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

## TL;DR

This paper introduces a new interactive deep learning method to accurately segment tumors in oropharyngeal cancer radiotherapy planning.

## Contribution

A novel two-stage Interactive Click Refinement framework for improved tumor segmentation in oropharyngeal cancer.

## Key findings

- The 2S-ICR framework achieved a Dice similarity coefficient of 0.722 without user interaction.
- After ten user interactions, the framework improved to a Dice similarity coefficient of 0.858.
- The method outperformed existing approaches in both automatic and interactive settings.

## 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.