Abstract PO-039: Artificial intelligence-based extracapsular extension prediction in head and neck cancer analysis

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.