Imaging studies for predicting hematoma expansion: from traditional imaging signs to artificial intelligence-based multimodal fusion - Report - MDSpire

Imaging studies for predicting hematoma expansion: from traditional imaging signs to artificial intelligence-based multimodal fusion

  • By

  • Jie Wu

  • Jinping Sheng

  • Yu Xiao

  • Fa Wu

  • Pingping He

  • Rui Jiang

  • Zhiwei Zuo

  • Peng Wang

  • June 26, 2026

  • 0 min

Share

Clinical Report: Advancements in Imaging Techniques for Forecasting Hematoma Expansion

Overview

This review outlines the evolution of imaging-based prediction of hematoma expansion (HE) following acute intracerebral hemorrhage (ICH). It highlights the transition from traditional imaging markers to AI-driven methodologies.

Background

Hematoma expansion is a critical event following ICH, significantly impacting patient morbidity and mortality. Accurate prediction of HE is essential for timely interventions. The burden of ICH is particularly high in regions like China.

Data Highlights

No numerical data available in the source material.

Key Findings

  • HE is defined as a significant increase in hematoma volume, traditionally measured as >6 mL or >33% growth.
  • Revised hematoma expansion (rHE) incorporates intraventricular hemorrhage growth, improving sensitivity for predicting poor outcomes.
  • AI-driven methods, including radiomics and deep learning, have shown potential in outperforming traditional imaging markers.
  • Challenges in model generalizability and interpretability remain significant barriers to clinical implementation.
  • Future directions include federated learning and explainable AI to enhance predictive accuracy.

Clinical Implications

Clinicians should consider the evolving definitions and methodologies for predicting HE, particularly the incorporation of AI techniques.

Conclusion

The transition to AI-enhanced multimodal approaches represents a significant advancement in the prediction of hematoma expansion.

Related Resources & Content

  1. Author(s)/Org, Source, Year -- Title
  2. Author(s)/Org, Source, Year -- Title
  3. Author(s)/Org, Source, Year -- Title
  4. Author(s)/Org, Source, Year -- Title
  5. European Radiology — Predictive Features of Non-contrast CT for Growth of Intraventricular Hemorrhage
  6. 2022 Guideline for the Management of Patients With Spontaneous Intracerebral Hemorrhage
  7. European Stroke Organisation (ESO) and European Association of Neurosurgical Societies (EANS) guideline on stroke due to spontaneous intracerebral haemorrhage
  8. Tranexamic acid versus placebo in individuals with intracerebral haemorrhage treated within 2 h of symptom onset (STOP-MSU): an international, double-blind, randomised, phase 2 trial - ScienceDirect
  9. Redefining Hematoma Expansion With the Inclusion of Intraventricular Hemorrhage Growth | CoLab
  10. Ultraearly Hematoma Growth in Acute Spontaneous Intracerebral Hemorrhage Predicts Early and Long-Term Poor Clinical Outcomes: A Prospective, Observational Cohort Study
  11. Ultra-early hematoma expansion is associated with ongoing hematoma growth and poor functional outcome | medRxiv
  12. Computed tomography in acute intracerebral hemorrhage: neuroimaging predictors of hematoma expansion and outcome | Insights into Imaging | Springer Nature Link
  13. (PDF) Co-localization of NCCT hypodensity and CTA spot sign predicts substantial intracerebral hematoma expansion: The Black-&-White sign
  14. Frontiers | The clinical potential of radiomics to predict hematoma expansion in spontaneous intracerebral hemorrhage: a narrative review
  15. Can artificial intelligence accurately predict the risk of hematoma expansion in intracerebral hemorrhage? A systematic review and Meta-analysis of 7,665 patients - PubMed
  16. HemExp: Clinically-Guided Latent Diffusion for Modeling Hematoma Expansion

Original Source(s)

Related Content