Intra-operative extracorporeal irradiation of tumour-invaded craniotomy bone flap in meningioma: a case series.

BACKGROUND: Extracorporeal irradiation of tumorous calvaria (EITC) can be performed to restore function and form of the skull after resection of bone-invasive meningioma. We sought to examine the rate of tumour recurrence and other selected outcomes in patients undergoing meningioma resection and EITC. METHODS: Retrospective single-centre study of adult patients undergoing meningioma resection and EITC between January 2015 and November 2022 at a tertiary neurosurgical centre. Patient demographics, surgery data, tumour data, use of adjuvant therapy, surgical complications, and tumour recurrences were collected. RESULTS: Eighteen patients with 11 (61%) CNS WHO grade 1, 6 (33%) grade 2, and 1 (6%) grade 3 meningiomas were included. Median follow-up was 42 months (range 3-88). Five (28%) patients had a recurrence, but none were associated with the bone flap. Two (11%) wound infections requiring explant surgery occurred. Six (33%) patients required a further operation. Two operations were for recurrences, one was for infection, one was a washout and wound exploration but no evidence of infection was found, one patient requested the removal of a small titanium implant, and one patient required a ventriculoperitoneal shunt for a persistent CSF collection. There were no cases of bone flap resorption and cosmetic outcome was not routinely recorded. CONCLUSION: EITC is feasible and fast to perform with good outcomes and cost-effectiveness compared to other reconstructive methods. We observed similar recurrence rates and lower infection rates requiring explant compared to the largest series of cranioplasty in meningioma. Cosmetic outcome is universally under-reported and should be reported in future studies.

Ten daily fractions for partial breast irradiation. Long-term results of a prospective phase II trial.

Partial breast irradiation (PBI) is an effective adjuvant treatment after breast conservative surgery for selected early-stage breast cancer patients. However, the best fractionation scheme is not well defined. Hereby, we report the 5-year clinical outcome and toxicity of a phase II prospective study of a novel regimen to deliver PBI, which consists in 40 Gy delivered in 10 daily fractions. Patients with early-stage (pT1-pT2, pN0-pN1a, M0) invasive breast cancer were enrolled after conservative surgery. The minimum age at diagnosis was 60 years old. PBI was delivered with 3D-conformal radiotherapy technique with a total dose of 40 Gy, fractionated in 10 daily fractions (4 Gy/fraction). Eighty patients were enrolled. The median follow-up was 67 months. Five-year local control (LC), disease-free survival (DFS), and overall survival (OS) were 95%, 91%, and 96%, respectively. Grade I and II subcutaneous fibrosis were documented in 23% and 5% of cases. No grade III late toxicity was observed. PBI delivered in 40 Gy in 10 daily fractions provided good clinical results and was a valid radiotherapy option for early-stage breast cancer patients.

Local alkylating chemotherapy applied immediately after 5-ALA guided resection of glioblastoma does not provide additional benefit.

Grade IV glioma is the most common and aggressive primary brain tumour. Gross total resection with 5-aminolevulinic acid (5-ALA) guided surgery combined with local chemotherapy (carmustine wafers) is an attractive treatment strategy in these patients. No previous studies have examined the benefit carmustine wafers in a treatment programme of 5-ALA guided resection followed by a temozolomide-based chemoradiotherapy protocol. The objective of this study was to examine the benefit of carmustine wafers on survival in patients undergoing 5-ALA guided resection. A retrospective cohort study of 260 patients who underwent 5-ALA resection of confirmed WHO 2007 Grade IV glioma between July 2009 and December 2014. Survival curves were calculated using the Kaplan-Meier method from surgery. The log-rank test was used to compare survival curves between groups. Cox regression was performed to identify variables predicting survival. A propensity score matched analysis was used to compare survival between patients who did and did not receive carmustine wafers while controlling for baseline characteristics. Propensity matched analysis showed no significant survival benefit of insertion of carmustine wafers over 5-ALA resection alone (HR 0.97 [0.68-1.26], p = 0.836). There was a trend to higher incidence of wound infection in those who received carmustine wafers (15.4 vs. 7.1%, p = 0.064). The Cox regression analysis showed that intraoperative residual fluorescent tumour and residual enhancing tumour on post-operative MRI were significantly predictive of reduced survival. Carmustine wafers have no added benefit following 5-ALA guided resection. Residual fluorescence and residual enhancing disease following resection have a negative impact on survival.

