Search

Extracapsular extension (ECE) is a decisive indication for treatment planning of patients with head and neck squamous cell carcinoma (HNSCC). ECE occurs when metastatic tumor cells within the lymph node break through the nodal capsule into surrounding tissues. It is crucial to identify whether ECE occurs in HNSCC patient treatment. Current ECE detection practice mainly relies on the visual identification of doctors and professionals, which can be extremely labor intensive and time-consuming. Therefore, we aim to automatically perform ECE detection using a machine learning technique to classify whether ECE appears or not. In this research, we propose a systematic machine learning approach to detect ECE from 3D computed tomography (CT) scans. The process includes four steps: 1) apply sliding-cube to extract small 3D samples from patient data; 2) various 3D features are extracted for each sample; and 3) three machine learning models, gradient boosting (GB), random forest (RF), and support vector machine (SVM), with feature extraction and selection approaches, are employed for sample classification task; 4) classify the patient based on sample classification result. Different training scenarios are designed for the experimental test. Based on five-fold cross-validation, the experimental results have demonstrated that our model is able to classify ECE and non-ECE patients. To check the explainability of the models, feature analysis is also conducted. The outcome of this research is expected to promote the implementation of artificial intelligence for ECE classification and detection as well as head and neck cancer diagnosis in the radiology computer vision field. Citation Format: Yibin Wang, William N. Duggar, Toms V. Thomas, Paul Roberts, Linkan Bian, Haifeng Wang. Artificial intelligence-based extracapsular extension prediction in head and neck cancer analysis [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-039.

Objective: To evaluate patterns of patient management in an academic Radiation Oncology department between 3/17/20 and 5/8/20 during the COVID-19 pandemic. Background: As a response to the worldwide COVID-19 pandemic, our Radiation Oncology department instituted a number of measures to limit spread of the disease to our patients and staff. This included prospectively evaluating all new referrals for radiation treatment and determining an appropriate course of action, which if appropriate included delaying the start of radiation, hypofractionation, or using other modalities of treatment prior to start of radiation. Methods: We analyzed data for 82 patients between 3/17/20-5/8/20 to evaluate patterns of management. The chi-squared test was used to evaluate the descriptive characteristics of the study population, with P values ≤ 0.05 considered statistically significant. One sample t-test was used to compare the statistical mean difference between sample variables. Data were analyzed using SPSS 24.0 software (IBM, Armonk, NY, USA). Results: The data set comprised 38% Caucasians and 59% African Americans. An age breakdown revealed 12.3% below age 30, 42% between ages 30-60, and 45.7% over age of 60. When the data were analyzed by gender, we noted a significant difference by site of treatment (p=0.005) and whether immediate treatment was required or not (p=0.029). This likely reflects gender-driven differences in cancer site with patients diagnosed with prostate cancer getting LHRH agonist therapy prior to start of radiation. Hypofractionated radiation schedules were used in 2 patients with cord compression early during the study period compared to 3 patients who received standard fractionation later, and one person elected to go straight to hospice care (p=0.002). Of patients for heterotopic ossification prophylaxis, 3/14 declined radiation and one was over the weight limit of the radiation table (p=0.000). 41% of patients were inpatients. No patients developed COVID-19 during our study period. Conclusion: A prospective evaluation of new patient referrals may have helped mitigate the spread of COVID-19 at our Radiation Oncology facility. This is one of several prospective measures that our department took to protect patients and staff. Citation Format: Sanjay Joseph, Mary Nittala, Paul Roberts, Maurice King, Hiba Ahmed, Ashley Albert, Toms Thomas, Robert Allbright, Satyaseelan Packianathan, Eswarkumar Mundra, Srinivasan Vijayakumar. Prospective planning of radiation treatment at new patient conference during the COVID-19 Pandemic: The University of Mississippi Medical Center experience [abstract]. In: Proceedings of the AACR Virtual Meeting: COVID-19 and Cancer; 2020 Jul 20-22. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(18_Suppl):Abstract nr PO-034.

Introduction: The purpose of this study is to evaluate the incidence, management, and prognosis of hypopharyngeal carcinoma in a tertiary care institution over the past 25 years. Methods: We retrospectively analyzed patients from 1995 to 2019 from the head and neck cancer data base of our institution. The data regarding the demographics, stage, treatment, and follow-up were collected. Outcomes including median survival and overall survival were evaluated using the Kaplan Meier method. All analyses were performed using SPSS version 24. Results: We identified 144 hypopharyngeal carcinoma patients, and the incidence was almost 4% of all head and neck cancers. All patients had squamous cell carcinoma. Sixty-one percent of patients were African Americans and 36% were Caucasians. Ninety percent of the patients were males, and 10% were females. Pyriform sinus was the subsite most commonly affected (67%), followed by posterior pharyngeal wall (10%) and postcricoid area (5%). Ninety-six percent of patients presented with advanced-stage disease (stages III and IV), with only 4% of patients presenting with early-stage disease (Stages I and II). Fifty-one percent of patients underwent definitive chemoradiotherapy with or without induction chemotherapy and 23% of patients underwent surgical management, followed by adjuvant radiation or chemoradiation, depending on risk factors. Ten percent of patients received only palliative chemotherapy and 15% did not receive any treatments. Induction chemotherapy was used in 31% of patients prior to initiation of definitive chemoradiation treatment. The median overall survival of early-stage patients and of advanced-stage patients was 56 months and 15 months, respectively. The median survival of the patients with advanced-stage patients who received definitive treatment was 26 months. The patients who underwent definitive operative management followed by adjuvant treatments had an improved median survival as compared to those undergoing definitive chemoradiation treatment (38 months vs. 16 months, p=0.05). Similarly, the overall survival at 3 years (30% vs. 54%, p=0.05) and 5 years (13% vs. 34%, p=0.05) was also better for surgery patients. The patients who received induction chemotherapy had clinically worse median survival as compared to those who did not, but this was not statistically significant (14 months vs. 21 months, p=0.2). Conclusions: Our results agree with the published literature regarding the low incidence of hypopharyngeal cancer, presentation in advanced stages, and poor long-term outcomes. Selection of patients for laryngeal preservation should be done very carefully. Our results suggest that trimodality treatment may be more efficacious than definitive chemoradiotherapy for locally advanced disease. Future studies are warranted to evaluate if neoadjuvant chemoradiotherapy followed by surgery might be able to improve the current poor outcomes for advanced hypopharyngeal cancer patients who are not eligible for laryngeal preservation. Citation Format: Toms Vengaloor Thomas, Mary R. Nittala, Divyang Mehta, Madhava Rao Kanakamedala, Anu Abraham, Lacey Weatherall, Eldrin Bhanat, Ashley A. Albert, Srinivasan Vijayakumar. Hypopharyngeal carcinoma management: 25-year experience from a tertiary care medical center in United States [abstract]. In: Proceedings of the AACR-AHNS Head and Neck Cancer Conference: Optimizing Survival and Quality of Life through Basic, Clinical, and Translational Research; 2019 Apr 29-30; Austin, TX. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(12_Suppl_2):Abstract nr B20.