Data-Driven Dose-Volume Histogram Prediction.

PURPOSE: To evaluate dose-volume histogram (DVH) prediction from prior radiation therapy data. METHODS AND MATERIALS: An Oncospace radiation therapy database was constructed including images, structures, and dose distributions for patients with advanced lung cancer. DVH data was queried for total lungs, esophagus, heart, and external body contours. Each query returned DVH data for the N-most similar organs at risk (OARs) based on OAR-to-planning-target-volume (PTV) geometry via the overlap volume histogram (OVH). The DVHs for 5, 20, and 50 of the most similar OVHs were returned for each OAR for each patient. The OVH(0cm) is the relative volume of the OAR overlapping with the PTV, and the OVH(2cm) is the relative volume of the OAR 2 cm away from the PTV. The OVH(cm) and DVH(%) queried from the database were separated into interquartile ranges (IQRs), nonoutlier ranges (NORs) (equal to 3 × IQR), and the average database DVH (DVH-DB) computed from the NOR data. The ability to predict the clinically delivered DVH was evaluated based on percentiles and differences between the DVH-DB and the clinical DVH (DVH-CL) for a varying number of returned patient DVHs for a subset of patients. RESULTS: The ability to predict the clinically delivered DVH was excellent in the lungs and body; the IQR and NOR were <4% and <16%, respectively, in the lungs and <1% and <5%, respectively, in the body at all distances less than 2 cm from the PTV. For 21/23 patients considered, the differences in lung DVH-DB and DVH-CL were <4.6% and in 14/23 cases, <3%. In esophagus and heart, the ability to predict DVH-CL was weaker, with mean DVH differences >10% for 12/23 esophagi and 10/23 hearts. In esophagus and heart queries, the NOR was often 10% to 100% volume in dose ranges between 0% and 50% of prescription, independent of the number of patients queried. CONCLUSIONS: Using prior data to predict clinical dosimetry is increasingly of interest, but model- and data-driven methods have limitations if based on limited data sets. This study's results showed that prediction may be reasonable in organs containing tumors with known overlap, but for nonoverlapped OARs, planning preference and plan design may dominate the clinical dose.

Knowledge-based quality control of organ delineations in radiation therapy.

PURPOSE: To reduce the likelihood of errors in organ delineations used for radiotherapy treatment planning, a knowledge-based quality control (KBQC) system, which discriminates between valid and anomalous delineations is developed. METHOD AND MATERIALS: The KBQC is comprised of a group-wise inference system and anomaly detection modules trained using historical priors from 296 locally advanced lung and prostate cancer patient computational tomographies (CTs). The inference system discriminates different organs based on shape, relational, and intensity features. For a given delineated image set, the inference system solves a combinatorial optimization problem that results in an organ group whose relational features follow those of the training set considering the posterior probabilities obtained from support vector machine (SVM), discriminant subspace ensemble (DSE), and artificial neural network (ANN) classifiers. These classifiers are trained on nonrelational features with a 10-fold cross-validation scheme. The anomaly detection module is a bank of ANN autoencoders, each corresponding with an organ, trained on nonrelational features. A heuristic rule detects anomalous organs that exceed predefined organ-specific tolerances for the feature reconstruction error and the classifier's posterior probabilities. Independent data sets with anomalous delineations were used to test the overall performance of the KBQC system. The anomalous delineations were manually manipulated, computer-generated, or propagated based on a transformation obtained by imperfect registrations. Both peer-review-based scoring system and shape similarity coefficient (DSC) were used to label regions of interest (ROIs) as normal or anomalous in two independent test cohorts. RESULTS: The accuracy of the classifiers was ≥ $\ge$ 99.8%, and the minimum per-class F1-scores were 0.99, 0.99, and 0.98 for SVM, DSE, and ANN, respectively. The group-wise inference system reduced the miss-classification likelihood for the test data set with anomalous delineations compared to each individual classifier and a fused classifier that used the average posterior probability of all classifiers. For 15 independent locally advanced lung patients, the system detected > $>$ 79% of the anomalous ROIs. For 1320 auto-segmented abdominopelvic organs, the anomaly detection system identified anomalous delineations, which also had low Dice similarity coefficient values with respect to manually delineated organs in the training data set. CONCLUSION: The KBQC system detected anomalous delineations with superior accuracy compared to classification methods that judge only based on posterior probabilities.

Clinical Outcomes and Predictors of Lung Toxicity After Multiple Courses of Lung Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer.

