Comparison of Machine Leaning Models for Prediction of Acute Pain Severity and On-Treatment Opioid Utilization in Oral Cavity and Oropharyngeal Cancer Patients Receiving Radiation Therapy: Exploratory Analysis from a Large-Scale Retrospective Cohort.

Background: Acute pain is a common and debilitating symptom experienced by oral cavity and oropharyngeal cancer (OC/OPC) patients undergoing radiation therapy (RT). Uncontrolled pain can result in opioid overuse and increased risks of long-term opioid dependence. The specific aim of this exploratory analysis was the prediction of severe acute pain and opioid use in the acute on-treatment setting, to develop risk-stratification models for pragmatic clinical trials. Materials and Methods: A retrospective study was conducted on 900 OC/OPC patients treated with RT during 2017 to 2023. Clinical data including demographics, tumor data, pain scores and medication data were extracted from patient records. On-treatment pain intensity scores were assessed using a numeric rating scale (0-none, 10-worst) and total opioid doses were calculated using morphine equivalent daily dose (MEDD) conversion factors. Analgesics efficacy was assessed based on the combined pain intensity and the total required MEDD. ML models, including Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Model (GBM) were developed and validated using ten-fold cross-validation. Performance of models were evaluated using discrimination and calibration metrics. Feature importance was investigated using bootstrap and permutation techniques. Results: For predicting acute pain intensity, the GBM demonstrated superior area under the receiver operating curve (AUC) (0.71), recall (0.39), and F1 score (0.48). For predicting the total MEDD, LR outperformed other models in the AUC (0.67). For predicting the analgesics efficacy, SVM achieved the highest specificity (0.97), and best calibration (ECE of 0.06), while RF and GBM achieved the same highest AUC, 0.68. RF model emerged as the best calibrated model with ECE of 0.02 for pain intensity prediction and 0.05 for MEDD prediction. Baseline pain scores and vital signs demonstrated the most contributed features for the different predictive models. Conclusion: These ML models are promising in predicting end-of-treatment acute pain and opioid requirements and analgesics efficacy in OC/OPC patients undergoing RT. Baseline pain score, vital sign changes were identified as crucial predictors. Implementation of these models in clinical practice could facilitate early risk stratification and personalized pain management. Prospective multicentric studies and external validation are essential for further refinement and generalizability.

Sinonasal NUT carcinoma: A consecutive case series and systematic review.

BACKGROUND: Sinonasal NUT carcinoma is an extremely rare, lethal malignancy with limited literature. METHODS: A case series was conduction of all patients with sinonasal NUT carcinoma at a single institution between 2010 and 2022. Survival and associated were evaluated. A systematic review of the literature was performed. RESULTS: In 12 patients, followed for a median of 1.5 years, the median overall survival (OS) and disease-specific survival (DSS) were both 14.6 months. Patients with maxillary sinus tumors were 91% more likely to survive (hazard ratio [HR]: 0.094, 95% confidence interval [CI]: 0.011-0.78, p = 0.011). Patients with higher-stage disease stage had worse OS (stage IVb-c vs. III-IVa, p = 0.05). All three patients who were alive with no evidence of disease received induction chemotherapy. CONCLUSION: For patients with sinonasal NUT carcinoma, the median survival was 15 months but better with lower-stage and maxillary tumors. Induction chemotherapy may be beneficial.

Surgery After BRAF-Directed Therapy Is Associated with Improved Survival in BRAFV600E Mutant Anaplastic Thyroid Cancer: A Single-Center Retrospective Cohort Study.

