Adjuvant radiation following clear margin resection of high T-stage cutaneous squamous cell carcinoma halves the risk of local and locoregional recurrence: A dual-center retrospective study.

BACKGROUND: Although adjuvant radiation (ART) following clear margin surgery is recommended for select high-risk cutaneous squamous cell carcinomas, efficacy data are limited. OBJECTIVE: To evaluate the impact of ART on outcomes following clear margin surgery for high T-stage cutaneous squamous cell carcinomas. METHODS: A 20-year retrospective cohort study at 2 academic centers of high T-stage cutaneous squamous cell carcinomas (Brigham and Women's Hospital T2b or T3) with negative histologic margins post resection. Local recurrence (LR) and locoregional recurrence (LRR) were compared by whether tumors received ART or observation. RESULTS: A total of 508 tumors were included, of which 96 underwent ART (ART+). ART+ had a lower 5-year cumulative incidence of LR (ART+, 3.6% [95% CI, 1.6%-7.7%] vs ART-, 8.7% [95% CI, 6.3%-12.0%]) and LRR (ART+, 7.5% [95% CI, 4.4%-11.9%] vs ART-, 15.3% [95% CI, 11.9%-22.1%]). Recurrent tumors ≥6 cm or Brigham and Women's Hospital T3 tumors were classified as high-risk due to a higher 5-year cumulative incidence of LRR (High-risk, 26.3% [95% CI, 19.0%-35.7%]). High-risk tumors treated with ART had a lower 5-year cumulative incidence of LRR (ART+, 17.2% [95% CI, 11.9%-26.4%] vs ART-, 31.0% [95% CI, 26.1%-40.8%]). LIMITATIONS: Retrospective design, heterogeneous population, variations in radiation protocols. CONCLUSION: ART following clear margin surgery for high T-stage cutaneous squamous cell carcinomas resulted in half the risk of LR and LRR.

Short-term mortality risks among patients with oropharynx cancer by human papillomavirus status.

BACKGROUND: There is substantial variation in head and neck cancer (HNC) mortality and competing mortality among patients with HNC. In this study, the authors characterize the causes and risks of short-term mortality among patients with oropharynx cancer (OPC) and how these risks differ by human papillomavirus (HPV) status. METHODS: A custom Surveillance, Epidemiology, and End Results (SEER) data set with HPV status was used to identify 4930 patients with OPC who were diagnosed with nonmetastatic (M0) disease from 2013 to 2014, including 3560 (72.2%) HPV-positive patients and 1370 HPV-negative patients. Causes of death and cumulative incidence estimates for HNC-specific mortality, competing mortality, second-cancer mortality, and noncancer mortality were analyzed by HPV status. Risk factors for mortality events were determined using multivariable competing risk regression models. RESULTS: Compared with HPV-negative patients, HPV-positive patients had a lower risk of 2-year cumulative incidence of all-cause mortality (10.4% vs 33.3%; P < .0001) and a lower risk of both HNC-specific mortality (4.8% vs 16.2%; P < .0001) and competing-cause mortality (5.6% vs 16.8%; P < .0001). Second-cancer mortality was the most common cause of non-HNC mortality among HPV-negative patients. Both second-cancer mortality and noncancer mortality were significantly higher among patients who had HPV-negative OPC (10.8% and 6.1%, respectively) compared with those who had HPV-positive OPC (2.4% and 3.2%, respectively; both P < .0001). The median follow-up was 11 months (range 1-23 months) in this cohort with known HPV-status. CONCLUSIONS: Patients with HPV-positive and HPV-negative OPC have significantly different rates of both HNC mortality and competing mortality. HPV-negative patients are at substantial risk of competing mortality, even within 2 years of cancer diagnosis. These differences can inform power calculations for clinical trials and patient management in the acute and survivorship settings.

The Benefits of Adjuvant Trastuzumab for HER-2-Positive Salivary Gland Cancers.

