Nan Li1, Ruben Carmona1, Igor Sirak2, Linda Kasaova2, David Followill3, Jeff Michalski4, Walter Bosch4, William Straube4, Loren K Mell1, Kevin L Moore5. 1. Department of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California. 2. Department of Oncology and Radiotherapy, University Hospital, Hradec Kralove, Czech Republic. 3. Department of Radiation Physics, University of Texas MD Anderson Cancer Center, Houston, Texas. 4. Department of Radiation Oncology, Washington University in St Louis, St Louis, Missouri. 5. Department of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, California. Electronic address: kevinmoore@ucsd.edu.
Abstract
PURPOSE: To demonstrate an efficient method for training and validation of a knowledge-based planning (KBP) system as a radiation therapy clinical trial plan quality-control system. METHODS AND MATERIALS: We analyzed 86 patients with stage IB through IVA cervical cancer treated with intensity modulated radiation therapy at 2 institutions according to the standards of the INTERTECC (International Evaluation of Radiotherapy Technology Effectiveness in Cervical Cancer, National Clinical Trials Network identifier: 01554397) protocol. The protocol used a planning target volume and 2 primary organs at risk: pelvic bone marrow (PBM) and bowel. Secondary organs at risk were rectum and bladder. Initial unfiltered dose-volume histogram (DVH) estimation models were trained using all 86 plans. Refined training sets were created by removing sub-optimal plans from the unfiltered sample, and DVH estimation models… and DVH estimation models were constructed by identifying 30 of 86 plans emphasizing PBM sparing (comparing protocol-specified dosimetric cutpoints V10 (percentage volume of PBM receiving at least 10 Gy dose) and V20 (percentage volume of PBM receiving at least 20 Gy dose) with unfiltered predictions) and another 30 of 86 plans emphasizing bowel sparing (comparing V40 (absolute volume of bowel receiving at least 40 Gy dose) and V45 (absolute volume of bowel receiving at least 45 Gy dose), 9 in common with the PBM set). To obtain deliverable KBP plans, refined models must inform patient-specific optimization objectives and/or priorities (an auto-planning "routine"). Four candidate routines emphasizing different tradeoffs were composed, and a script was developed to automatically re-plan multiple patients with each routine. After selection of the routine that best met protocol objectives in the 51-patient training sample (KBPFINAL), protocol-specific DVH metrics and normal tissue complication probability were compared for original versus KBPFINAL plans across the 35-patient validation set. Paired t tests were used to test differences between planning sets. RESULTS: KBPFINAL plans outperformed manual planning across the validation set in all protocol-specific DVH cutpoints. The mean normal tissue complication probability for gastrointestinal toxicity was lower for KBPFINAL versus validation-set plans (48.7% vs 53.8%, P<.001). Similarly, the estimated mean white blood cell count nadir was higher (2.77 vs 2.49 k/mL, P<.001) with KBPFINAL plans, indicating lowered probability of hematologic toxicity. CONCLUSIONS: This work demonstrates that a KBP system can be efficiently trained and refined for use in radiation therapy clinical trials with minimal effort. This patient-specific plan quality control resulted in improvements on protocol-specific dosimetric endpoints.