Background: The aim of this study was to describe the oncologic outcomes of patients with BRAFV600E-mutated anaplastic thyroid cancer (ATC) who had neoadjuvant BRAF-directed therapy with subsequent surgery. For context, we also reviewed patients who received BRAF-directed therapy after surgery, and those who did not have surgery after BRAF-directed therapy. Methods: This was a single-center retrospective cohort study conducted at a tertiary care cancer center in Texas from 2017 to 2021. Fifty-seven consecutive patients with BRAFV600E-mutated ATC and at least 1 month of BRAF-directed therapy were included. Primary outcomes were overall survival (OS) and progression-free survival (PFS). Results: All patients had stage IVB (35%) or IVC (65%) ATC. Approximately 70% of patients treated with BRAF-directed therapy ultimately had surgical resection of residual disease. Patients who had neoadjuvant BRAF-directed therapy followed by surgery (n = 32) had 12-month OS of 93.6% [confidence interval (CI) 84.9-100] and PFS of 84.4% [CI 71.8-96.7]. Patients who had surgery before BRAF-directed therapy (n = 12) had 12-month OS of 74.1% [CI 48.7-99.5] and PFS of 50% [CI 21.7-78.3]. Finally, patients who did not receive surgery after BRAF-directed therapy (n = 13) had 12-month OS of 38.5% [CI 12.1-64.9] and PFS of 15.4% [CI 0-35.0]. Neoadjuvant BRAF-directed therapy reduced tumor size, extent of surgery, and surgical morbidity score. Subgroup analysis suggested that any residual ATC in the surgical specimen was associated with significantly worse 12-month OS and PFS (OS = 83.3% [CI 62.6-100], PFS = 61.5% [CI 35.1-88]) compared with patients with pathologic ATC complete response (OS = 100%, PFS = 100%). Conclusions: We observed that neoadjuvant BRAF-directed therapy reduced extent of surgery and surgical morbidity. While acknowledging potential selection bias, the 12-month OS rate appeared higher in patients who had BRAF-directed therapy followed by surgery as compared with BRAF-directed therapy without surgery; yet, it was not significantly different from surgery followed by BRAF-directed therapy. PFS appeared higher in patients treated with neoadjuvant BRAF-directed therapy relative to patients in the other groups. These promising results of neoadjuvant BRAF-directed therapy followed by surgery for BRAF-mutated ATC should be confirmed in prospective clinical trials.

Impact of Somatic Mutations on Survival Outcomes in Patients With Anaplastic Thyroid Carcinoma.

PURPOSE: Anaplastic thyroid carcinoma (ATC) uniformly present with aggressive disease, but the mutational landscape of tumors varies. We aimed to determine whether tumor mutations affect survival outcomes in ATC. MATERIALS AND METHODS: Patients who underwent mutation sequencing using targeted gene panels between 2005 and 2019 at a tertiary referral center were included. Associations between mutation status and survival outcomes were assessed using Cox proportional hazards models. RESULTS: A total of 202 patients were included, where 122 died of ATC (60%). The median follow-up was 31 months (interquartile range, 18-45 months). The most common mutations were in TP53 (59%), BRAF (41%), TERT promoter (37%), and the RAS gene family (22%). Clinicopathologic characteristics and overall survival (OS) significantly correlated with mutations in BRAFV600E and RAS, which were mutually exclusive. The BRAFV600E mutation was associated with the presence of a papillary thyroid carcinoma precursor and significantly better OS (median OS: 24 months). RAS-mutated patients more commonly presented without cervical lymph node involvement but had the worst OS (median OS: 6 months). Tumors that were wild-type for both BRAF and RAS were enriched for NF1 mutations and harbored intermediate prognosis (median OS: 15 months). In multivariate analyses, RAS mutations were associated with a more than 2.5-fold higher risk of death (adjusted hazard ratio, 2.64; 95% CI, 1.66 to 4.20) compared with BRAFV600E. In patients treated with BRAF-directed therapy (n = 60), disease progression occurred in 48% of patients (n = 29). The median progression-free survival was 14 months. The presence of a TP53 mutation was independently associated with reduced progression-free survival in BRAFV600E-mutated patients treated with BRAF-directed therapy (adjusted hazard ratio, 2.89; 95% CI, 1.35 to 6.21). CONCLUSION: Mutation analysis provides prognostic information in ATC and should be incorporated into routine clinical care.