BACKGROUND: Although high-grade salivary gland cancers (SGCs) often express androgen receptor (AR) and/or HER-2/neu, therapeutically targeting these receptors in SGC remains investigational. We investigated the prevalence of receptor expression and the benefit of adjuvant HER-2 directed therapy in the high-risk postoperative setting and explored the clinical utility of sequentially targeting these receptors in the setting of advanced disease. MATERIALS AND METHODS: We clinically annotated 95 patients with SGC (excluding adenoid cystic carcinoma) treated at our institution from 2002 to 2019 and recorded AR, HER-2/neu status, and tumor genomic profiling results when available. Clinicopathologic information was then integrated with outcomes. RESULTS: Of 95 patients, most had high-risk histologies, with salivary duct carcinoma (SDC) as the most frequent diagnosis (43, 45%). Thirty-five (37%) experienced recurrence (51% SDC). HER-2/neu was positive (1-3+) by immunostaining in 34 of 52 (65%) evaluable cases. There was no difference in survival based on HER-2/neu or AR expression. Nine of 17 (53%) patients with HER-2+ SDC received adjuvant chemoradiation with trastuzumab. Median disease-free survival (DFS) and overall survival (OS) were longer among patients with HER-2/neu 3+ staining tumors who received adjuvant trastuzumab versus those who did not (DFS, 117 vs. 9 months; p = .02; OS, 74 vs. 43 months; p = .02), with no difference among other HER-2/neu subgroups (0-2+). Two of nine (22%) patients treated with adjuvant trastuzumab demonstrated recurrence, both with low HER-2/neu staining intensity (1+). Longer time to recurrence (hazard ratio, 0.94; p = .01) predicted improved outcomes. Both androgen deprivation and HER-2-directed therapies had clinical benefit beyond the first-line metastatic setting, with partial response observed beyond second-line use. CONCLUSION: Although prospective data are lacking, the use of adjuvant trastuzumab in high-risk patients with SGC appears beneficial, particularly among patients with tumors exhibiting HER-2/neu 3+ immunostaining. IMPLICATIONS FOR PRACTICE: Results of this study showed an improved disease-free and overall survival in patients treated with adjuvant trastuzumab for high-risk salivary gland cancers with strong HER-2/neu staining intensity. Following recurrence or metastatic spread, sequential HER-2, and androgen-directed therapies may benefit certain patients with salivary gland cancer.

Evaluation of a community-based dental screening program prior to radiotherapy for head and neck cancer: a single-center experience.

PURPOSE: Oral toxicities following radiation therapy (RT) for head and neck (HN) cancer can be profound and are associated with poor health outcomes. The Division of Oral Medicine and Dentistry at Brigham and Women's Hospital and Dana-Farber Cancer Institute therefore implemented a dental evaluation program designed for community-based (CB) dentists to evaluate and treat patients scheduled for HN RT. The aim of this retrospective single-center cohort study was to assess the compliance of CB dentists with this pre-RT dental evaluation program. METHODS: A retrospective analysis of dental evaluations completed by CB dentists from December 2013 to December 2015 was performed. Descriptive statistics were used to determine compliance. RESULTS: A total of 186 dental evaluations were received. Compliance with completion of dental treatment was as follows: scaling and prophylaxis: 94.5% (172/182); dental restorations: 78.7% (48/61); endodontic therapy: 76.9% (10/13); and dental extractions: 76.9% (30/39). Compliance of CB dentists with all requested components of the pre-RT evaluation and treatment was 77.4% (144/186). The median distance traveled by patients to the CB dentist and to the hospital was 5.2 miles (range 0.03-66.0) and 46.5 miles (range 0.8-1457; p < 0.01), respectively. CONCLUSION: In this study, the majority of patients completed their necessary dental treatment in a timely manner by their CB dentist in collaboration with an oral medicine specialist. Given the high compliance of CB dentists, this program could serve as a model for other cancer centers to optimize oral and dental health prior to RT.