Symptom clusters for revising scale membership in the analysis of prostate cancer patient reported outcome measures: a secondary data analysis of the Medical Research Council RT01 trial (ISCRTN47772397).

PURPOSE: To investigate the role of symptom clusters in the analysis and utilisation of patient reported outcome measures (PROMs) for data modelling and clinical practice. To compare symptom clusters with scales, and to explore their value in PROMs interpretation and symptom management. METHODS: A dataset called RT01 (ISCRTN47772397) of 843 prostate cancer patients was used. PROMs were reported with the University of California, Los Angeles Prostate Cancer Index (UCLA-PCI). Symptom clusters were explored with hierarchical cluster analysis (HCA) and average linkage method (correlation > 0.6). The reliability of the Urinary Function Scale was evaluated with Cronbach's Alpha. The strength of the relationship between the items was investigated with Spearman's correlation. Predictive accuracy of the clusters was compared to the scales by receiver operating characteristic (ROC) analysis. Presence of urinary symptoms at 3 years measured with the late effects on normal tissue: subjective, objective, management tool (LENT/SOM) was an endpoint. RESULTS: Two symptom clusters were identified (urinary cluster and sexual cluster). The grouping of symptom clusters was different than UCLA-PCI Scales. Two items of the urinary function scales ("number of pads" and "urinary leak interfering with sex") were excluded from the urinary cluster. The correlation with the other items in the scale ranged from 0.20 to 0.21 and 0.31 to 0.39, respectively. Cronbach's Alpha showed low correlation of those items with the Urinary Function Scale (0.14-0.36 and 0.33-0.44, respectively). All urinary function scale items were subject to a ceiling effect. Clusters had better predictive accuracy, AUC = 0.70 -0.65, while scales AUC = 0.67-0.61. CONCLUSION: This study adds to the knowledge on how cluster analysis can be applied for the interpretation and utilisation of PROMs. We conclude that multiple-item scales should be evaluated and that symptom clusters provide a study-specific approach for modelling and interpretation of PROMs.

Rosette-forming glioneuronal tumor with dissemination throughout the ventricular system: a case report.

A 33-year-old female was found to have a rosette-forming glioneuronal tumor (RGNT) occurring within the fourth ventricle with multifocal extension to the third and lateral ventricles. She presented with headaches, blurred vision, nausea, and intermittent dizziness. A brain magnetic resonance imaging (MRI) scan showed hydrocephalus and multifocal nodules throughout the ventricular system with the largest mass occupying the fourth ventricle. An endoscopic third ventriculostomy and biopsy were performed. Histological examination demonstrated a glioneuronal neoplasm with the characteristic features of RGNT. While the histopathological features of our case are well in accord with those reported in the literature, the multifocal intraventricular growth pattern has only been described twice before. Moreover, RGNT of the fourth ventricle with dissemination throughout the supratentorial ventricles has only been described once before. Long-term studies are required to assess the best treatment modalities and clinical behavior of this extremely rare disseminated RGNT entity.

CZTS (Cu2 ZnSnS4 )-based Nanomaterials in Photocatalytic and Hydrogen Production Applications: A Recent Progress towards Sustainable Environment.

A variety of unique compounds have been examined to accommodate the current demand for useful multi-functional nanomaterials, copper-based quaternary CZTS semiconductors are one of them. Due to their special characteristic features like non-toxicity, cheap, and abundance, they have been recommended in recent literature for various applications. Apart from individual CZTS, different hetero-structures have also been prepared with different compounds which is well discussed and elaborated in this article. Additionally, their preparation methods, properties, and application viability have also been discussed comprehensively. The application of CZTS such as photocatalytic dye degradation and hydrogen evolution reaction has been elaborated on in this article identifying their benefits and challenges to give readers a thorough visualization. Apart from that, challenges reported in studies, a few approaches are also mentioned to possibly counter them.

Large-scale meta-genome-wide association study reveals common genetic factors linked to radiation-induced acute toxicities across cancer types.

