Artificial intelligence in diagnostic imaging: collaborative asset or looming replacement?

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Clinical Diagnostics

Background:

• Artificial intelligence (AI) is rapidly advancing in diagnostic imaging.
• Key questions arise regarding AI's role: collaboration versus replacement of human expertise.
• Current evidence on AI applications, clinical, ethical, and legal challenges require review.

Purpose of the Study:

• To review current evidence on AI applications in diagnostic imaging.
• To focus on the clinical, ethical, and legal challenges posed by AI.
• To advocate for responsible AI implementation in healthcare.

Main Methods:

• Review of current evidence on AI in diagnostic imaging.
• Discussion of clinical, ethical, and legal challenges.
• Analysis of financial and practical implications of AI integration.

Main Results:

• AI models show promise in detecting abnormalities and optimizing workflows.
• Many AI models are limited by narrow datasets and lack external validation.
• Ethical issues include algorithm transparency, bias, accountability, and regulatory oversight needs.

Conclusions:

• Radiologists remain crucial for image interpretation and validating AI outputs.
• Overreliance on AI risks eroding diagnostic skills; responsible implementation is key.
• AI should support, not replace, healthcare professionals' expertise and judgment.