Deep Hybrid Learning Prediction of Patient-Specific Quality Assurance in Radiotherapy: Implementation in Clinical Routine

被引:5
作者
Moreau, Noemie [1 ]
Bonnor, Laurine [1 ]
Jaudet, Cyril [1 ]
Lechippey, Laetitia [1 ]
Falzone, Nadia [2 ]
Batalla, Alain [1 ]
Bertaut, Cindy [3 ]
Corroyer-Dulmont, Aurelien [1 ,4 ]
机构
[1] CLCC Francois Baclesse, Med Phys Dept, F-14000 Caen, France
[2] Genesis Care Theranost, Bldg 1 & 11,Mill,41-43 Bourke Rd, Alexandria, NSW 2015, Australia
[3] Cherbourg Hosp, Med Phys Dept, F-50100 Cherbourg, France
[4] Normandie Univ, UNICAEN, CNRS, ISTCT, F-14000 Caen, France
关键词
machine learning; deep hybrid learning; radiotherapy; VMAT; quality assurance; clinical routine; CLASSIFICATION-REGRESSION MODEL; PLAN COMPLEXITY; QA; IMRT;
D O I
10.3390/diagnostics13050943
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Arc therapy allows for better dose deposition conformation, but the radiotherapy plans (RT plans) are more complex, requiring patient-specific pre-treatment quality assurance (QA). In turn, pre-treatment QA adds to the workload. The objective of this study was to develop a predictive model of Delta4-QA results based on RT-plan complexity indices to reduce QA workload. Methods. Six complexity indices were extracted from 1632 RT VMAT plans. A machine learning (ML) model was developed for classification purpose (two classes: compliance with the QA plan or not). For more complex locations (breast, pelvis and head and neck), innovative deep hybrid learning (DHL) was trained to achieve better performance. Results. For not complex RT plans (with brain and thorax tumor locations), the ML model achieved 100% specificity and 98.9% sensitivity. However, for more complex RT plans, specificity falls to 87%. For these complex RT plans, an innovative QA classification method using DHL was developed and achieved a sensitivity of 100% and a specificity of 97.72%. Conclusions. The ML and DHL models predicted QA results with a high degree of accuracy. Our predictive QA online platform is offering substantial time savings in terms of accelerator occupancy and working time.
引用
收藏
页数:11
相关论文
共 33 条
[1]  
Agazaryan Nzhde, 2003, J Appl Clin Med Phys, V4, P40, DOI 10.1120/1.1525243
[2]  
[Anonymous], 2020, AN SOFTW DISTR
[3]   Use of metrics to quantify IMRT and VMAT treatment plan complexity: A systematic review and perspectives [J].
Antoine, Mikael ;
Ralite, Flavien ;
Soustiel, Charles ;
Marsac, Thomas ;
Sargos, Paul ;
Cugny, Audrey ;
Caron, Jerome .
PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS, 2019, 64 :98-108
[4]   Integration of AI and Machine Learning in Radiotherapy QA [J].
Chan, Maria F. ;
Witztum, Alon ;
Valdes, Gilmer .
FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2020, 3
[5]   Complexity metrics for IMRT and VMAT plans: a review of current literature and applications [J].
Chiavassa, Sophie ;
Bessieres, Igor ;
Edouard, Magali ;
Mathot, Michel ;
Moignier, Alexandra .
BRITISH JOURNAL OF RADIOLOGY, 2019, 92 (1102)
[6]  
Chollet F., 2015, Keras
[7]   Patient-specific quality assurance using machine log files analysis for stereotactic body radiation therapy (SBRT) [J].
Chow, Vivian U. Y. ;
Kan, Monica W. K. ;
Chan, Anthony T. C. .
JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, 2020, 21 (11) :179-187
[8]  
Corroyer-Dulmont A., 2022, DEEP HYBRID LEARNING
[9]  
Darzidehkalani Erfan, 2022, J Am Coll Radiol, V19, P969, DOI 10.1016/j.jacr.2022.03.015
[10]   Anatomy-based, patient-specific VMAT QA using EPID or MLC log files [J].
Defoor, Dewayne L. ;
Vazquez-Quino, Luis A. ;
Mavroidis, Panayiotis ;
Papanikolaou, Nikos ;
Stathakis, Sotirios .
JOURNAL OF APPLIED CLINICAL MEDICAL PHYSICS, 2015, 16 (03) :206-215