) on the internal and external test sets, respectively. With model assistance, segmentation performance was improved for the radiological resident (DSC, 75.70% vs. 82.87%, p < 0.05) and expert radiologist (DSC, 85.03% vs. 85.74%, p > 0.05).ConclusionsDL is a novel method for automatic and accurate segmentation of FM on SIJ MRI and can effectively increase radiologist's performance, which might assist in improving diagnosis and progression of axSpA.Critical relevance statementDL models allowed automatic and accurate segmentation of FM on sacroiliac joint MRI, which might facilitate quantitative analysis of FM and have the potential to improve diagnosis and prognosis of axSpA.Key points• Deep learning was used for automatic segmentation of fat metaplasia on MRI. • UNet-based models achieved automatic and accurate segmentation of fat metaplasia. • Automatic segmentation facilitates quantitative analysis of fat metaplasia to improve diagnosis and prognosis of axial spondyloarthritis.

Dataset Information

Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction.

Background and objective

Methods

Results

Conclusions

Publications

Automatic segmentation of hemispheric CSF on MRI using deep learning: Quantifying cerebral edema following large hemispheric infarction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets