Bayesian deep learning outperforms clinical trial estimators of intracerebral and intraventricular hemorrhage volume

Intracerebral hemorrhage (ICH) and intraventricular hemorrhage (IVH) clinical trials rely on manual linear and semi‐quantitative (LSQ) estimators like the ABC/2, modified Graeb and IVH scores for timely volumetric estimation from CT. Deep learning (DL) volumetrics of ICH have recently approached the accuracy of gold‐standard planimetry. However, DL and LSQ strategies have been limited by unquantified uncertainty, in particular when ICH and IVH estimates intersect. Bayesian deep learning methods can be used to approximate uncertainty, presenting an opportunity to improve quality assurance in clinical trials.

• Publication year

  2022

• Venue

  Journal of Neuroimaging

• Publication date

  2022-04-17

• Fields of study

  Medicine

• Identifiers
  DOI 10.1111/jon.12997PMID 35434846PMCID PMC9474710
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema

  2021cited by this paper
• Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoring

  2021cited by this paper
• Multiclass semantic segmentation and quantification of traumatic brain injury lesions on head CT using deep learning: an algorithm development and multicentre validation study.

  2020cited by this paper
• Evaluating White Matter Lesion Segmentations with Refined Sørensen-Dice Analysis

  2020cited by this paper
• 3D Deep Neural Network Segmentation of Intracerebral Hemorrhage: Development and Validation for Clinical Trials

  2020cited by this paper
• Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation

  2020cited by this paper
• Quantitative Comparison of Monte-Carlo Dropout Uncertainty Measures for Multi-class Segmentation

  2020cited by this paper
• Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation

  2020cited by this paper
• Dilated Dense U-Net for Infant Hippocampus Subfield Segmentation

  2019cited by this paper
• Fully Automated Segmentation Algorithm for Hematoma Volumetric Analysis in Spontaneous Intracerebral Hemorrhage.

  2019cited by this paper
• Efficacy and safety of minimally invasive surgery with thrombolysis in intracerebral haemorrhage evacuation (MISTIE III): a randomised, controlled, open-label, blinded endpoint phase 3 trial.

  2019cited by this paper
• Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images

  2018cited by this paper
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks

  2018cited by this paper
• Bayesian convolutional neural network based MRI brain extraction on nonhuman primates

  2018cited by this paper
• Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentation

  2018cited by this paper
• On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task

  2017cited by this paper
• Thrombolytic removal of intraventricular haemorrhage in treatment of severe stroke: results of the randomised, multicentre, multiregion, placebo-controlled CLEAR III trial.

  2017cited by this paper
• V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

  2016cited by this paper
• Safety and efficacy of minimally invasive surgery plus recombinant tissue plasminogen activator in intracerebral haemorrhage evacuation (MISTIE): a randomised, phase 2 trial

  2016cited by this paper
• The Safety and Feasibility of Image-Guided BrainPath-Mediated Transsulcul Hematoma Evacuation: A Multicenter Study

  2016cited by this paper
• Multi-Scale Context Aggregation by Dilated Convolutions

  2015cited by this paper
• Accuracy of the ABC/2 Score for Intracerebral Hemorrhage: Systematic Review and Analysis of MISTIE, CLEAR-IVH, and CLEAR III

  2015cited by this paper
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

  2015cited by this paper
• Validated automatic brain extraction of head CT images

  2015cited by this paper
• Spontaneous intracerebral and intraventricular hemorrhage: advances in minimally invasive surgery and thrombolytic evacuation, and lessons learned in recent trials.

  2014cited by this paper
• Spontaneous Intracerebral and Intraventricular Hemorrhage: Advances in Minimally Invasive Surgery and Thrombolytic Evacuation, and Lessons Learned in Recent Trials.

  2014cited by this paper
• The Modified Graeb Score: An Enhanced Tool for Intraventricular Hemorrhage Measurement and Prediction of Functional Outcome

  2013cited by this paper
• Evaluation of intraventricular hemorrhage assessment methods for predicting outcome following intracerebral hemorrhage.

  2012cited by this paper
• Defining hematoma expansion in intracerebral hemorrhage

  2011cited by this paper
• Volume-dependent overestimation of spontaneous intracerebral hematoma volume by the ABC/2 formula

  2009cited by this paper
• The IVH Score: A novel tool for estimating intraventricular hemorrhage volume: Clinical and research implications*

  2009cited by this paper
• Efficacy and safety of recombinant activated factor VII for acute intracerebral hemorrhage.

  2008cited by this paper
• Preliminary report of the clot lysis evaluating accelerated resolution of intraventricular hemorrhage (CLEAR-IVH) clinical trial.

  2008cited by this paper
• Intensive blood pressure reduction in acute cerebral haemorrhage trial (INTERACT): a randomised pilot trial.

  2008cited by this paper
• Intraventricular hemorrhage and hydrocephalus after spontaneous intracerebral hemorrhage: results from the STICH trial.

  2006cited by this paper
• Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation

  2004cited by this paper
• Efficient Implementation of Marching Cubes' Cases with Topological Guarantees

  2003cited by this paper
• The ICH score: a simple, reliable grading scale for intracerebral hemorrhage.

  2001cited by this paper
• Bayesian approach for neural networks--review and case studies

  2001cited by this paper
• The ICH Score

  2001cited by this paper
• Volume of ventricular blood is an important determinant of outcome in supratentorial intracerebral hemorrhage.

  1999cited by this paper
• The ABCs of measuring intracerebral hemorrhage volumes.

  1996cited by this paper
• Volume of Intracerebral Hemorrhage: A Powerful and Easy‐to‐Use Predictor of 30‐Day Mortality

  1993cited by this paper
• Intracerebral hemorrhage: External validation and extension of a model for prediction of 30‐day survival

  1991cited by this paper
• Prognostic significance of ventricular blood in supratentorial hemorrhage

  1990cited by this paper
• Primary intraventricular hemorrhage in adults.

  1986cited by this paper
• Computed tomographic diagnosis of intraventricular hemorrhage. Etiology and prognosis.

  1982cited by this paper
• Measures of the Amount of Ecologic Association Between Species

  1945cited by this paper
• Ieee Transactions on Knowledge and Data Engineering 1 towards Bayesian Deep Learning: a Framework and Some Existing Methods

  year unknowncited by this paper

• Operationalizing a complex acute clinical trial: Lessons from the BEACH study

  2025cites this paper
• Differentiating central fever from infectious fever in intracerebral haemorrhage

  2025cites this paper
• Strategies to Improve the Robustness and Generalizability of Deep Learning Segmentation and Classification in Neuroimaging

  2025cites this paper
• Artificial intelligence in clinical trials: A comprehensive review of opportunities, challenges, and future directions

  2025cites this paper
• Deep learning models for separate segmentations of intracerebral and intraventricular hemorrhage on head CT and segmentation quality assessment.

  2024cites this paper
• Do Deep Learning Algorithms Accurately Segment Intracerebral Hemorrhages on Noncontrast Computed Tomography? A Systematic Review and Meta‐Analysis

  2024cites this paper
• Prediction of hematoma expansion in spontaneous intracerebral hemorrhage using a multimodal neural network

  2024cites this paper
• Unified ICH quantification and prognosis prediction in NCCT images using a multi-task interpretable network

  2023cites this paper
• Multi-Method Diagnosis of CT Images for Rapid Detection of Intracranial Hemorrhages Based on Deep and Hybrid Learning

  2022cites this paper
• Automated identification and quantification of traumatic brain injury from CT scans: Are we there yet?

  2022influential citation