Literature DB >> 34417703

Accelerating Prediction of Malignant Cerebral Edema After Ischemic Stroke with Automated Image Analysis and Explainable Neural Networks.

Hossein Mohammadian Foroushani1, Ali Hamzehloo2, Atul Kumar2, Yasheng Chen2, Laura Heitsch3, Agnieszka Slowik4, Daniel Strbian5, Jin-Moo Lee2, Daniel S Marcus6, Rajat Dhar7.   

Abstract

BACKGROUND: Malignant cerebral edema is a devastating complication of stroke, resulting in deterioration and death if hemicraniectomy is not performed prior to herniation. Current approaches for predicting this relatively rare complication often require advanced imaging and still suffer from suboptimal performance. We performed a pilot study to evaluate whether neural networks incorporating data extracted from routine computed tomography (CT) imaging could enhance prediction of edema in a large diverse stroke cohort.
METHODS: An automated imaging pipeline retrospectively extracted volumetric data, including cerebrospinal fluid (CSF) volumes and the hemispheric CSF volume ratio, from baseline and 24 h CT scans performed in participants of an international stroke cohort study. Fully connected and long short-term memory (LSTM) neural networks were trained using serial clinical and imaging data to predict those who would require hemicraniectomy or die with midline shift. The performance of these models was tested, in comparison with regression models and the Enhanced Detection of Edema in Malignant Anterior Circulation Stroke (EDEMA) score, using cross-validation to construct precision-recall curves.
RESULTS: Twenty of 598 patients developed malignant edema (12 required surgery, 8 died). The regression model provided 95% recall but only 32% precision (area under the precision-recall curve [AUPRC] 0.74), similar to the EDEMA score (precision 28%, AUPRC 0.66). The fully connected network did not perform better (precision 33%, AUPRC 0.71), but the LSTM model provided 100% recall and 87% precision (AUPRC 0.97) in the overall cohort and the subgroup with a National Institutes of Health Stroke Scale (NIHSS) score ≥ 8 (p = 0.0001 vs. regression and fully connected models). Features providing the most predictive importance were the hemispheric CSF ratio and NIHSS score measured at 24 h.
CONCLUSIONS: An LSTM neural network incorporating volumetric data extracted from routine CT scans identified all cases of malignant cerebral edema by 24 h after stroke, with significantly fewer false positives than a fully connected neural network, regression model, and the validated EDEMA score. This preliminary work requires prospective validation but provides proof of principle that a deep learning framework could assist in selecting patients for surgery prior to deterioration.
© 2021. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.

Entities:  

Keywords:  Brain computed tomography scan; Brain edema; Cerebral infarction; Deep learning; Early diagnosis

Mesh:

Year:  2021        PMID: 34417703      PMCID: PMC8858326          DOI: 10.1007/s12028-021-01325-x

Source DB:  PubMed          Journal:  Neurocrit Care        ISSN: 1541-6933            Impact factor:   3.210


  3 in total

1.  Response by Kauw et al to Letter Regarding Article, "Intracranial Cerebrospinal Fluid Volume as a Predictor of Malignant Middle Cerebral Artery Infarction".

Authors:  Frans Kauw; Birgitta K Velthuis; Jan W Dankbaar
Journal:  Stroke       Date:  2019-08-27       Impact factor: 7.914

2.  Hemispheric CSF volume ratio quantifies progression and severity of cerebral edema after acute hemispheric stroke.

Authors:  Rajat Dhar; Ali Hamzehloo; Atul Kumar; Yasheng Chen; June He; Laura Heitsch; Agnieszka Slowik; Daniel Strbian; Jin-Moo Lee
Journal:  J Cereb Blood Flow Metab       Date:  2021-05-20       Impact factor: 6.200

3.  Quantitative Serial CT Imaging-Derived Features Improve Prediction of Malignant Cerebral Edema after Ischemic Stroke.

Authors:  Hossein Mohammadian Foroushani; Ali Hamzehloo; Atul Kumar; Yasheng Chen; Laura Heitsch; Agnieszka Slowik; Daniel Strbian; Jin-Moo Lee; Daniel S Marcus; Rajat Dhar
Journal:  Neurocrit Care       Date:  2020-07-29       Impact factor: 3.210

  3 in total
  3 in total

1.  Natural Language Processing of Radiology Reports to Detect Complications of Ischemic Stroke.

Authors:  Matthew I Miller; Agni Orfanoudaki; Michael Cronin; Hanife Saglam; Ivy So Yeon Kim; Oluwafemi Balogun; Maria Tzalidi; Kyriakos Vasilopoulos; Georgia Fanaropoulou; Nina M Fanaropoulou; Jack Kalin; Meghan Hutch; Brenton R Prescott; Benjamin Brush; Emelia J Benjamin; Min Shin; Asim Mian; David M Greer; Stelios M Smirnakis; Charlene J Ong
Journal:  Neurocrit Care       Date:  2022-05-09       Impact factor: 3.532

2.  Commentary on "Midline Shift Greater than 3 mm Independently Predicts Outcome After Ischemic Stroke".

Authors:  Rajat Dhar
Journal:  Neurocrit Care       Date:  2021-09-27       Impact factor: 3.210

Review 3.  Evaluation and Prediction of Post-stroke Cerebral Edema Based on Neuroimaging.

Authors:  Xiaocheng Zhang; Peiyu Huang; Ruiting Zhang
Journal:  Front Neurol       Date:  2022-01-11       Impact factor: 4.003

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.