Radiation dose enhancement associated with contemporary dental materials.

STATEMENT OF PROBLEM: Electron backscatter radiation from dental materials can contribute to soft tissue injury in patients undergoing head and neck radiation therapy. PURPOSE: The dose enhancement from the materials used for prosthodontic restoration of the dentition has not been well quantified. This study reports the magnitude of backscatter dose from the contemporary dental materials lithium disilicate and zirconia as compared with high-noble alloy and investigates the role of a spacer material in mitigating this effect. MATERIAL AND METHODS: Three flat slabs of dental materials high-noble alloy, lithium disilicate, and zirconia with thicknesses of 1.5 and 3 mm were irradiated with 6-MV photons from a clinical linear accelerator. Measurements were made using a thin-window parallel-plate ionization chamber placed at 0, 1, 3, and 5 mm from the material. One millimeter of poly(methyl methacrylate) or thermoplastic material was used to cover the dental material and measure the effect on the adjacent dose enhancement. RESULTS: Dose enhancements between 8% and 50% were recorded adjacent to the dental restoration materials. The largest enhancements occurred for the material of the highest density, the high-noble alloy. Dose enhancement was substantially lower for lithium disilicate (8%) and zirconia (30%). The thickness of the restoration material did not significantly affect dose enhancement. The dose enhancement decreased with distance from the material, dropping to <10% for all materials at 3 mm. CONCLUSIONS: Contemporary dental restorations enhance the backscatter dose. The presence of dental restorations may warrant the use of a stent to create separation from these materials as this can mitigate the effect.

The Use of Hyperbaric Oxygen for the Prevention and Management of Osteoradionecrosis of the Jaw: A Dana-Farber/Brigham and Women's Cancer Center Multidisciplinary Guideline.

BACKGROUND: Osteoradionecrosis of the jaw (ORN) is an infrequent yet potentially devastating complication of radiation therapy to the head and neck region. Treatment options include antimicrobial therapy, local sequestrectomy, resection, and the use of hyperbaric oxygen (HBO). Published data on ORN are difficult to compare because of the lack of a universally accepted classification and staging system, and the literature on the use of HBO to either prevent or successfully manage ORN is controversial and inconclusive. Therefore, we aimed to establish a standard approach for using HBO at our institution. MATERIALS AND METHODS: A literature search was conducted of articles published in the English language between January 1980 and January 2016. Retrieved articles were evaluated by two independent reviewers. Isolated case reports, abstracts, case series, review articles, and cohort studies without a control group were excluded; summary data were extracted from the remaining studies. A panel of experts from Head and Neck Oncology and Oral Medicine from the Dana-Farber Cancer Institute and Brigham and Women's Hospital reviewed the summary data and established multidisciplinary guidelines on the use of HBO for the prevention and management of ORN. RESULTS: Seven studies were evaluated and reviewed by the multidisciplinary panel. There was no consistent evidence in support of HBO for either the prevention or management of ORN. CONCLUSION: Based on the available evidence and expert opinion, routine use of HBO for the prevention or management of ORN is not recommended and is rarely used at our institution. The Oncologist 2017;22:343-350 IMPLICATIONS FOR PRACTICE: The Division of Head and Neck Oncology of Dana-Farber/Brigham and Women's Cancer Center does not recommend the routine use of HBO for the prevention or management of ORN. Adjunctive HBO may be considered for use on a case-by-case basis in patients considered to be at exceptionally high risk who have failed conservative therapy and subsequent surgical resection.

Definitive chemoradiation alters the immunologic landscape and immune checkpoints in head and neck cancer.

