Intelligent imaging: Applications of machine learning and deep learning in radiology.

Area of Science:

• Radiology and Medical Imaging
• Artificial Intelligence
• Computer-Aided Diagnosis

Background:

• Artificial intelligence (AI) is increasingly integrated into medical imaging workflows.
• Existing AI applications focus on triaging and radiomic feature analysis.
• AI offers significant potential for improving image quality and diagnostic accuracy.

Purpose of the Study:

• To highlight the transformative impact of AI in radiology.
• To discuss key AI applications beyond initial reporting and feature analysis.
• To explore the implications of AI for both human and veterinary radiology.

Main Methods:

• Review of current AI applications in radiological image analysis.
• Discussion of AI's role in image optimization, reconstruction, and artifact reduction.
• Comparative analysis of AI benefits and risks in human and veterinary contexts.

Main Results:

• AI significantly enhances noise reduction and image optimization after dose reduction.
• AI enables direct image reconstruction from projection data and pseudo-CT generation for attenuation correction.
• AI applications are already augmenting human-led radiology and are relevant to veterinary practices.

Conclusions:

• AI is crucial for advancing medical image analysis in radiology.
• AI integration promises improved efficiency and diagnostic capabilities.
• The future of radiology involves human-AI collaboration and AI autonomy.