Search

With the era of big data, the utilization of machine learning algorithms in radiation oncology is rapidly growing with applications including: treatment response modeling, treatment planning, contouring, organ segmentation, image-guidance, motion tracking, quality assurance, and more. Despite this interest, practical clinical implementation of machine learning as part of the day-to-day clinical operations is still lagging. The aim of this white paper is to further promote progress in this new field of machine learning in radiation oncology by highlighting its untapped advantages and potentials for clinical advancement, while also presenting current challenges and open questions for future research. The targeted audience of this paper includes newcomers as well as practitioners in the field of medical physics/radiation oncology. The paper also provides general recommendations to avoid common pitfalls when applying these powerful data analytic tools to medical physics and radiation oncology problems and suggests some guidelines for transparent and informative reporting of machine learning results.

PurposeMachine learning classification algorithms (classifiers) for prediction of treatment response are becoming more popular in radiotherapy literature. General Machine learning literature provides evidence in favor of some classifier families (random forest, support vector machine, gradient boosting) in terms of classification performance. The purpose of this study is to compare such classifiers specifically for (chemo)radiotherapy datasets and to estimate their average discriminative performance for radiation treatment outcome prediction.MethodsWe collected 12 datasets (3496 patients) from prior studies on post-(chemo)radiotherapy toxicity, survival, or tumor control with clinical, dosimetric, or blood biomarker features from multiple institutions and for different tumor sites, that is, (non-)small-cell lung cancer, head and neck cancer, and meningioma. Six common classification algorithms with built-in feature selection (decision tree, random forest, neural network, support vector machine, elastic net logistic regression, LogitBoost) were applied on each dataset using the popular open-source R package caret. The R code and documentation for the analysis are available online (https://github.com/timodeist/classifier_selection_code). All classifiers were run on each dataset in a 100-repeated nested fivefold cross-validation with hyperparameter tuning. Performance metrics (AUC, calibration slope and intercept, accuracy, Cohen's kappa, and Brier score) were computed. We ranked classifiers by AUC to determine which classifier is likely to also perform well in future studies. We simulated the benefit for potential investigators to select a certain classifier for a new dataset based on our study (pre-selection based on other datasets) or estimating the best classifier for a dataset (set-specific selection based on information from the new dataset) compared with uninformed classifier selection (random selection).ResultsRandom forest (best in 6/12 datasets) and elastic net logistic regression (best in 4/12 datasets) showed the overall best discrimination, but there was no single best classifier across datasets. Both classifiers had a median AUC rank of 2. Preselection and set-specific selection yielded a significant average AUC improvement of 0.02 and 0.02 over random selection with an average AUC rank improvement of 0.42 and 0.66, respectively.ConclusionRandom forest and elastic net logistic regression yield higher discriminative performance in (chemo)radiotherapy outcome and toxicity prediction than other studied classifiers. Thus, one of these two classifiers should be the first choice for investigators when building classification models or to benchmark one's own modeling results against. Our results also show that an informed preselection of classifiers based on existing datasets can improve discrimination over random selection.

A substantial barrier to the single- and multi-institutional aggregation of data to supporting clinical trials, practice quality improvement efforts, and development of big data analytics resource systems is the lack of standardized nomenclatures for expressing dosimetric data. To address this issue, the American Association of Physicists in Medicine (AAPM) Task Group 263 was charged with providing nomenclature guidelines and values in radiation oncology for use in clinical trials, data-pooling initiatives, population-based studies, and routine clinical care by standardizing: (1) structure names across image processing and treatment planning system platforms; (2) nomenclature for dosimetric data (eg, dose-volume histogram [DVH]-based metrics); (3) templates for clinical trial groups and users of an initial subset of software platforms to facilitate adoption of the standards; (4) formalism for nomenclature schema, which can accommodate the addition of other structures defined in the future. A multisociety, multidisciplinary, multinational group of 57 members representing stake holders ranging from large academic centers to community clinics and vendors was assembled, including physicists, physicians, dosimetrists, and vendors. The stakeholder groups represented in the membership included the AAPM, American Society for Radiation Oncology (ASTRO), NRG Oncology, European Society for Radiation Oncology (ESTRO), Radiation Therapy Oncology Group (RTOG), Children's Oncology Group (COG), Integrating Healthcare Enterprise in Radiation Oncology (IHE-RO), and Digital Imaging and Communications in Medicine working group (DICOM WG); A nomenclature system for target and organ at risk volumes and DVH nomenclature was developed and piloted to demonstrate viability across a range of clinics and within the framework of clinical trials. The final report was approved by AAPM in October 2017. The approval process included review by 8 AAPM committees, with additional review by ASTRO, European Society for Radiation Oncology (ESTRO), and American Association of Medical Dosimetrists (AAMD). This Executive Summary of the report highlights the key recommendations for clinical practice, research, and trials.

Background: The role of artificial intelligence and radiomics in prediction model development in cancer has been increasing every passing day. Cervical cancer is the 4th most common cancer in women worldwide, contributing to 6.5% of all cancer types. The treatment outcome of cervical cancer patients varies and individualized prediction of disease outcome is of paramount importance. Purpose: The purpose of this study is to develop and validate the digital signature for 5-year overall survival prediction in cervical cancer using robust CT radiomic and clinical features. Materials and Methods: Pretreatment clinical features and CT radiomic features of 68 patients, who were treated with chemoradiation therapy in our hospital, were used in this study. Radiomic features were extracted using an in-house developed python script and pyradiomic package. Clinical features were selected by the recursive feature elimination technique. Whereas radiomic feature selection was performed using a multi-step process i.e., step-1: only robust radiomic features were selected based on our previous study, step-2: a hierarchical clustering was performed to eliminate feature redundancy, and step-3: recursive feature elimination was performed to select the best features for prediction model development. Four machine algorithms i.e., Logistic regression (LR), Random Forest (RF), Support vector classifier (SVC), and Gradient boosting classifier (GBC), were used to develop 24 models (six models using each algorithm) using clinical, radiomic and combined features. Models were compared based on the prediction score in the internal validation. Results: The average prediction accuracy was found to be 0.65 (95% CI: 0.60– 0.70), 0.72 (95% CI: 0.63–0.81), and 0.77 (95% CI: 0.72–0.82) for clinical, radiomic, and combined models developed using four prediction algorithms respectively. The average prediction accuracy was found to be 0.69 (95% CI: 0.62–0.76), 0.79 (95% CI: 0.72–0.86), 0.71 (95% CI: 0.62–0.80), and 0.72 (95% CI: 0.66–0.78) for LR, RF, SVC and GBC models developed on three datasets respectively. Conclusion: Our study shows the promising predictive performance of a robust radiomic signature to predict 5-year overall survival in cervical cancer patients. [ABSTRACT FROM AUTHOR]