Encrypted login | home

Program Information

Patient-Specific Prediction Guided Automatic Treatment Planning for Intensity Modulated Radiotherapy

T Song

Y Mai1 , Y Li2 , L Zhou1 , T Song1*, (1) Southern Medical University, Guangzhou, Guangdong, (2) Image Processing Center, Beihang University, Beijing, Beijing,


SU-I-GPD-T-333 (Sunday, July 30, 2017) 3:00 PM - 6:00 PM Room: Exhibit Hall

Purpose: To propose a novel automatic treatment planning framework for intensity modulated radiation therapy.

Methods: The automation was achieved by incorporating a patient-specific dosimetric endpoint prediction and thereupon prediction-oriented multi-criteria optimization. An in-house developed geometric-dosimetric prediction model was firstly performed to afford a close-to-optimal DVH endpoint, as the initial goals to the following priority list. Afterwards, the automatic multi-criteria optimization was motivated by gradually tuning goals according to a priority list order. Elements within the list were planning goals for ROI endpoint, and they were classified and sequenced according to its clinical importance. Both a relaxing and a tightening round were carried to traverse and assure the optimality of every endpoint, by adjusting criteria gradually from low to high priority, and in reverse the other round. Four GYN IMRT plans were collected to evaluate the feasibility and efficiency of our method. Both ROI's DVH and detailed dosimetric endpoint were compared for the original (clinical) plan and our automatic plan.

Results: DVH comparison show quality improvement for our proposed method, with comparable DVHs for the PTV but further dose sparing for most OARs, without any trade-offs. For the PTV, An average minimum dose was from 37.1Gy to 37.3Gy, and maximum dose from 49.9Gy to 49.7Gy, for the original plan and automatic plan, respectively. Average dose was decreased from 41.8Gy to 40Gy, and 42.2Gy to 37.9Gy for the rectum and bladder, respectively. Among these, average V40 of the rectum and bladder is decreased from 80.1% to 68.1%, and 64.8% to 54.6%, for clinical plan and automatic plan, respectively. Further dose sparing could be observed for other OARs.

Conclusion: We have successfully developed a patient-specific prediction guided automatic treatment planning framework for intensity modulated radiation therapy. This method can not only raise the routine working efficient, but also assure the plan quality.

Funding Support, Disclosures, and Conflict of Interest: This work is supported by the National Natural Science Foundation of China (No.81601577,81571771),China Postdoctoral Science Foundation and the National Natural Science Foundation of China (No.2016M592510), and Southern Medical University School start-up fund(No.LX2016N0004)

Contact Email: