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

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 18; p. 7952
• Main Authors: Bianconi, Francesco, Salis, Roberto, Fravolini, Mario Luca, Khan, Muhammad Usama, Minestrini, Matteo, Filippi, Luca, Marongiu, Andrea, Nuvoli, Susanna, Spanu, Angela, Palumbo, Barbara
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2023; MDPI
• Subjects: Automation; Cancer therapies; Clinical decision making; Datasets; Deep learning; Head & neck cancer; head and neck cancer; Medical imaging; Medical prognosis; Metastasis; Nuclear medicine; Patients; positron emission tomography; Radiation therapy; Radiomics; region of interest; segmentation; Tomography
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23187952

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.