McNutt, Todd

Salivary glands are common organs at risk in both head and neck external beam radiotherapy (EBRT) and radiopharmaceutical therapy (RPT), but incidences of xerostomia in RPT are inconsistent with the EBRT Quantitative Analysis of Normal Tissue Effects in the Clinic (QUANTEC) limits. In EBRT, salivary glands are usually assumed to be parallel organs, with QUANTEC guidelines based on Dmean, but this is known to be a gross over-simplification of the full complexity of the underlying functional organization. The goal of this work is to combine machine learning of EBRT dose–outcome data with stylized small-scale RPT dosimetry to discover more reliable normal tissue complication probability (NTCP) models of xerostomia across both modalities. A retrospective cohort of 211 EBRT patients was analyzed using a custom-designed in-house machine learning workflow. From this, a hierarchy of three models of increasing complexity was trained, evaluated for performance and generalization, and coupled with stylized small-scale salivary gland dosimetry to assess the influence of model complexity on the predicted NTCP for plausible patterns of RPT dose nonuniformity. The three models in the hierarchy (A, B, C), in increasing order of complexity, associate xerostomia with the following: the mean dose to the whole contralateral parotid (model A), the mean dose to a ductally localized region (model B) and a serial interaction dose term between two ductal sub-compartments (model C). While the difference between the three models for EBRT p-values and AUCs is rather marginal, for physiologically driven ductal dose distributions in RPT, the predicted reduction in TD50 can be as large as a factor of 10. These results provide hints towards a plausible reconciliation of the observed inconsistency of xerostomia in RPT with EBRT dose limits.

Background: Lower-dose cone-beam computed tomography protocols for image-guided radiotherapy may permit target localization while minimizing radiation exposure. We prospectively evaluated a lower-dose cone-beam protocol for central nervous system image-guided radiotherapy across a multinational pediatrics consortium. Methods: Seven institutions prospectively employed a lower-dose cone-beam computed tomography central nervous system protocol (weighted average dose 0.7 mGy) for patients ≤21 years. Treatment table shifts between setup with surface lasers versus cone-beam computed tomography were used to approximate setup accuracy, and vector magnitudes for these shifts were calculated. Setup group mean, interpatient, interinstitution, and random error were estimated, and clinical factors were compared by mixed linear modeling. Results: Among 96 patients, with 2179 pretreatment cone-beam computed tomography acquisitions, median age was 9 years (1-20). Setup parameters were 3.13, 3.02, 1.64, and 1.48 mm for vector magnitude group mean, interpatient, interinstitution, and random error, respectively. On multivariable analysis, there were no significant differences in mean vector magnitude by age, gender, performance status, target location, extent of resection, chemotherapy, or steroid or anesthesia use. Providers rated >99% of images as adequate or better for target localization. Conclusions: A lower-dose cone-beam computed tomography protocol demonstrated table shift vector magnitude that approximate clinical target volume/planning target volume expansions used in central nervous system radiotherapy. There were no significant clinical predictors of setup accuracy identified, supporting use of this lower-dose cone-beam computed tomography protocol across a diverse pediatric population with brain tumors.

It is an exciting time for big data efforts in radiation oncology. The use of big data to help aid both outcomes and decision‐making research is becoming a reality. However, there are true challenges that exist in the space of gathering and utilizing performance and outcomes data. Here, we summarize the current state of big data in radiation oncology with respect to outcomes and discuss some of the efforts and challenges in radiation oncology big data.

300 Background: The National Radiation Oncology Registry (NROR) is developing an IT infrastructure to support the efficient collection, aggregation, and analysis of data concerning cancer patients treated with radiotherapy across the United States. Methods: Detailed requirements were developed to emphasize the following distinguishing goals for the system: 1) streamline the process of data collection by minimizing manual data entry; 2) support the collection of patient-reported outcomes (PROs) and their linkage with clinician-observed outcomes; 3) facilitate data integration within the NROR and between the NROR and other registries; 4) allow for evolution of the system in response to new learning; and 5) promote sustainability and ongoing improvement through an open standard of interoperability. Results: An innovative technical architecture has been designed to meet the goals described. The system maximizes efficiency through automated extraction and electronic transfer of data from radiation oncology information systems. PROs are collected directly from patients via a web-based portal and linked to data submitted from participating institutions. A data dictionary has been developed based on national standards and controlled vocabularies to facilitate data integration. Contemporary forms-based database technology is used in combination with traditional relational technology to permit both flexible evolution of the system and efficient data analysis. A unique “gateway” architecture and open transmission standard makes it possible for commercial products to interoperate with the registry in the future. Conclusions: The NROR prototype system will be launched later this year to collect data for a pilot registry of prostate cancer patients. Its performance and usability will be important factors in the success of the pilot. If effective, the platform will support the expansion of the NROR to benefit patients, clinicians, researchers, payors, device manufacturers, and policy-makers by capturing reliable, population-based information on radiation treatment delivery and health outcomes.