A machine learning tool for re-planning and adaptive RT: A multicenter cohort investigation
| Autor: | F. Bunkheila, Elisa D'Angelo, S. Lappi, G. Orlandi, M. Bono, A. Bernabei, N. Maffei, Stefania Maggi, Bruno Meduri, V.E. Morabito, S. Malara, G.M. Mistretta, Frank Lohr, F. Rosica, T. Costi, Gabriele Guidi, C. Blasi, M. Cardinali, Alessandro Savini, C. D’Ugo, P. Ceroni, A. Ciarmatori |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
Biophysics Deformable registration General Physics and Astronomy Image registration Re-planning Machine learning computer.software_genre 030218 nuclear medicine & medical imaging Cohort Studies Machine Learning 03 medical and health sciences 0302 clinical medicine Retrospective analysis Humans Radiology Nuclear Medicine and imaging Adaptive radiotherapy Retrospective Studies business.industry Radiotherapy Planning Computer-Assisted Reproducibility of Results General Medicine Radiotherapy Computer-Assisted Support vector machine Adaptive RT 030220 oncology & carcinogenesis Cohort Artificial intelligence business computer |
| Zdroj: | Physica Medica. 32:1659-1666 |
| ISSN: | 1120-1797 |
| Popis: | 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.90 patients (pts) treated for head-neck cancer (HN) formed a multicenter data-set. 41 HN 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.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.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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect