Artificial Intelligence in Radiotherapy Treatment Planning: Present and Future

Area of Science:

• Medical Physics
• Radiotherapy
• Computer Science

Background:

• Radiotherapy treatment planning is critical for minimizing normal tissue damage and ensuring tumor control.
• Sophisticated computer science has enabled complex treatment plans but increased labor intensity.
• Traditional planning involves time-consuming, trial-and-error optimization for individual patients.

Purpose of the Study:

• To review current AI-driven smart planning tools in radiotherapy.
• To explore novel AI applications, including deep learning in treatment planning.
• To discuss challenges and future directions for AI in radiotherapy planning.

Main Methods:

• Categorization of current clinical AI tools into automated rule implementation, prior knowledge modeling, and multicriteria optimization.
• Review of novel AI-based applications and emerging research.
• Discussion of challenges associated with AI implementation in radiotherapy.

Main Results:

• AI tools significantly improve radiotherapy treatment planning efficiency and consistency.
• Current AI applications focus on automation and optimization of dosimetric trade-offs.
• Deep learning and other novel AI approaches show promise for future advancements.

Conclusions:

• AI-powered tools are transforming radiotherapy planning, enhancing efficiency and plan quality.
• Further research and development are needed to address the challenges of AI implementation.
• AI holds significant potential to further optimize radiotherapy workflows and patient outcomes.