BACKGROUND: The clinical outcomes of multicourse lung stereotactic body radiotherapy (SBRT) have yet to be validated in a prospective study, and there are a lack of data on allowable composite dosimetry. PATIENTS AND METHODS: Forty-four patients underwent multicourse lung SBRT for recurrent or metachronous NSCLC. The median biologically effective dose (BED10) for the first course and subsequent courses were 132 and 100 Gy, respectively. Patient and treatment characteristics were evaluated to determine the correlation with the development of radiation pneumonitis (RP). RESULTS: The local control rate was 91%. A total of 13.6% developed a grade 2+ RP, and 4.5% developed a grade 3+ RP, including one grade 5. On univariable analysis, multiple composite dosimetric factors (V5 [proportion of lung structure receiving at least 5 Gy], V10, V20, V40, and mean lung dose) were correlated with the development of RP. When comprised of the first and second course of SBRT, a composite lung V5 of < 30% and > 50% was associated with a 0 and 75% incidence of grade 2+ RP, respectively. We identified no significant correlation on multivariable analysis but observed a strong trend between composite lung V5 and the development of grade 2+ RP (hazard ratio, 1.157; P = .058). Evaluation of multiple clinical factors also identified a significant correlation between the timing of repeat lung SBRT and the development of grade 2+ RP after the second course (P = .0028). CONCLUSION: Subsequent courses of lung SBRT, prescribed to a median BED10 of 100 Gy, can provide a high rate of local control with a 4.5% incidence of grade 3+ toxicity. Composite lung V5 and the timing of the second course of lung SBRT may be correlated to the development of RP.

Quality assurance tool for organ at risk delineation in radiation therapy using a parametric statistical approach.

PURPOSE: To develop a quality assurance (QA) tool that identifies inaccurate organ at risk (OAR) delineations. METHODS: The QA tool computed volumetric features from prior OAR delineation data from 73 thoracic patients to construct a reference database. All volumetric features of the OAR delineation are computed in three-dimensional space. Volumetric features of a new OAR are compared with respect to those in the reference database to discern delineation outliers. A multicriteria outlier detection system warns users of specific delineation outliers based on combinations of deviant features. Fifteen independent experimental sets including automatic, propagated, and clinically approved manual delineation sets were used for verification. The verification OARs included manipulations to mimic common errors. Three experts reviewed the experimental sets to identify and classify errors, first without; and then 1 week after with the QA tool. RESULTS: In the cohort of manual delineations with manual manipulations, the QA tool detected 94% of the mimicked errors. Overall, it detected 37% of the minor and 85% of the major errors. The QA tool improved reviewer error detection sensitivity from 61% to 68% for minor errors (P = 0.17), and from 78% to 87% for major errors (P = 0.02). CONCLUSIONS: The QA tool assists users to detect potential delineation errors. QA tool integration into clinical procedures may reduce the frequency of inaccurate OAR delineation, and potentially improve safety and quality of radiation treatment planning.

Clinical adequacy assessment of autocontours for prostate IMRT with meaningful endpoints.

PURPOSE: To determine if radiation treatment plans created based on autosegmented (AS) regions-of-interest (ROI)s are clinically equivalent to plans created based on manually segmented ROIs, where equivalence is evaluated using probabilistic dosimetric metrics and probabilistic biological endpoints for prostate IMRT. METHOD AND MATERIALS: Manually drawn contours and autosegmented ROIs were created for 167 CT image sets acquired from 19 prostate patients. Autosegmentation was performed utilizing Pinnacle's Smart Probabilistic Image Contouring Engine. For each CT set, 78 Gy/39 fraction 7-beam IMRT treatment plans with 1 cm CTV-to-PTV margins were created for each of the three contour scenarios; PMD using manually delineated (MD) ROIs, PAS using autosegmented ROIs, and PAM using autosegmented organ-at-risks (OAR)s and the manually drawn target. For each plan, 1000 virtual treatment simulations with different systematic errors for each simulation and a different random error for each fraction were performed. The statistical probability of achieving dose-volume metrics (coverage probability (CP)), expectation values for normal tissue complication probability (NTCP), and tumor control probability (TCP) metrics for all possible cross-evaluation pairs of ROI types and planning scenarios were reported. In evaluation scenarios, the root mean square loss (RMSL) and maximum absolute loss (MAL) of coverage probability of dose-volume objectives, E[TCP], and E[NTCP] were compared with respect to the base plan created and evaluated with manually drawn contours. RESULTS: Femoral head dose objectives were satisfied in all situations, as well as the maximum dose objectives for all ROIs. Bladder metrics were within the clinical coverage tolerances except D35Gy for the autosegmented plan evaluated with the manual contours. Dosimetric indices for CTV and rectum could be highly compromised when the definition of the ROIs switched from manually delineated to autosegmented. Seventy-two percent of CT image sets satisfied the worst-case CP thresholds for all dosimetric objectives in all scenarios, the percentage dropped to 50% if biological indices were taken into account. Among evaluation scenarios, (MD,PAM ) bore the highest resemblance to (MD,PMD ) where 99% and 88% of cases met all CP thresholds for bladder and rectum, respectively. CONCLUSIONS: When including daily setup variations in prostate IMRT, the dose-volume metric CP, and biological indices of ROIs were approximately equivalent for the plans created based on manually drawn targets and autosegmented OARs in 88% of cases. The accuracy of autosegmented prostates and rectums are impediment to attain statistically equivalent plans created based on manually drawn ROIs.

