Systematic review of artificial intelligence in brachytherapy

Area of Science:

• Medical Physics
• Radiotherapy Oncology
• Artificial Intelligence in Medicine

Background:

• Brachytherapy (BT) is a crucial radiotherapy technique.
• The integration of artificial intelligence (AI), including deep learning and machine learning, is rapidly evolving in medical applications.
• Optimizing BT workflows and outcomes is an ongoing clinical challenge.

Purpose of the Study:

• To systematically review the scientific literature on the application of AI in brachytherapy.
• To compare AI methods quantitatively and/or qualitatively with current clinical standards in BT.
• To identify trends and potential benefits of AI in BT planning and delivery.

Main Methods:

• Systematic literature review adhering to PRISMA guidelines.
• Searched PubMed, Google Scholar, Cochrane Library, and multi-institutional databases (1980-2025).
• Included peer-reviewed articles focusing on AI in BT, analyzing AI methods, datasets, and clinical outcomes.

Main Results:

• 232 studies met inclusion criteria from over 10,820 initial results.
• AI applications span applicator reconstruction, segmentation, imaging, dose calculation, and outcome prediction.
• AI demonstrated potential for producing clinically acceptable planning data significantly faster than current methods.

Conclusions:

• AI holds significant potential to enhance efficiency and reduce human effort in brachytherapy.
• Current literature is predominantly retrospective, highlighting a need for prospective validation.
• AI integration may revolutionize repetitive tasks in BT, leading to improved clinical workflows.