Risk factors associated with patient-reported fatigue among long-term oropharyngeal carcinoma survivors.

BACKGROUND: The study objective is to identify risk factors associated with fatigue among long-term OPC survivors. METHODS: This cross-sectional study included disease-free OPC survivors treated curatively between 2000 and 2013 who were surveyed from September 2015 to July 2016. The outcome variable was patient-reported fatigue. Multivariable logistic regression was used to identify factors associated with moderate to severe fatigue. RESULTS: Among 863 OPC survivors, 17.4% reported moderate to severe fatigue. Self-reported thyroid problems (OR: 2.01; p = 0.003), current cigarette smoking at time of survey (OR: 3.85; p = 0.001), late lower cranial neuropathy (OR: 3.44; p = 0.002), and female sex (OR: 1.91; p = 0.010) were concurrent risk factors of reporting moderate to severe fatigue. Ipsilateral intensity-modulated radiotherapy (OR: 0.18; p = 0.014) was associated with lower risk of reporting moderate to severe fatigue. CONCLUSIONS: Our study identified thyroid problems, smoking, and late lower cranial neuropathy as associated with moderate to severe fatigue. These findings should be further validated in prospective studies to address fatigue among OPC survivors.

Impact of RBE variations on risk estimates of temporal lobe necrosis in patients treated with intensity-modulated proton therapy for head and neck cancer.

BACKGROUND: Temporal lobe necrosis (TLN) is a potential late effect after radiotherapy for skull base head and neck cancer (HNC). Several photon-derived dose constraints and normal tissue complication probability (NTCP) models have been proposed, however variation in relative biological effectiveness (RBE) may challenge the applicability of these dose constraints and models in proton therapy. The purpose of this study was therefore to investigate the influence of RBE variations on risk estimates of TLN after Intensity-Modulated Proton Therapy for HNC. MATERIAL AND METHODS: Seventy-five temporal lobes from 45 previously treated patients were included in the analysis. Sixteen temporal lobes had radiation associated Magnetic Resonance image changes (TLIC) suspected to be early signs of TLN. Fixed (RWDFix) and variable RBE-weighed doses (RWDVar) were calculated using RBE = 1.1 and two RBE models, respectively. RWDFix and RWDVar for temporal lobes were compared using Friedman's test. Based on RWDFix, six NTCP models were fitted and internally validated through bootstrapping. Estimated probabilities from RWDFix and RWDVar were compared using paired Wilcoxon test. Seven dose constraints were evaluated separately for RWDFix and RWDVar by calculating the observed proportion of TLIC in temporal lobes meeting the specific dose constraints. RESULTS: RWDVar were significantly higher than RWDFix (p < 0.01). NTCP model performance was good (AUC:0.79-0.84). The median difference in estimated probability between RWDFix and RWDVar ranged between 5.3% and 20.0% points (p < 0.01), with V60GyRBE and DMax at the smallest and largest differences, respectively. The proportion of TLIC was higher for RWDFix (4.0%-13.1%) versus RWDVar (1.3%-5.3%). For V65GyRBE ≤ 0.03 cc the proportion of TLIC was less than 5% for both RWDFix and RWDVar. CONCLUSION: NTCP estimates were significantly influenced by RBE variations. Dmax as model predictor resulted in the largest deviations in risk estimates between RWDFix and RWDVar. V65GyRBE ≤ 0.03 cc was the most consistent dose constraint for RWDFix and RWDVar.

Mixed Effect Modeling of Dose and Linear Energy Transfer Correlations With Brain Image Changes After Intensity Modulated Proton Therapy for Skull Base Head and Neck Cancer.