PURPOSE: To demonstrate an efficient method for training and validation of a knowledge-based planning (KBP) system as a radiation therapy clinical trial plan quality-control system. METHODS AND MATERIALS: We analyzed 86 patients with stage IB through IVA cervical cancer treated with intensity modulated radiation therapy at 2 institutions according to the standards of the INTERTECC (International Evaluation of Radiotherapy Technology Effectiveness in Cervical Cancer, National Clinical Trials Network identifier: 01554397) protocol. The protocol used a planning target volume and 2 primary organs at risk: pelvic bone marrow (PBM) and bowel. Secondary organs at risk were rectum and bladder. Initial unfiltered dose-volume histogram (DVH) estimation models were trained using all 86 plans. Refined training sets were created by removing sub-optimal plans from the unfiltered sample, and DVH estimation models… and DVH estimation models were constructed by identifying 30 of 86 plans emphasizing PBM sparing (comparing protocol-specified dosimetric cutpoints V10 (percentage volume of PBM receiving at least 10 Gy dose) and V20 (percentage volume of PBM receiving at least 20 Gy dose) with unfiltered predictions) and another 30 of 86 plans emphasizing bowel sparing (comparing V40 (absolute volume of bowel receiving at least 40 Gy dose) and V45 (absolute volume of bowel receiving at least 45 Gy dose), 9 in common with the PBM set). To obtain deliverable KBP plans, refined models must inform patient-specific optimization objectives and/or priorities (an auto-planning "routine"). Four candidate routines emphasizing different tradeoffs were composed, and a script was developed to automatically re-plan multiple patients with each routine. After selection of the routine that best met protocol objectives in the 51-patient training sample (KBPFINAL), protocol-specific DVH metrics and normal tissue complication probability were compared for original versus KBPFINAL plans across the 35-patient validation set. Paired t tests were used to test differences between planning sets. RESULTS: KBPFINAL plans outperformed manual planning across the validation set in all protocol-specific DVH cutpoints. The mean normal tissue complication probability for gastrointestinal toxicity was lower for KBPFINAL versus validation-set plans (48.7% vs 53.8%, P<.001). Similarly, the estimated mean white blood cell count nadir was higher (2.77 vs 2.49 k/mL, P<.001) with KBPFINAL plans, indicating lowered probability of hematologic toxicity. CONCLUSIONS: This work demonstrates that a KBP system can be efficiently trained and refined for use in radiation therapy clinical trials with minimal effort. This patient-specific plan quality control resulted in improvements on protocol-specific dosimetric endpoints.
Authors: David Good; Joseph Lo; W Robert Lee; Q Jackie Wu; Fang-Fang Yin; Shiva K Das Journal: Int J Radiat Oncol Biol Phys Date: 2013-04-25 Impact factor: 7.038
Authors: Benjamin E Nelms; Greg Robinson; Jay Markham; Kyle Velasco; Steve Boyd; Sharath Narayan; James Wheeler; Mark L Sobczak Journal: Pract Radiat Oncol Date: 2012-01-10
Authors: Daniel R Simpson; William Y Song; Vitali Moiseenko; Brent S Rose; Catheryn M Yashar; Arno J Mundt; Loren K Mell Journal: Int J Radiat Oncol Biol Phys Date: 2012-05-01 Impact factor: 7.038
Authors: Binbin Wu; Francesco Ricchetti; Giuseppe Sanguineti; Misha Kazhdan; Patricio Simari; Ming Chuang; Russell Taylor; Robert Jacques; Todd McNutt Journal: Med Phys Date: 2009-12 Impact factor: 4.071
Authors: Tahir Yusufaly; Austin Miller; Ana Medina-Palomo; Casey W Williamson; Hannah Nguyen; Jessica Lowenstein; Charles A Leath; Ying Xiao; Kevin L Moore; Katherine M Moxley; Carlos M Chevere-Mourino; Tony Y Eng; Tarrick Zaid; Loren K Mell Journal: Int J Radiat Oncol Biol Phys Date: 2020-07-03 Impact factor: 7.038
Authors: Kelly C Younge; Robin B Marsh; Dawn Owen; Huaizhi Geng; Ying Xiao; Daniel E Spratt; Joseph Foy; Krithika Suresh; Q Jackie Wu; Fang-Fang Yin; Samuel Ryu; Martha M Matuszak Journal: Int J Radiat Oncol Biol Phys Date: 2018-01-04 Impact factor: 7.038
Authors: James A Kavanaugh; Sarah Holler; Todd A DeWees; Clifford G Robinson; Jeffrey D Bradley; Puneeth Iyengar; Kristin A Higgins; Sasa Mutic; Lindsey A Olsen Journal: Pract Radiat Oncol Date: 2018-12-15
Authors: Adenike Olanrewaju; Laurence E Court; Lifei Zhang; Komeela Naidoo; Hester Burger; Sameera Dalvie; Julie Wetter; Jeannette Parkes; Christoph J Trauernicht; Rachel E McCarroll; Carlos Cardenas; Christine B Peterson; Kathryn R K Benson; Monique du Toit; Ricus van Reenen; Beth M Beadle Journal: Pract Radiat Oncol Date: 2021-02-25