Clinical outcomes of helical conformal versus nonconformal palliative radiation therapy for axial skeletal metastases.

PURPOSE: Palliative radiation therapy (RT) for bone metastases has traditionally been delivered with conventional, nonconformal RT (NCRT). Conformal RT (CRT) is potentially more complex and expensive than NCRT, but may reduce normal tissue dose and subsequently toxicity. In this retrospective analysis, we compared CRT with NCRT to investigate the association between conformality and toxicity. METHODS AND MATERIALS: A retrospective analysis of patients receiving palliative RT for axial skeletal bone metastases from 2012 to 2014 was conducted. Patient and treatment characteristics were obtained including dosimetric variables, acute toxicity, and subjective pain during treatment and in the acute posttreatment period (≤60 days after completion). Statistical analyses included t tests, χ2 tests, and multivariate logistic regression. RESULTS: A total of 179 patients and 254 bone metastases were identified (142 CRT, 112 NCRT). The CRT and NCRT groups were well matched for baseline characteristics (number of fractions, field size, treatment sites, and concurrent chemotherapy). In multivariate logistic regression models, technique (CRT vs NCRT) was not associated with development of acute toxicity. Regarding toxicity, Eastern Cooperative Oncology Group performance status and total dose were significantly associated with a higher rate of acute toxicity during RT (odds ratios, 0.649 and 1.129 and P = .027 and .044, respectively), and only a higher number of vertebral bodies in the treatment field was significantly associated with acute toxicity post-treatment (odds ratios, 1.219, P = .028). CRT was associated with improvement in bone pain during and posttreatment (P = .049 and .045, respectively). CONCLUSIONS: Our results demonstrate no difference in acute toxicity following palliative RT with CRT compared with NCRT for painful bone metastases; however, treatment volume did predict for increased toxicity. Larger studies may further elucidate the value of CRT including the impact of dose escalation for bone metastases and differences in patient reported outcomes between RT techniques.

Choosing a Prescription Isodose in Stereotactic Radiosurgery for Brain Metastases: Implications for Local Control.

OBJECTIVE: Stereotactic radiosurgery (SRS) achieves excellent local control (LC) with limited toxicity for most brain metastases. SRS dose prescription variables influence LC; therefore, we evaluated the impact of prescription isodose line (IDL) on LC after SRS. METHODS: A retrospective analysis of patients with brain metastases treated on a Gamma Knife platform from 2004 to 2014 was conducted. Clinical, toxicity, radiographic, and dosimetric data were collected. Cox proportional hazards regression was used to determine progression-free survival (PFS) and competing risks analysis was used to determine predictive factors for LC. RESULTS: A total of 134 patients with 374 brain metastases were identified with a median survival of 8.7 months (range, 0.2-64.8). The median tumor maximum dimension was 8 mm (range, 2-62 mm), median margin dose was 20 Gy (range, 5-24 Gy), and 12-month LC rate was 88.7%. On multivariate analysis, PFS improved with increasing IDL (P = 0.003) and decreased with non-non-small-cell lung cancer histology (P = 0.001). Margin dose, tumor size, conformality, and previous whole-brain irradiation failed to independently affect PFS. When adjusting for death as a competing risk, the cumulative likelihood of LC improved with higher IDL (P = 0.04). The rate of SRS-induced radiographic and clinical toxicity was low (16.6% and 1.5%, respectively), and neither was affected by IDL. CONCLUSIONS: Our results confirm that SRS for brain metastases results in favorable LC, particularly for patients with smaller tumors. We noted that dose delivery to a higher prescription IDL is associated with small but measurable improvements in LC. This finding could be related to higher dose just beyond the radiographically apparent tumor.