Prediction and classification of VMAT dosimetric accuracy using plan complexity and log-files analysis. (November 2022)

• Record Type: Journal Article
• Authors: Cilla, Savino; Viola, Pietro; Romano, Carmela; Craus, Maurizio; Buwenge, Milly; Macchia, Gabriella; Valentini, Vincenzo; Deodato, Francesco; Morganti, Alessio G.
• Is Part Of: Physica medica. Volume 103(2022)
• Page Start: 76
• Page End: 88
• Publication Date: 2022-11
• Subjects: Machine learning -- Quality assurance -- Log-files -- Complexity -- VMAT; Medical physics -- Periodicals; Biophysics -- Periodicals; Biophysics -- Periodicals; Imagerie médicale -- Périodiques; Radiothérapie -- Périodiques; Rayons X -- Sécurité -- Mesures -- Périodiques; Physique -- Périodiques; Médecine -- Périodiques; 610.153
• DOI: 10.1016/j.ejmp.2022.10.004
• Languages: English
• ISSNs: 1120-1797

Abstract

Graphical abstract: Highlights: Complexity index (MCS) and log-files analysis were used for PSQA accuracy assessment. Prediction accuracy for gamma-pass rate (γ% ) was 2.1%. Precision, recall and F-score performances for γ% was greater than 90%. An MCS-based traffic light protocol was implemented to "a-priori" flag delivery accuracy. The optimal MCS threshold values for failed and pass plans were <0.130 and >0.270. Abstract: Purpose: We presented different machine learning models based on log files analysis and complexity indexes to predict and classify the dosimetric accuracy of VMAT plans. Methods: A total of 1302 VMAT arcs from 651 treatment plans were analyzed using the modulation complexity score (MCS) and the dynamic log-files generated by the linac. Predicted and measured fluences were compared using γ-analysis in terms of mean γ-values (γmean ) and γ-pass rate (γ% ). A kernel regression model was developed aiming to predict individual γ% and γmean values. Multinomial logistic regression (LR), Naïve-Bayes (NB) and support vector machine (SVM) models were developed based on MCS values to classify QA results as "pass" (γ% greater than90 % and γmean < 0.5), "control" (80 % < γ% < 90 % and 0.50 < γmean < 0.75) and "fail" (γ% < 80 % and γmean > 0.75). Training, validation and testing groups were used to evaluate the model reliability. A complexity-based traffic light protocol was implemented to flag pass (green light), control (orange light) and failed plans (red light). Results: Prediction accuracy of residuals for γ% was 2.1 % and 2.2 % in the training and testing cohorts, respectively. For 2 %(local)/2mm, both γ% and γmean classification performances reported weighted precision, recall and F1-values greater than 90 % for all machine learning models. The optimal MCS threshold value for the identification of failed plans was 0.130, with a sensibility and specificity of 0.994 and 0.952, respectively. The optimal MCS threshold for reliable plans was 0.270, with a sensitivity and specificity of 0.925 and 0.922, respectively. Conclusions: Machine learning can accurately predict the dosimetric accuracy of VMAT treatments, representing an efficient tool to assist patient-specific QA.