Interactive 3D segmentation for primary gross tumor volume in oropharyngeal cancer

Abstract

Abstract Radiotherapy is the main treatment modality of oropharyngeal cancer (OPC), in which an accurate segmentation of primary gross tumor volume (GTVt) is essential but also challenging due to significant interobserver variability and the time consumed in manual tumor delineation. For such a challenge an interactive deep learning (DL) based approach offers the advantage of automatic high-performance segmentation with the flexibility for user correction when necessary. In this study, we investigate an interactive DL for GTVt segmentation in OPC by introducing a novel two-stage Interactive Click Refinement (2S-ICR) framework and implementing state-of-the-art algorithms. Using the 2021 HEad and neCK TumOR dataset for development and an external dataset from The University of Texas MD Anderson Cancer Center for evaluation, the 2S-ICR framework achieves a Dice similarity coefficient of 0.722 ± 0.142 without user interaction and 0.858 ± 0.050 after ten interactions, thus outperforming existing methods in both cases.