# Deep learning and high-resolution magnetic resonance vascular wall imaging: current challenges and future perspectives

## TL;DR

This paper reviews how deep learning can improve high-resolution MRI of brain vessel walls, making it more reliable and useful for diagnosing cerebrovascular diseases.

## Contribution

The paper provides a comprehensive review of deep learning applications in high-resolution vascular wall imaging for intracranial diseases.

## Key findings

- Deep learning can enhance the reliability of high-resolution vascular wall imaging.
- DL models assist in identifying various intracranial vascular lesions like aneurysms and arteriosclerosis.
- DL has potential as a diagnostic tool for cerebrovascular diseases.

## Abstract

High-resolution magnetic resonance vessel wall imaging (HR-VWI) is an advanced MR imaging technique that can directly visualize intracranial vessel walls and detect subtle pathological changes. HR-VWI can improve diagnostic confidence, help differentiate intracranial vascular diseases, and assist in patient risk stratification and prognosis. However, HR-VWI relies heavily on operator experience and is therefore unreliable in inexperienced hands. Deep learning (DL) is considered a leading artificial intelligence tool in image analysis. DL algorithms excel at image recognition by leveraging multimodal data, making them valuable in medical imaging. Recently, a growing number of studies have proposed the use of DL models as tools to support radiologists and overcome the inherent challenges of MR imaging. DL has numerous clinical applications in cerebral angiography, including the identification of intracranial aneurysms, arteriovenous malformations, arteriosclerosis, and moyamoya disease. This article comprehensively reviews the fundamentals of DL and its applications in HR-VWI, with a particular focus on its clinical applications in assessing various intracranial vascular lesions. DL-assisted HR-VWI has the potential to become an important ancillary diagnostic tool for cerebrovascular diseases.