G Guidi1, N Maffei2, B Meduri3, E D'Angelo3, G M Mistretta2, P Ceroni2, A Ciarmatori4, A Bernabei2, S Maggi5, M Cardinali6, V E Morabito5, F Rosica7, S Malara8, A Savini7, G Orlandi7, C D'Ugo8, F Bunkheila9, M Bono10, S Lappi10, C Blasi9, F Lohr3, T Costi2. 1. Medical Physics Department, Az. Ospedaliero Universitaria di Modena, Italy; Physics Department, Alma Mater Studiorum University of Bologna, Italy. Electronic address: guidi.gabriele@policlinico.mo.it. 2. Medical Physics Department, Az. Ospedaliero Universitaria di Modena, Italy. 3. Radiation Oncology Department, Az. Ospedaliero Universitaria di Modena, Italy. 4. Medical Physics Department, Az. Ospedaliero Universitaria di Modena, Italy; Radiotherapy Unit, Altnagelvin Hospital, Londonderry, United Kingdom. 5. Medical Physics Department, Az.Ospedaliero-Universitaria Ospedale Riuniti di Ancona, Italy. 6. Radiation Oncology Department, Az.Ospedaliero-Universitaria Ospedale Riuniti di Ancona, Italy. 7. Medical Physics Department, AUSL4 Teramo, Italy. 8. Radiation Oncology Department, AUSL4 Teramo, Italy. 9. Radiation Oncology Department, Az.Osp.Ospedali Riuniti Marche Nord di Pesaro, Italy. 10. Medical Physics Department, Az.Osp.Ospedali Riuniti Marche Nord di Pesaro, Italy.
Abstract
PURPOSE: To predict patients who would benefit from adaptive radiotherapy (ART) and re-planning intervention based on machine learning from anatomical and dosimetric variations in a retrospective dataset. MATERIALS AND METHODS: 90 patients (pts) treated for head-neck cancer (H&N) formed a multicenter data-set. 41 H&N pts (45.6%) were considered for learning; 49 pts (54.4%) were used to test the tool. A homemade machine-learning classifier was developed to analyze volume and dose variations of parotid glands (PG). Using deformable image registration (DIR) and GPU, patients' conditions were analyzed automatically. Support Vector Machines (SVM) was used for time-series evaluation. "Inadequate" class identified patients that might benefit from replanning. Double-blind evaluation by two radiation oncologists (ROs) was carried out to validate day/week selected for re-planning by the classifier. RESULTS: The cohort was affected by PG mean reduction of 23.7±8.8%. During the first 3weeks, 86.7% cases show PG deformation aligned with predefined tolerance, thus not requiring re-planning. From 4th week, an increased number of pts would potentially benefit from re-planning: a mean of 58% of cases, with an inter-center variability of 8.3%, showed "inadequate" conditions. 11% of cases showed "bias" due to DIR and script failure; 6% showed "warning" output due to potential positioning issues. Comparing re-planning suggested by tool with recommended by ROs, the 4th week seems the most favorable time in 70% cases. CONCLUSIONS: SVM and decision-making tool was applied to overcome ART challenges. Pts would benefit from ART and ideal time for re-planning intervention was identified in this retrospective analysis.
PURPOSE: To predict patients who would benefit from adaptive radiotherapy (ART) and re-planning intervention based on machine learning from anatomical and dosimetric variations in a retrospective dataset. MATERIALS AND METHODS: 90 patients (pts) treated for head-neck cancer (H&N) formed a multicenter data-set. 41 H&N pts (45.6%) were considered for learning; 49 pts (54.4%) were used to test the tool. A homemade machine-learning classifier was developed to analyze volume and dose variations of parotid glands (PG). Using deformable image registration (DIR) and GPU, patients' conditions were analyzed automatically. Support Vector Machines (SVM) was used for time-series evaluation. "Inadequate" class identified patients that might benefit from replanning. Double-blind evaluation by two radiation oncologists (ROs) was carried out to validate day/week selected for re-planning by the classifier. RESULTS: The cohort was affected by PG mean reduction of 23.7±8.8%. During the first 3weeks, 86.7% cases show PG deformation aligned with predefined tolerance, thus not requiring re-planning. From 4th week, an increased number of pts would potentially benefit from re-planning: a mean of 58% of cases, with an inter-center variability of 8.3%, showed "inadequate" conditions. 11% of cases showed "bias" due to DIR and script failure; 6% showed "warning" output due to potential positioning issues. Comparing re-planning suggested by tool with recommended by ROs, the 4th week seems the most favorable time in 70% cases. CONCLUSIONS: SVM and decision-making tool was applied to overcome ART challenges. Pts would benefit from ART and ideal time for re-planning intervention was identified in this retrospective analysis.
Authors: Elizabeth Huynh; Ahmed Hosny; Christian Guthier; Danielle S Bitterman; Steven F Petit; Daphne A Haas-Kogan; Benjamin Kann; Hugo J W L Aerts; Raymond H Mak Journal: Nat Rev Clin Oncol Date: 2020-08-25 Impact factor: 66.675
Authors: Issam El Naqa; Dan Ruan; Gilmer Valdes; Andre Dekker; Todd McNutt; Yaorong Ge; Q Jackie Wu; Jung Hun Oh; Maria Thor; Wade Smith; Arvind Rao; Clifton Fuller; Ying Xiao; Frank Manion; Matthew Schipper; Charles Mayo; Jean M Moran; Randall Ten Haken Journal: Med Phys Date: 2018-08-24 Impact factor: 4.071
Authors: Fu Jin; Huan-Li Luo; Juan Zhou; Ya-Nan He; Xian-Feng Liu; Ming-Song Zhong; Han Yang; Chao Li; Qi-Cheng Li; Xia Huang; Xiu-Mei Tian; Da Qiu; Guang-Lei He; Li Yin; Ying Wang Journal: Cancer Manag Res Date: 2018-06-22 Impact factor: 3.989
Authors: S B Lim; C J Tsai; Y Yu; P Greer; T Fuangrod; K Hwang; S Fontenla; F Coffman; N Lee; D M Lovelock Journal: Technol Cancer Res Treat Date: 2019-01-01