BACKGROUND: This study was designed to identify common genetic susceptibility and shared genetic variants associated with acute radiation-induced toxicity across 4 cancer types (prostate, head and neck, breast, and lung). METHODS: A genome-wide association study meta-analysis was performed using 19 cohorts totaling 12 042 patients. Acute standardized total average toxicity (STATacute) was modelled using a generalized linear regression model for additive effect of genetic variants, adjusted for demographic and clinical covariates (rSTATacute). Linkage disequilibrium score regression estimated shared single-nucleotide variation (SNV-formerly SNP)-based heritability of rSTATacute in all patients and for each cancer type. RESULTS: Shared SNV-based heritability of STATacute among all cancer types was estimated at 10% (SE = 0.02) and was higher for prostate (17%, SE = 0.07), head and neck (27%, SE = 0.09), and breast (16%, SE = 0.09) cancers. We identified 130 suggestive associated SNVs with rSTATacute (5.0 × 10‒8 < P < 1.0 × 10‒5) across 25 genomic regions. rs142667902 showed the strongest association (effect allele A; effect size ‒0.17; P = 1.7 × 10‒7), which is located near DPPA4, encoding a protein involved in pluripotency in stem cells, which are essential for repair of radiation-induced tissue injury. Gene-set enrichment analysis identified 'RNA splicing via endonucleolytic cleavage and ligation' (P = 5.1 × 10‒6, P = .079 corrected) as the top gene set associated with rSTATacute among all patients. In silico gene expression analysis showed that the genes associated with rSTATacute were statistically significantly up-regulated in skin (not sun exposed P = .004 corrected; sun exposed P = .026 corrected). CONCLUSIONS: There is shared SNV-based heritability for acute radiation-induced toxicity across and within individual cancer sites. Future meta-genome-wide association studies among large radiation therapy patient cohorts are worthwhile to identify the common causal variants for acute radiotoxicity across cancer types.

The Potential of Photoacoustic Imaging in Radiation Oncology.

Radiotherapy is recognized globally as a mainstay of treatment in most solid tumors and is essential in both curative and palliative settings. Ionizing radiation is frequently combined with surgery, either preoperatively or postoperatively, and with systemic chemotherapy. Recent advances in imaging have enabled precise targeting of solid lesions yet substantial intratumoral heterogeneity means that treatment planning and monitoring remains a clinical challenge as therapy response can take weeks to manifest on conventional imaging and early indications of progression can be misleading. Photoacoustic imaging (PAI) is an emerging modality for molecular imaging of cancer, enabling non-invasive assessment of endogenous tissue chromophores with optical contrast at unprecedented spatio-temporal resolution. Preclinical studies in mouse models have shown that PAI could be used to assess response to radiotherapy and chemoradiotherapy based on changes in the tumor vascular architecture and blood oxygen saturation, which are closely linked to tumor hypoxia. Given the strong relationship between hypoxia and radio-resistance, PAI assessment of the tumor microenvironment has the potential to be applied longitudinally during radiotherapy to detect resistance at much earlier time-points than currently achieved by size measurements and tailor treatments based on tumor oxygen availability and vascular heterogeneity. Here, we review the current state-of-the-art in PAI in the context of radiotherapy research. Based on these studies, we identify promising applications of PAI in radiation oncology and discuss the future potential and outstanding challenges in the development of translational PAI biomarkers of early response to radiotherapy.

Meta-GWAS identifies the heritability of acute radiation-induced toxicities in head and neck cancer.

BACKGROUND AND PURPOSE: We aimed to the genetic components and susceptibility variants associated with acute radiation-induced toxicities (RITs) in patients with head and neck cancer (HNC). MATERIALS AND METHODS: We performed the largest meta-GWAS of seven European cohorts (n = 4,042). Patients were scored weekly during radiotherapy for acute RITs including dysphagia, mucositis, and xerostomia. We analyzed the effect of variants on the average burden (measured as area under curve, AUC) per each RIT, and standardized total average acute toxicity (STATacute) score using a multivariate linear regression. We tested suggestive variants (p < 1.0x10-5) in discovery set (three cohorts; n = 2,640) in a replication set (four cohorts; n = 1,402). We meta-analysed all cohorts to calculate RITs specific SNP-based heritability, and effect of polygenic risk scores (PRSs), and genetic correlations among RITS. RESULTS: From 393 suggestive SNPs identified in discovery set; 37 were nominally significant (preplication < 0.05) in replication set, but none reached genome-wide significance (pcombined < 5 × 10-8). In-silico functional analyses identified "3'-5'-exoribonuclease activity" (FDR = 1.6e-10) for dysphagia, "inositol phosphate-mediated signalling" for mucositis (FDR = 2.20e-09), and "drug catabolic process" for STATacute (FDR = 3.57e-12) as the most enriched pathways by the RIT specific suggestive genes. The SNP-based heritability (±standard error) was 29 ± 0.08 % for dysphagia, 9 ± 0.12 % (mucositis) and 27 ± 0.09 % (STATacute). Positive genetic correlation was rg = 0.65 (p = 0.048) between dysphagia and STATacute. PRSs explained limited variation of dysphagia (3 %), mucositis (2.5 %), and STATacute (0.4 %). CONCLUSION: In HNC patients, acute RITs are modestly heritable, sharing 10 % genetic susceptibility, when PRS explains < 3 % of their variance. We identified numerus suggestive SNPs, which remain to be replicated in larger studies.