PURPOSE: Intensity modulated proton therapy (IMPT) could yield high linear energy transfer (LET) in critical structures and increased biological effect. For head and neck cancers at the skull base this could potentially result in radiation-associated brain image change (RAIC). The purpose of the current study was to investigate voxel-wise dose and LET correlations with RAIC after IMPT. METHODS AND MATERIALS: For 15 patients with RAIC after IMPT, contrast enhancement observed on T1-weighted magnetic resonance imaging was contoured and coregistered to the planning computed tomography. Monte Carlo calculated dose and dose-averaged LET (LETd) distributions were extracted at voxel level and associations with RAIC were modelled using uni- and multivariate mixed effect logistic regression. Model performance was evaluated using the area under the receiver operating characteristic curve and precision-recall curve. RESULTS: An overall statistically significant RAIC association with dose and LETd was found in both the uni- and multivariate analysis. Patient heterogeneity was considerable, with standard deviation of the random effects of 1.81 (1.30-2.72) for dose and 2.68 (1.93-4.93) for LETd, respectively. Area under the receiver operating characteristic curve was 0.93 and 0.95 for the univariate dose-response model and multivariate model, respectively. Analysis of the LETd effect demonstrated increased risk of RAIC with increasing LETd for the majority of patients. Estimated probability of RAIC with LETd = 1 keV/µm was 4% (95% confidence interval, 0%, 0.44%) and 29% (95% confidence interval, 0.01%, 0.92%) for 60 and 70 Gy, respectively. The TD15 were estimated to be 63.6 and 50.1 Gy with LETd equal to 2 and 5 keV/µm, respectively. CONCLUSIONS: Our results suggest that the LETd effect could be of clinical significance for some patients; LETd assessment in clinical treatment plans should therefore be taken into consideration.

Highly conformal reirradiation in patients with prior oropharyngeal radiation: Clinical efficacy and toxicity outcomes.

BACKGROUND: Reirradiation of head and neck cancer is associated with high rates of locoregional failure and potentially severe treatment-related toxicity. We report our institutional experience of reirradiation using modern highly conformal radiotherapy approaches in patients with prior oropharyngeal radiation. METHODS: We reviewed patients receiving curative-intent reirradiation with intensity-modulated radiation therapy, stereotactic body radiation therapy, and proton beam radiotherapy at our institution from 1999 to 2019. Disease control, survival, and toxicity rates following reirradiation were determined. RESULTS: Sixty-nine patients were evaluated. Local control (LC), progression-free survival, and overall survival at 2 years following reirradiation were 77%, 35%, and 51%, respectively. Grade 3 or greater (G3+) late toxicities occurred in 46% of patients and 41% required feeding tube placement during or after reirradiation. CONCLUSIONS: In select patients with prior oropharyngeal radiation, highly conformal reirradiation offers acceptable LC, but G3+ toxicity and out-of-field failure rates remain high. These findings warrant continued evaluation of new multimodality approaches to improve oncologic outcomes.

Assessing patient-reported symptom burden of long-term head and neck cancer survivors at annual surveillance in survivorship clinic.

BACKGROUND: This study reports long-term head and neck cancer (HNC) patient-reported symptoms using the MD Anderson Symptom Inventory Head and Neck Cancer Module (MDASI-HN) in a large cohort of HNC survivors. METHODS: MDASI-HN results were prospectively collected from an institutional survivorship database. Associations with clinicopathologic data were analyzed using χ2 , Mann-Whitney, and univariate regression. RESULTS: Nine hundred and twenty-eight patients were included. Forty-six percent had oropharyngeal primary tumors. Eighty-two percent had squamous cell carcinoma. Fifty-six percent of patients had ablative surgery and 81% had radiation therapy as a component of treatment. The most severe symptoms were xerostomia and dysphagia. Symptom scores were worst for hypopharynx and varied by subsite. Patients treated with chemoradiation or surgery followed by radiation ± chemotherapy reported the worst symptoms while patient treated with surgery plus radiation ± chemotherapy reported the worst interference. CONCLUSION: HNC survivors describe their long-term symptom burden and inform efforts to improve care many years into survivorship.

Xerostomia-related quality of life for patients with oropharyngeal carcinoma treated with proton therapy.