BACKGROUND: Preclinical and clinical studies suggest potential synergy between high dose per fraction focal radiation and immunotherapy. However, conventionally fractionated radiation regimens in combination with concurrent chemotherapy are more commonly administered to patients as definitive treatment and may have both immune-stimulating and -suppressive effects. METHODS: We prospectively collected longitudinal samples from head and neck squamous cell carcinoma patients receiving definitive radiation therapy. We quantified changes in populations of circulating immune cells and chemokines CXCL9, 10, and 16. Analyses of humoral and cellular immune responses were conducted in select patients via proteomic analysis and T-cell receptor sequencing. RESULTS: Treatment not only increased circulating CD-8+ T-effector cells, but also myeloid-derived suppressor cells, regulatory T cells, and checkpoint receptor-expressing T cells, particularly PD-1+ T cells. Significant decreases in CXCL10 and increases in CXLC16 were noted. Treatment also increased the percentage of unique and dominant TCR clones, and increased humoral responses as measured by proteomic array. CONCLUSIONS: Our results suggest that fractionated chemoradiation leads to quantifiable effects in circulating immune mediators, including a balance of stimulatory and suppressive mechanisms. These results suggest future combinations with immune checkpoint blockade.

Merkel Cell Carcinoma: A Population Analysis on Survival.

PURPOSE: Merkel cell carcinoma (MCC) is an aggressive cutaneous malignancy. However, factors associated with disease presentation and outcomes remain uncertain, especially in light of recent changes in workup, such as sentinel lymph node biopsy. Therefore, this study used the SEER database to examine factors that could affect stage at presentation and treatment. METHODS: We identified 4,543 patients and evaluated associations between sex, race, age, primary disease site, disease presentation, and treatment. We also used univariate and multivariate analyses to examine the effect of these factors on disease-specific survival (DSS) and overall survival (OS). We specifically conducted subgroup analyses on a more modern cohort of patients with MCC treated between 2006 and 2012. RESULTS: Male sex, older age, larger tumor size, and primary tumors of the scalp, neck, or trunk were associated with a higher burden of nodal disease. Multivariate predictors of worse DSS/OS in both the recent and overall cohort included age older than 75 years, number of lymph nodes involved, tumors greater than 5 cm, metastatic disease, or lack of radiation therapy. The number of involved nodes was the best predictor of DSS/OS. Associations with radiation therapy were most pronounced in patients with nodal disease and those not undergoing surgery. CONCLUSIONS: Sex, age, tumor size, and primary site of disease correlated with burden of nodal disease in MCC. Associations between disease presentation and treatment strategies such as radiation and DSS and OS have remained relatively constant in the modern era from 2006 to 2012 compared with findings from prior studies.

Changing prognostic significance of tumor stage and nodal stage in patients with squamous cell carcinoma of the oropharynx in the human papillomavirus era.

BACKGROUND: Although human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma (OPSCC) tends to present at an advanced nodal stage (N stage), the prognosis is generally better than that for HPV-negative OPSCC. Prior work has demonstrated the increasing incidence of HPV-related OPSCC in the United States. This study was designed to determine whether the changing epidemiology of OPSCC is reflected in changes in the prognostic significance of the tumor stage (T stage) and the N stage in a population-based cohort. METHODS: The Surveillance, Epidemiology, and End Results program was used to identify 13,328 patients who were 18 years old or older and were diagnosed with OPSCC from 1997 to 2008. The Kaplan-Meier method was used to estimate head and neck cancer-specific survival. Cox proportional hazards models were used to evaluate the associations between head and neck cancer-specific mortality (HNCSM) and T and N stages and the interaction of variables with the year of diagnosis. RESULTS: With a median follow-up of 67 months, there were 4099 head and neck cancer deaths. There was a significant interaction between the T stage and time (P for interaction = .01), with the effect of the T stage on HNCSM increasing from 1997 to 2008. The T stage retained a linear relationship with HNCSM. The effect of the N stage on HNCSM declined over time (P for interaction = .0004). The current American Joint Committee on Cancer (AJCC) staging system did not subdivide distinct prognostic subgroups for HNCSM by overall stage. CONCLUSIONS: In this population-based study of OPSCC, the effect of the N stage on cancer-specific mortality decreased over time as the impact of the T stage increased. The current AJCC staging system did not distinguish prognostic subgroups. These changes may reflect the increasing prevalence of HPV-related OPSCC. Further study in HPV-defined cohorts is needed to tailor the AJCC staging system to better reflect HNCSM risk. Cancer 2015;121:2594-2602. © 2015 American Cancer Society.

