Adaptive Proton Therapy Using CBCT-Guided Digital Twins.

Area of Science:

• Medical Physics
• Radiation Oncology
• Computational Biology

Background:

• Prostate stereotactic body radiation therapy (SBRT) is a preferred radiotherapy due to efficacy and shorter treatment times.
• Interfractional anatomical variations can compromise treatment accuracy and patient outcomes in prostate SBRT.
• Existing methods lack robust strategies to mitigate uncertainties arising from daily anatomical changes during treatment.

Approach:

• Development of a novel digital twin (DT) framework specifically for adaptive proton SBRT in prostate cancer.
• Integration of patient-specific setup uncertainties into the DT framework for enhanced treatment planning.
• Leveraging DT technology to create dynamic, adaptive treatment strategies tailored to individual patient anatomy.

Key Points:

• The DT framework enables real-time adaptation of proton SBRT plans based on interfractional variations.
• Utilizes patient-specific CTV setup uncertainty, which is typically smaller than conventional clinical setups.
• Demonstrates a pioneering approach to personalized radiotherapy through advanced computational modeling.

Conclusions:

• The proposed digital twin framework significantly enhances adaptive proton SBRT for prostate cancer.
• Addresses interfractional uncertainties, leading to improved treatment quality and potentially better patient outcomes.
• Offers a pathway towards personalized radiotherapy solutions, improving quality of life for prostate cancer patients.