PURPOSE: We report longitudinal patient-reported quality-of-life (QoL) outcomes related to xerostomia in patients with oropharyngeal cancer treated with intensity-modulated proton therapy (IMPT). MATERIALS AND METHODS: Patients treated from May 2012 through December 2016 at a single institution for AJCC7 stage III-IV, M0 oropharyngeal cancer were given the 15-item Xerostomia-Related QoL Scale (XeQoLS) before, during, and for up to 2 years after treatment. We evaluated the evolution of xerostomia-related QoL over that time, and examined potential associations between those measures with clinical characteristics. RESULTS: Sixty-nine patients had XeQoLS scores at baseline and at least once either during or after treatment. The mean (±SD) XeQoLS score (0-4) was 0.24 ±â€¯0.57 at baseline. Subsequent scores were 2.00 ±â€¯1.01 at 6 weeks on treatment, and 1.03 ±â€¯0.76, 0.97 ±â€¯0.78, 0.82 ±â€¯0.69, and 0.70 ±â€¯0.75 at 10 weeks, 6 months, 1 year, and 2 years after treatment, respectively. All were statistically different from baseline (p < 0.001). Univariate analyses demonstrated associations between XeQoLS score and time (p < 0.0001 for each interval), baseline XeQoLS score (p < 0.0001), stage (p = 0.008), N status (p = 0.006), and mean oral cavity dose (p = 0.038), but not for age, sex, T status, receipt of chemotherapy, smoking history, disease site, laterality of neck irradiation, mean parotid dose, or mean submandibular dose. Multivariate analysis suggested that baseline XeQoLS scores, phase of treatment, and N status were associated with XeQoLS scores measured during treatment and recovery. CONCLUSIONS: Patients receiving IMPT reported the greatest xerostomia-related QoL impairment at 6 weeks on treatment, with a 49% improvement by 10 weeks after treatment; however, XeQoLS scores remained above baseline after 2 years. As we aim to establish the value of IMPT in oropharyngeal tumors to de-intensify treatment over conventional therapy, these data help inform discussions about xerostomia-related quality of life for patients with oropharyngeal cancer treated with IMPT.

Complete Surgical Resection Following Neoadjuvant Dabrafenib Plus Trametinib in BRAFV600E-Mutated Anaplastic Thyroid Carcinoma.

Background: When achieved, complete surgical resection improves outcomes in anaplastic thyroid carcinoma (ATC). However, most ATC patients present with advanced inoperable disease, often with impending airway obstruction, increased hemorrhage risk, and significant dysphagia. Novel treatment strategies are critically needed to improve disease control and decrease locoregional morbidity. The objective of this study was to determine the feasibility and effectiveness of a neoadjuvant regimen by using dabrafenib with trametinib followed by surgical resection in patients with initially unresectable BRAFV600E-mutated ATC. Methods: Case series of six consecutive patients with BRAFV600E-mutated ATC diagnosed between January 2017 and February 2018. Pathologic confirmation of ATC was obtained before treatment. BRAFV600E status was ascertained via immunohistochemistry or sequencing of circulating tumor DNA. All patients received dabrafenib and trametinib (DT) followed by surgical resection and adjuvant chemoradiation. Three patients also received pembrolizumab. Results: Complete surgical resection was achieved in all patients. Histopathologic analyses of resected specimens showed high pathologic response rates with significantly decreased ATC viability and residual papillary thyroid carcinoma components. Overall survival at six months and one year was 100% and 83%, respectively. Locoregional control rate was 100%. Two patients died of distant metastases without evidence of locoregional disease at 8 and 14 months from diagnosis. The remaining four patients had no evidence of disease at the last follow-up. Conclusions: We report the first series in the literature of BRAFV600E-mutated ATC patients with locoregionally advanced disease treated with DT followed by surgical resection. We demonstrated feasibility of complete resection, decreased need for tracheostomy, high pathologic response rates, and durable locoregional control with symptom amelioration.

