Home > Journals > The Quarterly Journal of Nuclear Medicine and Molecular Imaging > Past Issues > The Quarterly Journal of Nuclear Medicine and Molecular Imaging 2022 December;66(4) > The Quarterly Journal of Nuclear Medicine and Molecular Imaging 2022 December;66(4):352-60

CURRENT ISSUE
 

JOURNAL TOOLS

Publishing options
eTOC
To subscribe
Submit an article
Recommend to your librarian
 

ARTICLE TOOLS

Publication history
Reprints
Permissions
Cite this article as
Share

 

ORIGINAL ARTICLE   

The Quarterly Journal of Nuclear Medicine and Molecular Imaging 2022 December;66(4):352-60

DOI: 10.23736/S1824-4785.20.03227-6

Copyright © 2020 EDIZIONI MINERVA MEDICA

language: English

Choline PET/CT features to predict survival outcome in high-risk prostate cancer restaging: a preliminary machine-learning radiomics study

Pierpaolo ALONGI 1 , Riccardo LAUDICELLA 1, 2, Alessandro STEFANO 3, Federico CAOBELLI 4, Albert COMELLI 5, 6, 7, 8, Antonio VENTO 2, Davide SARDINA 9, Gloria GANDUSCIO 9, Patrizia TOIA 10, Francesco CECI 11, Paola MAPELLI 12, 13, Maria PICCHIO 12, 13, Massimo MIDIRI 10, Sergio BALDARI 2, Roberto LAGALLA 10, Giorgio RUSSO 3

1 Unit of Nuclear Medicine, Fondazione Istituto G. Giglio, Cefalù, Palermo, Italy; 2 Unit of Nuclear Medicine, Department of Biomedical and Dental Sciences and of Morpho-functional Imaging, University of Messina, Messina, Italy; 3 Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Cefalù, Palermo, Italy; 4 Clinic of Radiology and Nuclear Medicine, Basel University Hospital, University of Basel, Basel, Switzerland; 5 Ri.MED Foundation, Palermo, Italy; 6 Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA; 7 Institute of Molecular Bioimaging and Physiology, National Research Council (IBFM-CNR), Cefalù, Palermo, Italy; 8 Department of Industrial and Digital Innovation (DIID), University of Palermo, Palermo, Italy; 9 Laboratory of Cellular and Molecular Pathophysiology, Department of Surgical, Oncological and Stomatological Sciences, University of Palermo, Palermo, Italy; 10 Section of Radiology, Department of Biopathology and Medical Biotechnologies (DIBIMED), University of Palermo, Palermo, Italy; 11 Unit of Nuclear Medicine, Department of Medical Sciences, University of Turin, Turin, Italy; 12 Vita-Salute San Raffaele University, Milan, Italy; 13 Department of Nuclear Medicine, IRCCS San Raffaele Scientific Institute, Milan, Italy



BACKGROUND: Radiomic features are increasingly utilized to evaluate tumor heterogeneity in PET imaging but to date its role has not been investigated for Cho-PET in prostate cancer. The potential application of radiomics features analysis using a machine-learning radiomics algorithm was evaluated to select 18F-Cho PET/CT imaging features to predict disease progression in PCa.
METHODS: We retrospectively analyzed high-risk PCa patients who underwent restaging 18F-Cho PET/CT from November 2013 to May 2018. 18F-Cho PET/CT studies and related structures containing volumetric segmentations were imported in the “CGITA” toolbox to extract imaging features from each lesion. A Machine-learning model has been adapted using NCA for feature selection, while DA was used as a method for feature classification and performance analysis.
RESULTS: One hundred and six imaging features were extracted for 46 lesions for a total of 4876 features analyzed. No significant differences between the training and validating sets in terms of age, sex, PSA values, lesion location and size (P>0.05) were demonstrated by the machine-learning model. Thirteen features were able to discriminate FU disease status after NCA selection. Best performance in DA classification was obtained using the combination of the 13 selected features (sensitivity 74%, specificity 58% and accuracy 66%) compared to the use of all features (sensitivity 40%, specificity 52%, and accuracy 51%). Per-site performance of the 13 selected features in DA classification were as follows: T = sensitivity 63%, specificity 83%, accuracy 71%; N = sensitivity 87%, specificity 91% of and accuracy 90%; bone-M = sensitivity 33%, specificity 77% and accuracy 66%.
CONCLUSIONS: An artificial intelligence model demonstrated to be feasible and able to select a panel of 18F-Cho PET/CT features with valuable association with PCa patients’ outcome.


KEY WORDS: Prostatic neoplasms; Positron emission tomography computed tomography; Choline

top of page