Improvement of prediction and classification performance for gamma passing rate by using plan complexity and dosiomics features. (December 2020)

• Record Type: Journal Article
• Authors: Hirashima, Hideaki; Ono, Tomohiro; Nakamura, Mitsuhiro; Miyabe, Yuki; Mukumoto, Nobutaka; Iramina, Hiraku; Mizowaki, Takashi
• Is Part Of: Radiotherapy and oncology. Volume 153(2020)
• Page Start: 250
• Page End: 257
• Publication Date: 2020-12
• Subjects: QA Quality assurance -- IMRT Intensity modulated radiotherapy -- VMAT Volumetric modulated arc therapy -- MLC Multi leaf collimator -- AAPM TG American association of Physicists in Medicine Task Group -- GPR Gamma passing rate -- DICOM-RT Digital imaging and communications in medicine in radio therapy -- FFF Flattening filter free -- MCS Modulation complexity score -- AAV Aperture area variability -- LSV Leaf sequence variability -- LTMCS Average leaf travel MCSv -- MIsport Modulation index for VMAT -- AA Aperture area -- AP Aperture perimeter -- AI Aperture irregularity -- PA Plan-averaged beam area -- PI Plan-averaged beam irregularity -- PM Plan-averaged beam modulation -- GLDM Gray level dependence matrix -- GLCM Gray level co-occurrence matrix -- GLRLM Gray level run length matrix -- GLSZM Gray level size zone matrix -- NGTDM Neighboring gray tone difference matrix -- SD Standard deviation -- MAE Mean absolute error -- RMSE Root mean square error -- CC Correlation coefficient -- AUC Area under curve -- ROC Receiver operating characteristic -- ANOVA Analysis of variance -- MU monitor unit; Prediction -- Classification -- Gamma passing rate -- Plan complexity feature -- Dosiomics feature -- Machine learning; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2020.07.031
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: The prediction and classification performance for gamma passing rate was assessed. 3D dosiomics feature was extracted from dose distribution on patient at treatment plans. Prediction and classification model was built by using plan and 3D dosiomics features. Dosiomics model has the potential to predict and classify gamma passing rate. The combination of both features improved the prediction and classification performance. Abstract: Purpose: The purpose of this study was to predict and classify the gamma passing rate (GPR) value by using new features (3D dosiomics features and combined with plan and dosiomics features) together with a machine learning technique for volumetric modulated arc therapy (VMAT) treatment plans. Methods and materials: A total of 888 patients who underwent VMAT were enrolled comprising 1255 treatment plans. Further, 24 plan complexity features and 851 dosiomics features were extracted from the treatment plans. The dataset was randomly split into a training/validation (80%) and test (20%) dataset. The three models for prediction and classification using XGBoost were as follows: (i) plan complexity features-based prediction method (plan model); (ii) 3D dosiomics feature-based prediction model (dosiomics model); (iii) a combination of both the previous models (hybrid model). The prediction performance was evaluated by calculating the mean absolute error (MAE) and the correlation coefficient (CC) between the predicted and measured GPRs. The classification performance was evaluated by calculating the area under curve (AUC) and sensitivity. Results: MAE and CC at γ2%/2 mm in the test dataset were 4.6% and 0.58, 4.3% and 0.61, and 4.2% and 0.63 for the plan model, dosiomics model, and hybrid model, respectively. AUC and sensitivity at γ2%/2 mm in test dataset were 0.73 and 0.70, 0.81 and 0.90, and 0.83 and 0.90 for the plan model, dosiomics model, and hybrid model, respectively. Conclusions: A combination of both plan and dosiomics features with machine learning technique can improve the prediction and classification performance for GPR.