Imaging and Biomarker Surveillance for Head and Neck Squamous Cell Carcinoma: A Systematic Review and American Radium Society Appropriate Use Criteria Statement.

Surveillance for survivors of head and neck cancer (HNC) is focused on early detection of recurrent or second primary malignancies. After initial restaging confirms disease-free status, the use of surveillance imaging for asymptomatic patients with HNC is controversial. Our objective was to comprehensively review literature pertaining to imaging and biomarker surveillance of asymptomatic patients treated for head and neck squamous cell carcinoma and to convene a multidisciplinary expert panel to provide appropriate use criteria for surveillance in representative clinical scenarios. The evidence base for the appropriate use criteria was gathered through a librarian-mediated search of literature published from 1990 to 2022 focused on surveillance imaging and circulating tumor-specific DNA for nonmetastatic head and neck squamous cell carcinoma using MEDLINE (Ovid), Embase, Web of Science Core Collection, and the Cochrane Central Register of Controlled Trials. The systematic review was reported according to PRISMA guidelines. Using the modified Delphi process, the expert panel voted on appropriate use criteria, providing recommendations for appropriate use of surveillance imaging and human papillomavirus (HPV) circulating tumor DNA. Of 5178 studies identified, 80 met inclusion criteria (5 meta-analyses/systematic reviews, 1 randomized control trial, 1 post hoc analysis, 25 prospective, and 48 retrospective cohort studies [with ≥50 patients]), reporting on 27,525 patients. No large, randomized, prospective trials examined whether asymptomatic patients who receive surveillance imaging or HPV circulating tumor DNA monitoring benefit from earlier detection of recurrence or second primary tumors in terms of disease-specific or quality-of-life outcomes. In the absence of prospective data, surveillance imaging for HNC survivors should rely on individualized recurrence-risk assessment accounting for initial disease staging, HPV disease status, and tobacco use history. There is an emerging surveillance role for circulating tumor biomarkers.

Personalized circulating tumor DNA for monitoring disease status in head and neck squamous cell carcinoma.

BACKGROUND: Many patients with locoregionally advanced HPV-negative head and neck squamous cell carcinoma (HNSCC) relapse. Circulating tumor (ct)DNA has the potential to identify minimal residual disease, but its clinical utility for virus-negative HNSCC is not well understood. METHODS: We retrospectively evaluated a personalized, commercial ctDNA assay (Signatera™, Natera) during clinical care of patients treated for predominantly newly diagnosed HPV-negative HNSCC. Signatera™ utilizes 16-plex PCR from matched tumor and blood. Objectives were to understand ctDNA detectability and correlate changes post-treatment with disease outcomes. RESULTS: Testing was successful in 100/116 (86%) patients (median age: 65, 68% male, 65% smokers); testing failed in 16 (14%) due to insufficient tissue. Oral cavity (55, 47%) tumors were most common; most had stage III-IV disease (82, 71%) while 17 (15%) had distant metastases. Pre-treatment, 75/100 patients with successful testing (75%) had detectable ctDNA (range: 0.03-4049.69 MTM/mL). No clinical features predicted ctDNA detectability or levels (multivariate analysis). At median follow-up of 5.1 months (range: 0.2-15.1), 55 (55%) had >1 test result (range: 1-7; 194 samples). Of 55, 17 (31%) remained ctDNA positive after starting treatment. Progression-free survival was significantly worse for patients who were ctDNA positive vs. negative post-treatment (HR 7.33, 95%CI 3.12-17.2, p<0.001); 1-year overall survival was 89.1% vs. 100%, respectively (HR 7.46, 95%CI 0.46-119.5; p=0.155). CONCLUSIONS: Tumor-informed ctDNA testing is feasible in non-viral HNSCC. ctDNA positivity is an indicator of disease progression and associated with inferior survival. Further research is warranted to understand whether ctDNA may be leveraged to guide therapy in HNSCC.

