The importance of evaluating the complete automated knowledge-based planning pipeline

TL;DR

This study evaluates how different prediction and optimization methods in knowledge-based planning pipelines affect radiation therapy plan quality, highlighting the importance of complete pipeline assessment.

Contribution

It systematically benchmarks four KBP pipelines combining GAN and RF predictions with two optimization methods, revealing the impact of each component on plan quality.

Findings

GAN-IP plans most often met clinical criteria

RF-based pipelines achieved higher clinical criterion satisfaction than GAN-based plans

Prediction error was higher for GAN than RF

Abstract

We determine how prediction methods combine with optimization methods in two-stage knowledge-based planning (KBP) pipelines to produce radiation therapy treatment plans. We trained two dose prediction methods, a generative adversarial network (GAN) and a random forest (RF) with the same 130 treatment plans. The models were applied to 87 out-of-sample patients to create two sets of predicted dose distributions that were used as input to two optimization models. The first optimization model, inverse planning (IP), estimates weights for dose-objectives from a predicted dose distribution and generates new plans using conventional inverse planning. The second optimization model, dose mimicking (DM), minimizes the sum of one-sided quadratic penalties between the predictions and the generated plans using several dose-objectives. Altogether, four KBP pipelines (GAN-IP, GAN-DM, RF-IP, and RF-DM) were constructed and benchmarked against the corresponding clinical plans using clinical criteria; the error of both prediction methods was also evaluated. The best performing plans were GAN-IP plans, which satisfied the same criteria as their corresponding clinical plans (78%) more often than any other KBP pipeline. However, GAN did not necessarily provide the best prediction for the second-stage optimization models. Specifically, both the RF-IP and RF-DM plans satisfied all clinical criteria 25% and 15% more often than GAN-DM plans (the worst performing planning), respectively. GAN predictions also had a higher mean absolute error (3.9 Gy) than those from RF (3.6 Gy). We find that state-of-the-art prediction methods when paired with different optimization algorithms, produce treatment plans with considerable variation in quality.