Pierpaolo Alongi1, Alessandro Stefano2, Albert Comelli3, Riccardo Laudicella4, Salvatore Scalisi5, Giuseppe Arnone6, Stefano Barone7, Massimiliano Spada8, Pierpaolo Purpura9, Tommaso Vincenzo Bartolotta6,9, Massimo Midiri6, Roberto Lagalla6, Giorgio Russo2. 1. Nuclear Medicine Unit, Fondazione Istituto G. Giglio, Contrada Pietrapollastra Pisciotto, 90015, Cefalù, PA, Italy. alongi.pierpaolo@gmail.com. 2. Institute of Molecular Bioimaging and Physiology, National Research Council (CNR), Cefalù, PA, Italy. 3. Ri.MED Foundation, Palermo, Italy. 4. Department of Biomedical and Dental Sciences and of Morpho-functional Imaging, Nuclear Medicine Unit, University of Messina, Messina, Italy. 5. Nuclear Medicine Unit, Fondazione Istituto G. Giglio, Contrada Pietrapollastra Pisciotto, 90015, Cefalù, PA, Italy. 6. Department of Biomedicine, Neuroscience and Advanced Diagnostics, University of Palermo, Palermo, Italy. 7. Dipartimento di Scienze Agronomiche, Alimentari e Forestali (SAAF), University of Palermo, Palermo, Italy. 8. Unit of Oncology, Fondazione Istituto G. Giglio, Cefalù, PA, Italy. 9. Department of Radiology, Fondazione Istituto Giuseppe Giglio Ct.da Pietrapollastra, Via Pisciotto, 90015, Cefalù (Palermo), Italy.
Abstract
OBJECTIVE: The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging. MATERIAL AND METHODS: Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M). RESULTS: In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%. CONCLUSION: This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes. KEY POINTS: • Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.
OBJECTIVE: The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging. MATERIAL AND METHODS: Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M). RESULTS: In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%. CONCLUSION: This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes. KEY POINTS: • Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.
Authors: Philip Cornford; Joaquim Bellmunt; Michel Bolla; Erik Briers; Maria De Santis; Tobias Gross; Ann M Henry; Steven Joniau; Thomas B Lam; Malcolm D Mason; Henk G van der Poel; Theo H van der Kwast; Olivier Rouvière; Thomas Wiegel; Nicolas Mottet Journal: Eur Urol Date: 2016-08-31 Impact factor: 20.096
Authors: Zachary S Zumsteg; Daniel E Spratt; Paul B Romesser; Xin Pei; Zhigang Zhang; Marisa Kollmeier; Sean McBride; Yoshiya Yamada; Michael J Zelefsky Journal: J Urol Date: 2015-07-10 Impact factor: 7.450
Authors: Albert Comelli; Alessandro Stefano; Samuel Bignardi; Giorgio Russo; Maria Gabriella Sabini; Massimo Ippolito; Stefano Barone; Anthony Yezzi Journal: Artif Intell Med Date: 2019-01-08 Impact factor: 5.326
Authors: Constantinos Zamboglou; Montserrat Carles; Tobias Fechter; Selina Kiefer; Kathrin Reichel; Thomas F Fassbender; Peter Bronsert; Goeran Koeber; Oliver Schilling; Juri Ruf; Martin Werner; Cordula A Jilg; Dimos Baltas; Michael Mix; Anca L Grosu Journal: Theranostics Date: 2019-04-13 Impact factor: 11.556
Authors: R Chowdhury; B Ganeshan; S Irshad; K Lawler; M Eisenblätter; H Milewicz; M Rodriguez-Justo; K Miles; P Ellis; A Groves; S Punwani; T Ng Journal: Br J Radiol Date: 2014-03-06 Impact factor: 3.039
Authors: Jake Kendrick; Roslyn J Francis; Ghulam Mubashar Hassan; Pejman Rowshanfarzad; Jeremy S L Ong; Martin A Ebert Journal: Eur J Nucl Med Mol Imaging Date: 2022-08-17 Impact factor: 10.057
Authors: Ahmed Ebada Salem; Gabriel C Fine; Matthew F Covington; Bhasker R Koppula; Richard H Wiggins; John M Hoffman; Kathryn A Morton Journal: Cancers (Basel) Date: 2022-06-18 Impact factor: 6.575