Enantio- and regioselective asymmetric allylic substitution using a chiral aminophosphinite ruthenium complex: an experimental and theoretical investigation.

The design and synthesis of a new chiral aminophosphinite-ligated ruthenium complex is described. The ruthenium complex, [Ru(AMP)2(CH3CN)2][BPh4]2 {AMP = (S)-tert-butyl 1-(diphenylphosphinooxy)-3-methylbutan-2-ylcarbamate}, has been found to catalyze nucleophilic addition of phenol and carboxylic acid to allyl chloride in a highly regioselective fashion with enantiomeric excess ranging from 12 to 90.

Response to BRAF and MEK1/2 inhibition in a young adult with BRAF V600E mutant epithelioid glioblastoma multiforme: A Case Report and Literature Review.

Epithelioid glioblastoma multiforme (eGBM) is a rare and aggressive variant of glioblastoma multiforme (GBM) that predominantly affects younger patients and can be difficult to distinguish from other gliomas. Data on how patients with eGBM might be best treated are limited, although genomic analyses have shown that almost half of tumours harbour activating BRAF gene mutations. Here we present the case of a young female with BRAF V600E-mutant eGBM who had a prolonged response to targeted therapy with the BRAF and MEK1/2 inhibitors dabrafenib and trametinib. We review current knowledge about eGBM, including the emerging role for BRAF- ± MEK1/2- targeted therapy.

Correlation of a hypoxia based tumor control model with observed local control rates in nasopharyngeal carcinoma treated with chemoradiotherapy.

PURPOSE: To extend the application of current radiation therapy (RT) based tumor control probability (TCP) models of nasopharyngeal carcinoma (NPC) to include the effects of hypoxia and chemoradiotherapy (CRT). METHODS: A TCP model is described based on the linear-quadratic model modified to account for repopulation, chemotherapy, heterogeneity of dose to the tumor, and hypoxia. Sensitivity analysis was performed to determine which parameters exert the greatest influence on the uncertainty of modeled TCP. On the basis of the sensitivity analysis, the values of specific radiobiological parameters were set to nominal values reported in the literature for NPC or head and neck tumors. The remaining radiobiological parameters were determined by fitting TCP to clinical local control data from published randomized studies using both RT and CRT. Validation of the model was performed by comparison of estimated TCP and average overall local control rate (LCR) for 45 patients treated at the institution with conventional linear-accelerator-based or helical tomotherapy based intensity-modulated RT and neoadjuvant chemotherapy. RESULTS: Sensitivity analysis demonstrates that the model is most sensitive to the radiosensitivity term alpha and the dose per fraction. The estimated values of alpha and OER from data fitting were 0.396 Gy(-1) and 1.417. The model estimate of TCP (average 90.9%, range 26.9%-99.2%) showed good correlation with the LCR (86.7%). CONCLUSIONS: The model implemented in this work provides clinicians with a useful tool to predict the success rate of treatment, optimize treatment plans, and compare the effects of multimodality therapy.

Evaluation of Deep Learning to Augment Image-Guided Radiotherapy for Head and Neck and Prostate Cancers.

