Multi-Scale Fusion Methodologies for Head and Neck Tumor Segmentation

TL;DR

This paper investigates multi-scale fusion deep learning architectures to improve the accuracy of head and neck tumor segmentation, aiming to enhance radiation therapy planning and reduce normal tissue irradiation.

Contribution

It introduces novel multi-scale fusion methodologies specifically designed for head and neck tumor segmentation in medical imaging.

Findings

Improved segmentation accuracy over existing methods

Enhanced delineation of complex tumor structures

Potential to automate and improve radiation therapy planning

Abstract

Head and Neck (H\&N) organ-at-risk (OAR) and tumor segmentations are essential components of radiation therapy planning. The varying anatomic locations and dimensions of H\&N nodal Gross Tumor Volumes (GTVn) and H\&N primary gross tumor volume (GTVp) are difficult to obtain due to lack of accurate and reliable delineation methods. The downstream effect of incorrect segmentation can result in unnecessary irradiation of normal organs. Towards a fully automated radiation therapy planning algorithm, we explore the efficacy of multi-scale fusion based deep learning architectures for accurately segmenting H\&N tumors from medical scans.