ICRP perspective on AI for radiation protection in imaging and radiotherapy

AI can improve radiation protection in medical imaging and radiotherapy through referral support, image reconstruction, and QA, but data bias and opaque models necessitate robust validation and AI literacy training, per an ICRP Committee 3 perspective.

• Mature AI applications include clinical decision support for referral appropriateness, image reconstruction, protocol optimization, automated contouring, treatment planning, adaptive radiotherapy, and QA.
• Emerging applications such as patient-specific dosimetry, occupational dose prediction, synthetic imaging, and predictive safety analytics require further validation.
• Implementation priorities: mitigate data bias, ensure continuous QA, harmonize regulation, and provide AI literacy training for healthcare professionals.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.