Characterization of a new physical phantom for testing rigid and deformable image registration.

The purpose of this study was to describe a new user-friendly, low-cost phantom that was developed to test the accuracy of rigid and deformable image registration (DIR) systems and to demonstrate the functional efficacy of the new phantom. The phantom was constructed out of acrylic and includes a variety of inserts that simulate different tissue shapes and properties. It can simulate deformations and location changes in patient anatomy by changing the rotations of both the phantom and the inserts. CT scans of this phantom were obtained and used to test the rigid and deformable registration accuracy of the Velocity software. Eight rotation and translation scenarios were used to test the rigid registration accuracy, and 11 deformation scenarios were used to test the DIR accuracy. The mean rotation accuracies in the X-Y (axial) and X-Z (coronal) planes were 0.50° and 0.13°, respectively. The mean translation accuracy was 1 mm in both the X and Y direction and was tested in soft tissue and bone. The DIR accuracies for soft tissue and bone were 0.93 (mean Dice similarity coefficient), 8.3 and 4.5 mm (mean Hausdouff distance), 0.95 and 0.79 mm (mean distance), and 1.13 and 1.12 (mean volume ratio) for soft tissue content (DTE oil) and bone, respectively. The new phantom has a simple design and can be constructed at a low cost. This phantom will allow DIR systems to be effectively and efficiently verified to ensure system performance.

Age-adjusted comorbidity and survival in locally advanced laryngeal cancer.

BACKGROUND: The purpose of this study was to quantify the relationship among age, pretreatment comorbidity, and survival outcomes in patients with locally advanced laryngeal cancer. METHODS: Baseline comorbidity data were collected and age-adjusted Charlson Comorbidity Index (CCI) was calculated for each case. Kaplan-Meier and Cox proportional hazards modeling were used to determine associations with survival. RESULTS: For 548 patients, with a median age of 59 years (range 31-91 years), 58% were treated with larynx preservation and the rest with total laryngectomy and adjuvant radiotherapy (RT). Two hundred thirty-eight patients (43%) had at least 1 comorbidity each. Cardiovascular diseases were the most common comorbidities (19%). The 5-year overall survival (OS) for patients with CCI ≤3 (n = 442) were superior to CCI >3 (n = 106; 60% vs 41%; P < .0001), although the 5-year disease-specific survival (DSS) rates were not significantly different. The 5-year noncancer CSS was better for age-adjusted CCI ≤3 (88% vs 67%; P < .0001). CONCLUSION: The age-adjusted CCI is a significant predictor of noncancer CSS and OS for patients with locally advanced laryngeal cancer but is not associated with DSS.

Proton Therapy for Head and Neck Cancers.

Because of its sharp lateral penumbra and steep distal fall-off, proton therapy offers dosimetric advantages over photon therapy. In head and neck cancer, proton therapy has been used for decades in the treatment of skull-base tumors. In recent years the use of proton therapy has been extended to numerous other disease sites, including nasopharynx, oropharynx, nasal cavity and paranasal sinuses, periorbital tumors, skin, and salivary gland, or to reirradiation. The aim of this review is to present the physical properties and dosimetric benefit of proton therapy over advanced photon therapy; to summarize the clinical benefit described for each disease site; and to discuss issues of patient selection and cost-effectiveness.

Identifying novel genes and biological processes relevant to the development of cancer therapy-induced mucositis: An informative gene network analysis.

