Role of Machine Learning (ML)-Based Classification Using Conventional 18F-FDG PET Parameters in Predicting Postsurgical Features of Endometrial Cancer Aggressiveness

Abstract

Purpose: to investigate the preoperative role of ML-based classification using conventional 18F-FDG PET parameters and clinical data in predicting features of EC aggressiveness. Methods: retrospective study, including 123 EC patients who underwent 18F-FDG PET (20092021) 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 conventional 18F-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.

The Utility of 18F-FDG-PET–CT Metabolic Parameters in Evaluating the Primary Tumor Aggressiveness and Lymph Node Metastasis of Nasopharyngeal Carcinoma

“…Therefore, as a tumor becomes increasingly undifferentiated and aggressive, it results in elevated glucose utilization and increased uptake of the radioactive tracer 18 F-FDG. 19 , 20 Black patients with breast cancer have poorer prognosis and higher mortality. Abubakar et al 19 observed differences in 18 F-FDG PET–CT metabolic parameters of locally advanced invasive ductal carcinoma (IDC) among patients of different racial groups and molecular subtypes.…”

“…18 F-FDG PET–CT parameters offer metabolic information that can be used to evaluate tumor aggressiveness, 18 - 20 predict lymph node metastasis (LNM) 21 - 23 and may be correlated with patient survival. 24 The maximum standard uptake value (SUV max ) is the most commonly used metabolic parameter.…”

Retrospective analysis of the 18F-FDG PET/CT cutoff value for metabolic parameters was performed as a prediction model to evaluate risk factors for endometrial cancer

“…This approach aims to be more closely aligned with clinical practice, providing guidance for patient surgery, adjuvant therapy, and prognosis assessment. Carolina Bezzi [ 36 ] investigated the role of machine learning (ML)-based classification using PET parameters in predicting features of EC aggressiveness, aiming at supporting the clinical decision-making process. Thus we would further our search involving the accuracy and predictive ability of PET/CT for the assessment of high-risk factors in EC patients according to 2023 new FIGO staging or use machine learning (ML) in the future.…”