Microinvasive breast cancer: ER, PR, and HER-2/neu status and clinical outcomes after breast-conserving therapy or mastectomy.

BACKGROUND: Contemporary clinical outcomes of microinvasive breast cancer (MIBC), defined as no focus >1 mm, are not well characterized. We document the immunophenotype, incidence of axillary metastases, and rate of recurrence in a well-defined case series. METHODS: We reviewed 83 consecutive patients with MIBC from 1997 to 2005. Estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER-2/neu) receptor status were assessed. The cumulative incidence of local recurrence (LR) and nodal/distant recurrence was calculated. Predictors of recurrence were identified and effect estimates determined. RESULTS: Fifty-two patients (63%) underwent breast-conserving therapy (BCT) and 31 (37%) underwent mastectomy. Sixty-one percent had ER-positive disease and 49% had HER-2/neu-positive disease. Three (4%) of 68 patients with sentinel node mapping or axillary dissection had single node micrometastases, and none had macrometastases or multiple nodes involved. Median follow-up was 6.4 years, with 6 LRs, 2 regional nodal recurrences, and 2 concurrent local/distant recurrences. The 5-year cumulative incidence of recurrence (local, nodal, or distant) was 5.3% (95% confidence interval [CI] 2.0-13.4) for all patients, and among BCT patients, the 5-year cumulative incidence of LR was 4.2% (95% CI 0.7-12.7). HER-2/neu overexpression was not associated with recurrence (P = 0.46). Close/positive margins (≤2 mm) were significantly associated with an increased risk of LR after BCT or mastectomy (hazard ratio 8.8; 95% CI 1.6-48.8; P = 0.003). CONCLUSIONS: MIBC has a favorable prognosis, and HER-2/neu overexpression, although highly prevalent, is not significantly associated with recurrence. Axillary metastases at diagnosis are small and infrequent. The cumulative incidence of LR after BCT is acceptable; however, our data confirm that negative margins (>2 mm) are required for optimal BCT outcomes.

Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer.

Importance: Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical skeletal muscle segmentation and cross-sectional area. However, manual muscle segmentation is labor intensive, prone to interobserver variability, and impractical for large-scale clinical use. Objective: To develop and externally validate a fully automated image-based deep learning platform for cervical vertebral muscle segmentation and SMI calculation and evaluate associations with survival and treatment toxicity outcomes. Design, Setting, and Participants: For this prognostic study, a model development data set was curated from publicly available and deidentified data from patients with HNSCC treated at MD Anderson Cancer Center between January 1, 2003, and December 31, 2013. A total of 899 patients undergoing primary radiation for HNSCC with abdominal computed tomography scans and complete clinical information were selected. An external validation data set was retrospectively collected from patients undergoing primary radiation therapy between January 1, 1996, and December 31, 2013, at Brigham and Women's Hospital. The data analysis was performed between May 1, 2022, and March 31, 2023. Exposure: C3 vertebral skeletal muscle segmentation during radiation therapy for HNSCC. Main Outcomes and Measures: Overall survival and treatment toxicity outcomes of HNSCC. Results: The total patient cohort comprised 899 patients with HNSCC (median [range] age, 58 [24-90] years; 140 female [15.6%] and 755 male [84.0%]). Dice similarity coefficients for the validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI, 0.90-0.91) and 0.90 (95% CI, 0.89-0.91), respectively, with a mean 96.2% acceptable rate between 2 reviewers on external clinical testing (n = 377). Estimated cross-sectional area and SMI values were associated with manually annotated values (Pearson r = 0.99; P < .001) across data sets. On multivariable Cox proportional hazards regression, SMI-derived sarcopenia was associated with worse overall survival (hazard ratio, 2.05; 95% CI, 1.04-4.04; P = .04) and longer feeding tube duration (median [range], 162 [6-1477] vs 134 [15-1255] days; hazard ratio, 0.66; 95% CI, 0.48-0.89; P = .006) than no sarcopenia. Conclusions and Relevance: This prognostic study's findings show external validation of a fully automated deep learning pipeline to accurately measure sarcopenia in HNSCC and an association with important disease outcomes. The pipeline could enable the integration of sarcopenia assessment into clinical decision making for individuals with HNSCC.

