Radiomics Features from Positron Emission Tomography with [18F] Fluorodeoxyglucose Can Help Predict Cervical Nodal Status in Patients with Head and Neck Cancer
Open Access
Abstract
Background: Detecting pathological lymph nodes (LNs) is crucial for establishing the proper clinical approach in patients with head and neck cancer (HNC). Positron emission tomography with [18F] fluorodeoxyglucose (FDG PET) has high diagnostic value, although it can yield false positives since FDG-avid LNs can also occur from non-cancerous diseases. Objectives: To explore if radiomics features from FDG PET can enhance the identification of pathological lymph nodes in head and neck cancer. Materials and methods: This study was carried out on cervical lymph nodes (26 negative, 25 positive) from a cohort of subjects, and the standard of reference was fine needle aspiration cytology or excisional biopsy. An initial set of 54 IBSI-compliant radiomics features, which was subsequently reduced to 31 after redundancy elimination, was considered for the analysis. Mann–Whitney U tests were performed to compare each feature between positive and negative LNs. Classification models based on two sets of features, PETBase (SUVmax, MTV and TLG) and PETRad (radiomics features), respectively, were trained using logistic regression, support vector machines and Gaussian naïve Bayes, and their performance was compared. Accuracy was estimated via leave-one-out cross-validation. Results: We identified via univariate analysis 21 features that were statistically different between positive and negative LNs. In particular, dispersion features indicated that positive LNs had higher uptake non-uniformity than the negative ones. AUC, sensitivity, specificity and accuracy obtained with logistic regression were, respectively, 0.840, 68.0%, 89.5% and 80.4% for PETBase and 0.880, 72.0%, 90.0% and 82.4% for PETRad. The other classification models showed the same trend. Conclusions: Radiomics features from FDG PET can improve the diagnostic accuracy of LN status in HNC.
Keywords
Funding Information
- Department of Engineering, Università degli Studi di Perugia, Italy (D.D. 132/2022, D.M. 351/2022)
- Italian Ministry of University and Research (MUR) (D.D. 132/2022, D.M. 351/2022)
This publication has 33 references indexed in Scilit:
- Reviewing the epidemiology of head and neck cancer: definitions, trends and risk factorsBritish Dental Journal, 2022
- Radiomics‐based machine learning for the diagnosis of lymph node metastases in patients with head and neck cancer: Systematic reviewHead & Neck, 2022
- Joint EANM/SNMMI guideline on radiomics in nuclear medicineEuropean Journal of Nuclear Medicine and Molecular Imaging, 2022
- Radiomics in PET ImagingPET Clinics, 2021
- Reprint of “Squamous cell carcinoma of the oral cavity, larynx, oropharynx and hypopharynx: EHNS-ESMO-ESTRO Clinical Practice Guidelines for diagnosis, treatment and follow-up”Oral Oncology, 2021
- Predicting lymph node metastasis in patients with oropharyngeal cancer by using a convolutional neural network with associated epistemic and aleatoric uncertaintyPhysics in Medicine & Biology, 2020
- Distinguishing Lymphomatous and Cancerous Lymph Nodes in 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography by Radiomics AnalysisContrast Media & Molecular Imaging, 2020
- Regional thickness of facial skin and superficial fat: Application to the minimally invasive proceduresClinical Anatomy, 2019
- Youden Index and the optimal threshold for markers with mass at zeroStatistics in Medicine, 2007
- Impact of FDG-PET/CT Imaging on Nodal Staging for Head-And-Neck Squamous Cell CarcinomaInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2007