학술논문
Role of Machine Learning (ML)-Based Classification Using Conventional 18 F-FDG PET Parameters in Predicting Postsurgical Features of Endometrial Cancer Aggressiveness.
Document Type
Academic Journal
Author
Bezzi C; Faculty of Medicine and Surgery, Vita-Salute San Raffaele University, Via Olgettina 58, 20132 Milan, Italy.; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Bergamini A; Faculty of Medicine and Surgery, Vita-Salute San Raffaele University, Via Olgettina 58, 20132 Milan, Italy.; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Mathoux G; School of Medicine and Surgery, University of Milano-Bicocca, Piazza dell'Ateneo Nuovo 1, 20126 Milan, Italy.; Ghezzo S; Faculty of Medicine and Surgery, Vita-Salute San Raffaele University, Via Olgettina 58, 20132 Milan, Italy.; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Monaco L; School of Medicine and Surgery, University of Milano-Bicocca, Piazza dell'Ateneo Nuovo 1, 20126 Milan, Italy.; Candotti G; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Fallanca F; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Gajate AMS; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Rabaiotti E; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Cioffi R; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Bocciolone L; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Gianolli L; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Taccagni G; Pathology Unit, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Candiani M; Faculty of Medicine and Surgery, Vita-Salute San Raffaele University, Via Olgettina 58, 20132 Milan, Italy.; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Mangili G; Unit of Obstetrics and Gynaecology, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Mapelli P; Faculty of Medicine and Surgery, Vita-Salute San Raffaele University, Via Olgettina 58, 20132 Milan, Italy.; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.; Picchio M; Faculty of Medicine and Surgery, Vita-Salute San Raffaele University, Via Olgettina 58, 20132 Milan, Italy.; Nuclear Medicine Department, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, 20132 Milan, Italy.
Source
Publisher: MDPI Country of Publication: Switzerland NLM ID: 101526829 Publication Model: Electronic Cited Medium: Print ISSN: 2072-6694 (Print) Linking ISSN: 20726694 NLM ISO Abbreviation: Cancers (Basel) Subsets: PubMed not MEDLINE
Subject
Language
English
ISSN
2072-6694
Abstract
Purpose: to investigate the preoperative role of ML-based classification using conventional 18 F-FDG PET parameters and clinical data in predicting features of EC aggressiveness.
Methods: retrospective study, including 123 EC patients who underwent18 F-FDG PET (2009-2021) for preoperative staging. Maximum standardized uptake value (SUVmax), SUVmean, metabolic tumour volume (MTV), and total lesion glycolysis (TLG) were computed on the primary tumour. Age and BMI were collected. Histotype, myometrial invasion (MI), risk group, lymph-nodal involvement (LN), and p53 expression were retrieved from histology. The population was split into a train and a validation set (80-20%). The train set was used to select relevant parameters (Mann-Whitney U test; ROC analysis) and implement ML models, while the validation set was used to test prediction abilities.
Results: on the validation set, the best accuracies obtained with individual parameters and ML were: 61% (TLG) and 87% (ML) for MI; 71% (SUVmax) and 79% (ML) for risk groups; 72% (TLG) and 83% (ML) for LN; 45% (SUVmax; SUVmean) and 73% (ML) for p53 expression.
Conclusions: ML-based classification using conventional18 F-FDG PET parameters and clinical data demonstrated ability to characterize the investigated features of EC aggressiveness, providing a non-invasive way to support preoperative stratification of EC patients.
Methods: retrospective study, including 123 EC patients who underwent
Results: on the validation set, the best accuracies obtained with individual parameters and ML were: 61% (TLG) and 87% (ML) for MI; 71% (SUVmax) and 79% (ML) for risk groups; 72% (TLG) and 83% (ML) for LN; 45% (SUVmax; SUVmean) and 73% (ML) for p53 expression.
Conclusions: ML-based classification using conventional