Luca Giovanella, Lisa Milan, Arnoldo Piccardo, Gianluca Bottoni, Marco Cuzzocrea, Gaetano Paone, Luca Ceriani
Author Information
Luca Giovanella: Clinic for Nuclear Medicine and Molecular Imaging, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, 6500, Bellinzona, Switzerland. luca.giovanella@eoc.ch. ORCID
Lisa Milan: Clinic for Nuclear Medicine and Molecular Imaging, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, 6500, Bellinzona, Switzerland.
Arnoldo Piccardo: Department of Nuclear Medicine, E.O. "Ospedali Galliera", Genoa, Italy.
Gianluca Bottoni: Department of Nuclear Medicine, E.O. "Ospedali Galliera", Genoa, Italy.
Marco Cuzzocrea: Clinic for Nuclear Medicine and Molecular Imaging, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, 6500, Bellinzona, Switzerland.
Gaetano Paone: Clinic for Nuclear Medicine and Molecular Imaging, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, 6500, Bellinzona, Switzerland.
Luca Ceriani: Clinic for Nuclear Medicine and Molecular Imaging, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, 6500, Bellinzona, Switzerland.
PURPOSE: As ~25% of cytologically indeterminate thyroid nodules harbour malignancy, diagnostic lobectomy is still performed in many cases. FDG PET/CT rules out malignancy in visually negative nodules; however, none of the currently available interpretation criteria differentiates malignant from benign FDG-avid nodules. We evaluated the ability of PET metrics and radiomics features (RFs) to predict final diagnosis of FDG-avid cytologically indeterminate thyroid nodules. METHODS: Seventy-eight patients were retrospectively included. After volumetric segmentation of each thyroid lesion, 4 PET metrics and 107 RFs were extracted. A logistic regression was performed including thyroid stimulating hormone, PET metrics, and RFs to assess their predictive performance. A linear combination of the resulting parameters generated a radiomics score (RS) that was matched with cytology classes (Bethesda III and IV) and compared with final diagnosis. RESULTS: Two RFs (shape_Sphericity and glcm_Autocorrelation) differentiated malignant from benign lesions. A predictive model integrating RS and cytology classes effectively stratified the risk of malignancy. The prevalence of thyroid cancer increased from 5 to 37% and 79% in accordance with the number (score 0, 1 or 2, respectively) of positive biomarkers. CONCLUSIONS: Our multiparametric model may be useful for reducing the number of diagnostic lobectomies with advantages in terms of costs and quality of life for patients.
