Models for predicting objective function weights in prostate cancer IMRT. Issue 4 (17th March 2015)

• Record Type: Journal Article
• Authors: Boutilier, Justin J.; Lee, Taewoo; Craig, Tim; Sharpe, Michael B.; Chan, Timothy C. Y.
• Is Part Of: Medical physics. Volume 42:Issue 4(2015)
• Page Start: 1586
• Page End: 1595
• Publication Date: 2015-03-17
• Subjects: biological organs -- cancer -- learning (artificial intelligence) -- optimisation -- radiation therapy -- regression analysis; Therapeutic applications, including brachytherapy -- Probability theory, stochastic processes, and statistics -- Cancer -- Numerical optimization; Radiation therapy -- In which a programme is changed according to experience gained by the computer itself during a complete run; Learning machines -- Inference methods or devices; knowledge‐based treatment planning -- machine learning -- inverse optimization; Cancer -- Biomedical modeling -- Medical treatment planning -- Intensity modulated radiation therapy -- Machine learning -- Optimization -- Cluster analysis -- Anatomy -- Dosimetry -- Radiation treatment; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1118/1.4914140
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract : Purpose: To develop and evaluate the clinical applicability of advanced machine learning models that simultaneously predict multiple optimization objective function weights from patient geometry for intensity‐modulated radiation therapy of prostate cancer. Methods: A previously developed inverse optimization method was applied retrospectively to determine optimal objective function weights for 315 treated patients. The authors used an overlap volume ratio (OV) of bladder and rectum for different PTV expansions and overlap volume histogram slopes (OVSR and OVSB for the rectum and bladder, respectively) as explanatory variables that quantify patient geometry. Using the optimal weights as ground truth, the authors trained and applied three prediction models: logistic regression (LR), multinomial logistic regression (MLR), and weighted K ‐nearest neighbor (KNN). The population average of the optimal objective function weights was also calculated. Results: The OV at 0.4 cm and OVSR at 0.1 cm features were found to be the most predictive of the weights. The authors observed comparable performance (i.e., no statistically significant difference) between LR, MLR, and KNN methodologies, with LR appearing to perform the best. All three machine learning models outperformed the population average by a statistically significant amount over a range of clinical metrics including bladder/rectum V53Gy, bladder/rectum V70Gy, and dose to the bladder, rectum, CTV, and PTV. When comparing the weights directly, the LR model predicted bladder and rectum weights that had, on average, a 73% and 74% relative improvement over the population average weights, respectively. The treatment plans resulting from the LR weights had, on average, a rectum V70Gy that was 35% closer to the clinical plan and a bladder V70Gy that was 29% closer, compared to the population average weights. Similar results were observed for all other clinical metrics. Conclusions: The authors demonstrated that the KNN and MLR weight prediction methodologies perform comparably to the LR model and can produce clinical quality treatment plans by simultaneously predicting multiple weights that capture trade‐offs associated with sparing multiple OARs.