Performance Analysis of Six Semi-Automated Tumour Delineation Methods on [18F] Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG PET/CT) in Patients with Head and Neck Cancer

Author:

Bianconi Francesco1ORCID,Salis Roberto2,Fravolini Mario Luca1ORCID,Khan Muhammad Usama1,Minestrini Matteo3,Filippi Luca4ORCID,Marongiu Andrea2ORCID,Nuvoli Susanna2ORCID,Spanu Angela2ORCID,Palumbo Barbara3ORCID

Affiliation:

1. Department of Engineering, Università degli Studi di Perugia, Via Goffredo Duranti 93, 06125 Perugia, Italy

2. Unit of Nuclear Medicine, Department of Medicine, Surgery and Pharmacy, University of Sassari, 07100 Sassari, Italy

3. Section of Nuclear Medicine and Health Physics, Department of Medicine and Surgery, Università degli Studi di Perugia, Piazza Lucio Severi 1, 06132 Perugia, Italy

4. Policlinico Tor Vergata Hospital, Viale Oxford 81, 00133 Rome, Italy

Abstract

Background. Head and neck cancer (HNC) is the seventh most common neoplastic disorder at the global level. Contouring HNC lesions on [18F] Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) scans plays a fundamental role for diagnosis, risk assessment, radiotherapy planning and post-treatment evaluation. However, manual contouring is a lengthy and tedious procedure which requires significant effort from the clinician. Methods. We evaluated the performance of six hand-crafted, training-free methods (four threshold-based, two algorithm-based) for the semi-automated delineation of HNC lesions on FDG PET/CT. This study was carried out on a single-centre population of n=103 subjects, and the standard of reference was manual segmentation generated by nuclear medicine specialists. Figures of merit were the Sørensen–Dice coefficient (DSC) and relative volume difference (RVD). Results. Median DSC ranged between 0.595 and 0.792, median RVD between −22.0% and 87.4%. Click and draw and Nestle’s methods achieved the best segmentation accuracy (median DSC, respectively, 0.792 ± 0.178 and 0.762 ± 0.107; median RVD, respectively, −21.6% ± 1270.8% and −32.7% ± 40.0%) and outperformed the other methods by a significant margin. Nestle’s method also resulted in a lower dispersion of the data, hence showing stronger inter-patient stability. The accuracy of the two best methods was in agreement with the most recent state-of-the art results. Conclusions. Semi-automated PET delineation methods show potential to assist clinicians in the segmentation of HNC lesions on FDG PET/CT images, although manual refinement may sometimes be needed to obtain clinically acceptable ROIs.

Funder

Department of Engineering, Università degli Studi di Perugia

Italian Ministry of University and Research

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry

Reference47 articles.

1. Reviewing the epidemiology of head and neck cancer: Definitions, trends and risk factors;Gormley;Br. Dent. J.,2022

2. Merlano, M.C., and Garrone, O. (2022). I Numeri del Cancro in Italia, Intermedia Editore. Chapter 3.1.

3. Head and neck cancer prevention: From primary prevention to impact of clinicians on reducing burden;Hashim;Ann. Oncol.,2019

4. Role of Epstein–Barr virus and human papilloma virus in the development of oropharyngeal cancer: A literature review;Migliaro;Int. J. Dent.,2022

5. Eyassu, E., and Young, M. (2022). Chapter Nuclear Medicine PET/CT Head and Neck Cancer Assessment, Protocols, and Interpretation, StatPearls Publishing.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3