Utility and limitations of metabolic parameters in head and neck cancer: finding a practical segmentation method

Rijo-Cedeño, Jefferson; Mucientes, Jorge; Villarreal, Ithzel María; Royuela, Ana; Vicente, Patricia García; García-Berrocal, José Ramón

doi:10.1007/s00405-022-07401-y

Cited by 1 publication

(1 citation statement)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison with the recent literature therefore indicates that the accuracy attained by our two best methods was in agreement with state-of-the art approaches. We conclude observing that a fixed SUV 2.5 threshold, a commonly used approach [ 34 , 35 ], should be considered with care in HNC as it consistently overestimated the tumour volume by a large margin. This is likely the consequence of the ‘spillover’ effect as already discussed in [ 34 ].…”

Section: Discussionmentioning

confidence: 95%

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

Bianconi,

Salis,

Fravolini

et al. 2023

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 95%