Fully-automated sarcopenia assessment in head and neck cancer: development and external validation of a deep learning pipeline.

Purpose: Sarcopenia is an established prognostic factor in patients diagnosed with head and neck squamous cell carcinoma (HNSCC). The quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical neck skeletal muscle (SM) segmentation and cross-sectional area. However, manual SM segmentation is labor-intensive, prone to inter-observer variability, and impractical for large-scale clinical use. To overcome this challenge, we have developed and externally validated a fully-automated image-based deep learning (DL) platform for cervical vertebral SM segmentation and SMI calculation, and evaluated the relevance of this with survival and toxicity outcomes. Materials and Methods: 899 patients diagnosed as having HNSCC with CT scans from multiple institutes were included, with 335 cases utilized for training, 96 for validation, 48 for internal testing and 393 for external testing. Ground truth single-slice segmentations of SM at the C3 vertebra level were manually generated by experienced radiation oncologists. To develop an efficient method of segmenting the SM, a multi-stage DL pipeline was implemented, consisting of a 2D convolutional neural network (CNN) to select the middle slice of C3 section and a 2D U-Net to segment SM areas. The model performance was evaluated using the Dice Similarity Coefficient (DSC) as the primary metric for the internal test set, and for the external test set the quality of automated segmentation was assessed manually by two experienced radiation oncologists. The L3 skeletal muscle area (SMA) and SMI were then calculated from the C3 cross sectional area (CSA) of the auto-segmented SM. Finally, established SMI cut-offs were used to perform further analyses to assess the correlation with survival and toxicity endpoints in the external institution with univariable and multivariable Cox regression. Results: DSCs for validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI: 0.90 - 0.91) and 0.90 (95% CI: 0.89 - 0.91), respectively. The predicted CSA is highly correlated with the ground-truth CSA in both validation (r = 0.99, p < 0.0001) and test sets (r = 0.96, p < 0.0001). In the external test set (n = 377), 96.2% of the SM segmentations were deemed acceptable by consensus expert review. Predicted SMA and SMI values were highly correlated with the ground-truth values, with Pearson r ß 0.99 (p < 0.0001) for both the female and male patients in all datasets. Sarcopenia was associated with worse OS (HR 2.05 [95% CI 1.04 - 4.04], p = 0.04) and longer PEG tube duration (median 162 days vs. 134 days, HR 1.51 [95% CI 1.12 - 2.08], p = 0.006 in multivariate analysis. Conclusion: We developed and externally validated a fully-automated platform that strongly correlates with imaging-assessed sarcopenia in patients with H&N cancer that correlates with survival and toxicity outcomes. This study constitutes a significant stride towards the integration of sarcopenia assessment into decision-making for individuals diagnosed with HNSCC. SUMMARY STATEMENT: In this study, we developed and externally validated a deep learning model to investigate the impact of sarcopenia, defined as the loss of skeletal muscle mass, on patients with head and neck squamous cell carcinoma (HNSCC) undergoing radiotherapy. We demonstrated an efficient, fullyautomated deep learning pipeline that can accurately segment C3 skeletal muscle area, calculate cross-sectional area, and derive a skeletal muscle index to diagnose sarcopenia from a standard of care CT scan. In multi-institutional data, we found that pre-treatment sarcopenia was associated with significantly reduced overall survival and an increased risk of adverse events. Given the increased vulnerability of patients with HNSCC, the assessment of sarcopenia prior to radiotherapy may aid in informed treatment decision-making and serve as a predictive marker for the necessity of early supportive measures.

