Multi-task autoencoder based classification-regression model for patient-specific VMAT QA Journal Article


Authors: Wang, L.; Li, J.; Zhang, S.; Zhang, X.; Zhang, Q.; Chan, M. F.; Yang, R.; Sui, J.
Article Title: Multi-task autoencoder based classification-regression model for patient-specific VMAT QA
Abstract: Patient-specific quality assurance (PSQA) of volumetric modulated arc therapy (VMAT) to assure accurate treatment delivery is resource-intensive and time-consuming. Recently, machine learning has been increasingly investigated in PSQA results prediction. However, the classification performance of models at different criteria needs further improvement and clinical validation (CV), especially for predicting plans with low gamma passing rates (GPRs). In this study, we developed and validated a novel multi-task model called autoencoder based classification-regression (ACLR) for VMAT PSQA. The classification and regression were integrated into one model, both parts were trained alternatively while minimizing a defined loss function. The classification was used as an intermediate result to improve the regression accuracy. Different tasks of GPRs prediction and classification based on different criteria were trained simultaneously. Balanced sampling techniques were used to improve the prediction accuracy and classification sensitivity for the unbalanced VMAT plans. Fifty-four metrics were selected as inputs to describe the plan modulation-complexity and delivery-characteristics, while the outputs were PSQA GPRs. A total of 426 clinically delivered VMAT plans were used for technical validation (TV), and another 150 VMAT plans were used for CV to evaluate the generalization performance of the model. The ACLR performance was compared with the Poisson Lasso (PL) model and found significant improvement in prediction accuracy. In TV, the absolute prediction error (APE) of ACLR was 1.76%, 2.60%, and 4.66% at 3%/3 mm, 3%/2 mm, and 2%/2 mm, respectively; whereas the APE of PL was 2.10%, 3.04%, and 5.29% at 3%/3 mm, 3%/2 mm, and 2%/2 mm, respectively. No significant difference was found between CV and TV in prediction accuracy. ACLR model set with 3%/3 mm can achieve 100% sensitivity and 83% specificity. The ACLR model could classify the unbalanced VMAT QA results accurately, and it can be readily applied in clinical practice for virtual VMAT QA. © 2020 Institute of Physics and Engineering in Medicine.
Keywords: radiotherapy; quality assurance; forecasting; patient treatment; regression analysis; volumetric modulated arc therapy; learning systems; classification performance; clinical validations; deep learning; prediction accuracy; patient-specific qa; vmat qa; balanced samplings; classification regression; generalization performance; intermediate results
Journal Title: Physics in Medicine and Biology
Volume: 65
Issue: 23
ISSN: 0031-9155
Publisher: IOP Publishing Ltd  
Date Published: 2020-11-25
Start Page: 235023
Language: English
DOI: 10.1088/1361-6560/abb31c
PROVIDER: scopus
PUBMED: 33245054
PMCID: PMC10072931
DOI/URL:
Notes: Article -- Export Date: 4 January 2021 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Maria F Chan
    190 Chan