Computer-aided imaging analysis in acute ischemic stroke - background and clinical applications.

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Neurology

Background:

• Medical image analysis tools are crucial for detecting abnormalities and improving diagnostic accuracy.
• Artificial intelligence (AI) and machine learning (ML) have significantly advanced medical imaging interpretation over the last decade.
• Automatic evaluation of acute ischemic stroke is a key area of development in medical imaging.

Purpose of the Study:

• To review the advancements in computer-aided diagnosis for acute ischemic stroke.
• To focus on the automatic analysis of non-contrast-enhanced computed tomography, computed tomography angiography, and perfusion imaging.
• To highlight the role of AI/ML in supporting physicians and standardizing acute stroke treatment.

Main Methods:

• Review of current literature and commercially available AI/ML-based tools for stroke imaging.
• Focus on analysis techniques for non-contrast CT, CT angiography, and perfusion imaging.
• Discussion of the complementary role of these tools in clinical practice.

Main Results:

• AI and ML tools show significant improvements in medical imaging interpretation for stroke.
• Commercial products can identify and quantify ischemic core, penumbra, arterial occlusion, and collateral flow.
• These tools are intended to support, not replace, physician interpretation for acute treatment selection.

Conclusions:

• AI/ML tools offer complementary support for physicians in diagnosing acute ischemic stroke.
• Further studies are needed to evaluate and compare different imaging strategies and algorithms.
• Standardization of treatment and stroke management can be facilitated through advanced imaging analysis.