Importance: Personalized radiotherapy planning depends on high-quality delineation of target tumors and surrounding organs at risk (OARs). This process puts additional time burdens on oncologists and introduces variability among both experts and institutions. Objective: To explore clinically acceptable autocontouring solutions that can be integrated into existing workflows and used in different domains of radiotherapy. Design, Setting, and Participants: This quality improvement study used a multicenter imaging data set comprising 519 pelvic and 242 head and neck computed tomography (CT) scans from 8 distinct clinical sites and patients diagnosed either with prostate or head and neck cancer. The scans were acquired as part of treatment dose planning from patients who received intensity-modulated radiation therapy between October 2013 and February 2020. Fifteen different OARs were manually annotated by expert readers and radiation oncologists. The models were trained on a subset of the data set to automatically delineate OARs and evaluated on both internal and external data sets. Data analysis was conducted October 2019 to September 2020. Main Outcomes and Measures: The autocontouring solution was evaluated on external data sets, and its accuracy was quantified with volumetric agreement and surface distance measures. Models were benchmarked against expert annotations in an interobserver variability (IOV) study. Clinical utility was evaluated by measuring time spent on manual corrections and annotations from scratch. Results: A total of 519 participants' (519 [100%] men; 390 [75%] aged 62-75 years) pelvic CT images and 242 participants' (184 [76%] men; 194 [80%] aged 50-73 years) head and neck CT images were included. The models achieved levels of clinical accuracy within the bounds of expert IOV for 13 of 15 structures (eg, left femur, κ = 0.982; brainstem, κ = 0.806) and performed consistently well across both external and internal data sets (eg, mean [SD] Dice score for left femur, internal vs external data sets: 98.52% [0.50] vs 98.04% [1.02]; P = .04). The correction time of autogenerated contours on 10 head and neck and 10 prostate scans was measured as a mean of 4.98 (95% CI, 4.44-5.52) min/scan and 3.40 (95% CI, 1.60-5.20) min/scan, respectively, to ensure clinically accepted accuracy. Manual segmentation of the head and neck took a mean 86.75 (95% CI, 75.21-92.29) min/scan for an expert reader and 73.25 (95% CI, 68.68-77.82) min/scan for a radiation oncologist. The autogenerated contours represented a 93% reduction in time. Conclusions and Relevance: In this study, the models achieved levels of clinical accuracy within expert IOV while reducing manual contouring time and performing consistently well across previously unseen heterogeneous data sets. With the availability of open-source libraries and reliable performance, this creates significant opportunities for the transformation of radiation treatment planning.

Opportunities for Quantitative Translational Modeling in Oncology.

A 2-day meeting was held by members of the UK Quantitative Systems Pharmacology Network () in November 2018 on the topic of Translational Challenges in Oncology. Participants from a wide range of backgrounds were invited to discuss current and emerging modeling applications in nonclinical and clinical drug development, and to identify areas for improvement. This resulting perspective explores opportunities for impactful quantitative pharmacology approaches. Four key themes arose from the presentations and discussions that were held, leading to the following recommendations: Evaluate the predictivity and reproducibility of animal cancer models through precompetitive collaboration. Apply mechanism of action (MoA) based mechanistic models derived from nonclinical data to clinical trial data. Apply MoA reflective models across trial data sets to more robustly quantify the natural history of disease and response to differing interventions. Quantify more robustly the dose and concentration dependence of adverse events through mathematical modelling techniques and modified trial design.

Heparin-induced thrombocytopaenia presenting as acute aortic mural thrombosis.

Heparin-induced thrombocytopaenia (HIT) is a life and limb-threatening acquired autoimmune complication of heparin-based treatment, characterised by thrombocytopaenia and thrombosis. We present a case of a 77-year-old female with concomitant metastatic ovarian and breast cancer who presented to our institution with worsening shortness of breath. She had been diagnosed with acute pulmonary embolism 1 month earlier that was treated with therapeutic low molecular weight heparin (LMWH). In view of her worsening symptoms, CT imaging was performed. This demonstrated significant progression of the bilateral pulmonary emboli and new mural thrombosis of the thoracic aorta, despite being compliant with therapeutic anticoagulation. She had also developed thrombocytopaenia since commencing LMWH, which raised the clinical suspicion of HIT syndrome. The HIT pre-test probability score was intermediate and LMWH was immediately discontinued pending further investigation. She was commenced on rivaroxaban, a direct oral anticoagulant, and her platelet count soon recovered. Laboratory testing was strongly positive on both immunological and functional assays, thus confirming a diagnosis of HIT syndrome. A repeat CT scan 3 weeks later showed a reduction in the overall thrombus load. Whilst venous thrombosis is observed in as many as half of patients with HIT, arterial thrombosis is a far less common event. Furthermore, arterial involvement usually affects the distal vessels with significant atherosclerotic burden and typically presents as acute limb ischaemia or ischaemic stroke. Aortic thrombosis, as in this case, is a rare complication of HIT syndrome.

Automated customized retrieval of radiotherapy data for clinical trials, audit and research.

