Cerebral aneurysm evolution modeling from microstructural computational models to machine learning: A review

Area of Science:

• Biomedical Engineering
• Computational Biology
• Medical Imaging Analysis

Background:

• Cerebral aneurysms pose a rupture risk, necessitating treatment decisions based on size and risk factors.
• Current methods may miss smaller aneurysms with high growth and rupture potential.
• Accurate prediction of aneurysm behavior is vital for patient management.

Purpose of the Study:

• To review computational growth models for cerebral aneurysms.
• To describe morphological and clinical risk factors influencing aneurysm behavior.
• To discuss integrating computational models with machine learning for improved prediction tools.

Main Methods:

• Review of existing computational growth models for cerebral aneurysms.
• Analysis of morphological and clinical risk factors.
• Exploration of machine learning integration with computational models.

Main Results:

• Identification of various computational growth models applicable to cerebral aneurysms.
• Cataloging of key geometrical and clinical risk factors.
• Discussion on methodologies for combining predictive models with AI.

Conclusions:

• Computational models and AI offer a promising approach to predict aneurysm growth and rupture risk.
• Integrating vascular microstructure, disease mechanisms, and risk factors is key.
• This review provides a foundation for developing advanced predictive tools for clinical use.