RESUMO
Introduction: Manual review of organ at risk (OAR) contours is crucial for creating safe radiotherapy plans but can be time-consuming and error prone. Statistical and deep learning models show the potential to automatically detect improper contours by identifying outliers using large sets of acceptable data (knowledge-based outlier detection) and may be able to assist human reviewers during review of OAR contours. Methods: This study developed an automated knowledge-based outlier detection method and assessed its ability to detect erroneous contours for all common head and neck (HN) OAR types used clinically at our institution. We utilized 490 accurate CT-based HN structure sets from unique patients, each with forty-two HN OAR contours when anatomically present. The structure sets were distributed as 80% for training, 10% for validation, and 10% for testing. In addition, 190 and 37 simulated contours containing errors were added to the validation and test sets, respectively. Single-contour features, including location, shape, orientation, volume, and CT number, were used to train three single-contour feature models (z-score, Mahalanobis distance [MD], and autoencoder [AE]). Additionally, a novel contour-to-contour relationship (CCR) model was trained using the minimum distance and volumetric overlap between pairs of OAR contours to quantify overlap and separation. Inferences from single-contour feature models were combined with the CCR model inferences and inferences evaluating the number of disconnected parts in a single contour and then compared. Results: In the test dataset, before combination with the CCR model, the area under the curve values were 0.922/0.939/0.939 for the z-score, MD, and AE models respectively for all contours. After combination with CCR model inferences, the z-score, MD, and AE had sensitivities of 0.838/0.892/0.865, specificities of 0.922/0.907/0.887, and balanced accuracies (BA) of 0.880/0.900/0.876 respectively. In the validation dataset, with similar overall performance and no signs of overfitting, model performance for individual OAR types was assessed. The combined AE model demonstrated minimum, median, and maximum BAs of 0.729, 0.908, and 0.980 across OAR types. Discussion: Our novel knowledge-based method combines models utilizing single-contour and CCR features to effectively detect erroneous OAR contours across a comprehensive set of 42 clinically used OAR types for HN radiotherapy.
RESUMO
BACKGROUND: Prolonged survival of patients with metastatic disease has furthered interest in metastasis-directed therapy (MDT). RESEARCH QUESTION: There is a paucity of data comparing lung MDT modalities. Do outcomes among sublobar resection (SLR), stereotactic body radiation therapy (SBRT), and percutaneous ablation (PA) for lung metastases vary in terms of local control and survival? STUDY DESIGN AND METHODS: Medical records of patients undergoing lung MDT at a single cancer center between January 2015 and December 2020 were reviewed. Overall survival, local progression, and toxicity outcomes were collected. Patient and lesion characteristics were used to generate multivariable models with propensity weighted analysis. RESULTS: Lung MDT courses (644 total: 243 SLR, 274 SBRT, 127 PA) delivered to 511 patients were included with a median follow-up of 22 months. There were 47 local progression events in 45 patients, and 159 patients died. Two-year overall survival and local progression were 80.3% and 63.3%, 83.8% and 9.6%, and 4.1% and 11.7% for SLR, SBRT, and PA, respectively. Lesion size per 1 cm was associated with worse overall survival (hazard ratio, 1.24; P = .003) and LP (hazard ratio, 1.50; P < .001). There was no difference in overall survival by modality. Relative to SLR, there was no difference in risk of local progression with PA; however, SBRT was associated with a decreased risk (hazard ratio, 0.26; P = .023). Rates of severe toxicity were low (2.1%-2.6%) and not different among groups. INTERPRETATION: This study performs a propensity weighted analysis of SLR, SBRT, and PA and shows no impact of lung MDT modality on overall survival. Given excellent local control across MDT options, a multidisciplinary approach is beneficial for patient triage and longitudinal management.