Mucositis is a complex, dose-limiting toxicity of chemotherapy or radiotherapy that leads to painful mouth ulcers, difficulty eating or swallowing, gastrointestinal distress, and reduced quality of life for patients with cancer. Mucositis is most common for those undergoing high-dose chemotherapy and hematopoietic stem cell transplantation and for those being treated for malignancies of the head and neck. Treatment and management of mucositis remain challenging. It is expected that multiple genes are involved in the formation, severity, and persistence of mucositis. We used Ingenuity Pathway Analysis (IPA), a novel network-based approach that integrates complex intracellular and intercellular interactions involved in diseases, to systematically explore the molecular complexity of mucositis. As a first step, we searched the literature to identify genes that harbor or are close to the genetic variants significantly associated with mucositis. Our literature review identified 27 candidate genes, of which ERCC1, XRCC1, and MTHFR were the most frequently studied for mucositis. On the basis of this 27-gene list, we used IPA to generate gene networks for mucositis. The most biologically significant novel molecules identified through IPA analyses included TP53, CTNNB1, MYC, RB1, P38 MAPK, and EP300. Additionally, uracil degradation II (reductive) and thymine degradation pathways (p = 1.06-08) were most significant. Finally, utilizing 66 SNPs within the 8 most connected IPA-derived candidate molecules, we conducted a genetic association study for oral mucositis in the head and neck cancer patients who were treated using chemotherapy and/or radiation therapy (186 head and neck cancer patients with oral mucositis vs. 699 head and neck cancer patients without oral mucositis). The top ranked gene identified through this association analysis was RB1 (rs2227311, p-value = 0.034, odds ratio = 0.67). In conclusion, gene network analysis identified novel molecules and biological processes, including pathways related to inflammation and oxidative stress, that are relevant to mucositis development, thus providing the basis for future studies to improve the management and treatment of mucositis in patients with cancer.

Thyroid Gland Malignancies.

Surgery remains the most important effective treatment for differentiated (DTC) and medullary thyroid cancer (MTC). Radioactive iodine (RAI) is another important treatment but is reserved only for DTC whose disease captures RAI. Once patients fail primary therapy, observation is often recommended, as most DTC and MTC patients will have indolent disease. However, in a fraction of patients, systemic therapy must be considered. In recent decades 4 systemic therapies have been approved by the United States FDA for DTC and MTC. Sorafenib and lenvatinib are approved for DTC and vandetanib and cabozantinib for MTC. Anaplastic thyroid cancer (ATC) is a rare and rapidly progressive form of thyroid cancer with a very high mortality rate. Treatment of ATC remains a challenge. Most patients are not surgical candidates at diagnosis due to advanced disease. External beam radiation and radiosensitizing radiation are the mainstay of therapy at this time. However, exciting new drugs and approaches to therapy are on the horizon but it will take a concerted, worldwide effort to complete clinical trials in order to find effective therapies that will improve the overall survival for this devastating disease.

Prospective randomized double-blind study of atlas-based organ-at-risk autosegmentation-assisted radiation planning in head and neck cancer.

BACKGROUND AND PURPOSE: Target volumes and organs-at-risk (OARs) for radiotherapy (RT) planning are manually defined, which is a tedious and inaccurate process. We sought to assess the feasibility, time reduction, and acceptability of an atlas-based autosegmentation (AS) compared to manual segmentation (MS) of OARs. MATERIALS AND METHODS: A commercial platform generated 16 OARs. Resident physicians were randomly assigned to modify AS OAR (AS+R) or to draw MS OAR followed by attending physician correction. Dice similarity coefficient (DSC) was used to measure overlap between groups compared with attending approved OARs (DSC=1 means perfect overlap). 40 cases were segmented. RESULTS: Mean ± SD segmentation time in the AS+R group was 19.7 ± 8.0 min, compared to 28.5 ± 8.0 min in the MS cohort, amounting to a 30.9% time reduction (Wilcoxon p<0.01). For each OAR, AS DSC was statistically different from both AS+R and MS ROIs (all Steel-Dwass p<0.01) except the spinal cord and the mandible, suggesting oversight of AS/MS processes is required; AS+R and MS DSCs were non-different. AS compared to attending approved OAR DSCs varied considerably, with a chiasm mean ± SD DSC of 0.37 ± 0.32 and brainstem of 0.97 ± 0.03. CONCLUSIONS: Autosegmentation provides a time savings in head and neck regions of interest generation. However, attending physician approval remains vital.