OBJECTIVE: To enable fast and customizable automated collection of radiotherapy (RT) data from tomotherapy storage. METHODS: Human-readable data maps (TagMaps) were created to generate DICOM-RT (Digital Imaging and Communications in Medicine standard for Radiation Therapy) data from tomotherapy archives, and provided access to "hidden" information comprising delivery sinograms, positional corrections and adaptive-RT doses. RESULTS: 797 data sets totalling 25,000 scans were batch-exported in 31.5 h. All archived information was restored, including the data not available via commercial software. The exported data were DICOM-compliant and compatible with major commercial tools including RayStation, Pinnacle and ProSoma. The export ran without operator interventions. CONCLUSION: The TagMap method for DICOM-RT data modelling produced software that was many times faster than the vendor's solution, required minimal operator input and delivered high volumes of vendor-identical DICOM data. The approach is applicable to many clinical and research data processing scenarios and can be adapted to recover DICOM-RT data from other proprietary storage types such as Elekta, Pinnacle or ProSoma. Advances in knowledge: A novel method to translate data from proprietary storage to DICOM-RT is presented. It provides access to the data hidden in electronic archives, offers a working solution to the issues of data migration and vendor lock-in and paves the way for large-scale imaging and radiomics studies.

Identifying risk factors for L'Hermitte's sign after IMRT for head and neck cancer.

BACKGROUND: L'Hermitte's sign (LS) after chemoradiotherapy for head and neck cancer appears related to higher spinal cord doses. IMRT plans limit spinal cord dose, but the incidence of LS remains high. METHODS: One hundred seventeen patients treated with TomoTherapy™ between 2008 and 2015 prospectively completed a side-effect questionnaire (VoxTox Trial Registration: UK CRN ID 13716). Baseline patient and treatment data were collected. Radiotherapy plans were analysed; mean and maximum spinal cord dose and volumes receiving 10, 20, 30 and 40 Gy were recorded. Dose variation across the cord was examined. These data were included in a logistic regression model. RESULTS: Forty two patients (35.9%) reported LS symptoms. Concurrent weekly cisplatin did not increase LS risk (p = 0.70, OR = 1.23 {95% CI 0.51-2.34}). Of 13 diabetic participants (9 taking metformin), only 1 developed LS (p = 0.025, OR = 0.13 {95% CI 0.051-3.27}). A refined binary logistic regression model showed that patients receiving unilateral radiation (p = 0.019, OR = 2.06 {95% CI 0.15-0.84}) were more likely to develop LS. Higher V40Gy (p = 0.047, OR = 1.06 {95% CI 1.00-1.12}), and younger age (mean age 56.6 vs 59.7, p = 0.060, OR = 0.96 {95% CI 0.92-1.00}) were associated with elevated risk of LS, with borderline significance. CONCLUSIONS: In this cohort, concomitant cisplatin did not increase risk, and LS incidence was lower in diabetic patients. Patient age and dose gradients across the spinal cord may be important factors.

Autosegmentation of prostate anatomy for radiation treatment planning using deep decision forests of radiomic features.

Machine learning for image segmentation could provide expedited clinic workflow and better standardization of contour delineation. We evaluated a new model using deep decision forests of image features in order to contour pelvic anatomy on treatment planning CTs. 193 CT scans from one UK and two US institutions for patients undergoing radiotherapy treatment for prostate cancer from 2012-2016 were anonymized. A decision forest autosegmentation model was trained on a random selection of 94 images from Institution 1 and tested on 99 scans from Institution 1, 2, and 3. The accuracy of model contours was measured with the Dice similarity coefficient (DSC) and the median slice-wise Hausdorff distance (MSHD) using clinical contours as the ground truth reference. Two comparison studies were performed. The accuracy of the model was compared to four commercial software packages on twenty randomly-selected images. Additionally, inter-observer variability (IOV) of contours between three radiation oncology experts and the original contours was evaluated on ten randomly-selected images. The highest median values of DSC across all institutions were 0.94-0.97 for bladder (with interquartile range, or IQR, of 0.92-0.98) and 0.96-0.97 (IQR 0.94-0.97) for femurs. Good agreement was seen for prostate, with median DSC 0.75-0.76 (IQR 0.67-0.82), and rectum, with median DSC 0.71-0.82 (IQR 0.63-0.87). The lowest median scores were 0.49-0.70 for seminal vesicles (IQR 0.31-0.79). For the commercial software comparison, model-based segmentation produced higher DSC than atlas-based segmentation, with decision forests producing highest DSC for all organs of interest. For the interobserver study, variability in DSC between observers was similar to the agreement between the model and ground truth. Deep decision forests of radiomic features can generate contours of pelvic anatomy with reasonable agreement with physician contours. This method could be useful for automated treatment planning, and autosegmentation may improve efficiency and increase standardization in the clinic.