Patient-specific Quality Assurance Failure Prediction with Deep Tabular Models

Abstract

AbstractBackgroundPatient-specific quality assurance (PSQA) is part of the standard practice to ensure that a patient receives the dose from intensity-modulated radiotherapy (IMRT) beams as planned in the treatment planning system (TPS). PSQA failures can cause a delay in patient care and increase workload and stress of staff members. A large body of previous work for PSQA failure prediction focuses on non-learned plan complexity measures. Another prominent line of work uses machine learning methods, often in conjunction with feature engineering. Currently, there are no machine learning solutions which work directly with multi-leaf collimator (MLC) leaf positions, providing an opportunity to improve leaf sequencing algorithms using these techniques.PurposeTo improve patient safety and work efficiency, we develop a tabular transformer model based directly on the MLC leaf positions (without any feature engineering) to predict IMRT PSQA failure. This neural model provides an end-to-end differentiable map from MLC leaf positions to the probability of PSQA plan failure, which could be useful for regularizing gradient-based leaf sequencing optimization algorithms and generating a plan that is more likely to pass PSQA.MethodWe retrospectively collected DICOM RT PLAN files of 968 patient plans treated with volumetric arc therapy. We construct a beam-level tabular dataset with 1873 beams as samples and MLC leaf positions as features. We train an attention-based neural network FT-Transformer to predict the ArcCheck-based PSQA gamma pass rates. In addition to the regression task, we evaluate the model in the binary classification context predicting the pass or fail of PSQA. The performance was compared to the results of the two leading tree ensemble methods (CatBoost and XGBoost) and a non-learned method based on mean MLC gap.ResultsThe FT-Transformer model achieves 1.44% Mean Absolute Error (MAE) in the regression task of the gamma pass rate prediction and performs on par with XGBoost (1.53 % MAE) and CatBoost (1.40 % MAE). In the binary classification task of PSQA failure prediction, FT-Transformer achieves 0.85 ROC AUC (with CatBoost and XGBoost achieving 0.87 ROC AUC and the mean-MLC-gap complexity metric achieving 0.72 ROC AUC). Moreover, FT-Transformer, CatBoost, and XGBoost all achieve 80% true positive rate while keeping the false positive rate under 20%.ConclusionsWe demonstrate that reliable PSQA failure predictors can be successfully developed based solely on MLC leaf positions. Our FT-Transformer neural network can reduce the need for patient rescheduling due to PSQA failures by 80% while sending only 20% of plans that would not have failed the PSQA for replanning. FT-Transformer achieves comparable performance with the leading tree ensemble methods while having an additional benefit of providing an end-to-end differentiable map from MLC leaf positions to the probability of PSQA failure.