Screening for extranodal extension in HPV-associated oropharyngeal carcinoma: evaluation of a CT-based deep learning algorithm in patient data from a multicentre, randomised de-escalation trial.

BACKGROUND: Pretreatment identification of pathological extranodal extension (ENE) would guide therapy de-escalation strategies for in human papillomavirus (HPV)-associated oropharyngeal carcinoma but is diagnostically challenging. ECOG-ACRIN Cancer Research Group E3311 was a multicentre trial wherein patients with HPV-associated oropharyngeal carcinoma were treated surgically and assigned to a pathological risk-based adjuvant strategy of observation, radiation, or concurrent chemoradiation. Despite protocol exclusion of patients with overt radiographic ENE, more than 30% had pathological ENE and required postoperative chemoradiation. We aimed to evaluate a CT-based deep learning algorithm for prediction of ENE in E3311, a diagnostically challenging cohort wherein algorithm use would be impactful in guiding decision-making. METHODS: For this retrospective evaluation of deep learning algorithm performance, we obtained pretreatment CTs and corresponding surgical pathology reports from the multicentre, randomised de-escalation trial E3311. All enrolled patients on E3311 required pretreatment and diagnostic head and neck imaging; patients with radiographically overt ENE were excluded per study protocol. The lymph node with largest short-axis diameter and up to two additional nodes were segmented on each scan and annotated for ENE per pathology reports. Deep learning algorithm performance for ENE prediction was compared with four board-certified head and neck radiologists. The primary endpoint was the area under the curve (AUC) of the receiver operating characteristic. FINDINGS: From 178 collected scans, 313 nodes were annotated: 71 (23%) with ENE in general, 39 (13%) with ENE larger than 1 mm ENE. The deep learning algorithm AUC for ENE classification was 0·86 (95% CI 0·82-0·90), outperforming all readers (p<0·0001 for each). Among radiologists, there was high variability in specificity (43-86%) and sensitivity (45-96%) with poor inter-reader agreement (κ 0·32). Matching the algorithm specificity to that of the reader with highest AUC (R2, false positive rate 22%) yielded improved sensitivity to 75% (+ 13%). Setting the algorithm false positive rate to 30% yielded 90% sensitivity. The algorithm showed improved performance compared with radiologists for ENE larger than 1 mm (p<0·0001) and in nodes with short-axis diameter 1 cm or larger. INTERPRETATION: The deep learning algorithm outperformed experts in predicting pathological ENE on a challenging cohort of patients with HPV-associated oropharyngeal carcinoma from a randomised clinical trial. Deep learning algorithms should be evaluated prospectively as a treatment selection tool. FUNDING: ECOG-ACRIN Cancer Research Group and the National Cancer Institute of the US National Institutes of Health.

Interventions for head and neck cancer survivors: Systematic review.

BACKGROUND: Interventions for head/neck cancer (HNC) survivors may not address their cancer-related and general health needs. METHODS: Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guided this systematic review of studies from 2000 to 2021 of interventions targeting cancer survivors treated with curative-intent, using MEDLINE, Embase, Emcare, and PsycINFO. Interventions were categorized into domains of the Quality of Cancer Survivorship Care Framework to characterize the scope and quality of interventions. RESULTS: We identified 28 studies for inclusion: 13 randomized and 15 non-randomized. Most targeted surveillance/management of physical effects (n = 24) including 13 that also targeted psychosocial effects. Four studies addressed prevention/surveillance for recurrence/new cancers, one addressed health promotion/disease prevention, and one addressed chronic medical conditions. Most studies (n = 27) had medium-high risk of bias. CONCLUSIONS: There are few high-quality studies addressing HNC survivorship. Future rigorously designed studies should address broader areas of care, including chronic disease management and health promotion/disease prevention.