Predicting aggressive disease and poor outcome in endometrial cancer using preoperative [18F]FDG PET primary tumor radiomics.
Purpose: To develop a [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) primary tumor radiomic model for predicting disease-specific survival (DSS), and compare it with conventional PET markers in a large endometrial cancer cohort. Methods: Radiomic features were extracted from p...
| Published in: | European Journal of Nuclear Medicine & Molecular Imaging Vol. 53; no. 1; pp. 167 - 181 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Published: |
Springer Nature
Dec2025
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=189634231&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 189634231 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 16197070 NPC jtl: European Journal of Nuclear Medicine & Molecular Imaging issn: 16197070 maglogo: N pubinfo: dt: Dec2025 vid: 53 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 189634231 185857225 10.1007/s00259-025-07335-7 189634231 ppf: 167 ppct: 14 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Predicting aggressive disease and poor outcome in endometrial cancer using preoperative [18F]FDG PET primary tumor radiomics. aug: au: Fasmer, Kristine Eldevik Gulati, Ankush Lindås, Sunniva Krakstad, Camilla Haldorsen, Ingfrid Salvesen affil: https://ror.org/03np4e098 Mohn Medical Imaging and Visualization Centre, Department of Radiology, Haukeland University Hospital, Bergen, Norway sug: ab: Purpose: To develop a [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) primary tumor radiomic model for predicting disease-specific survival (DSS), and compare it with conventional PET markers in a large endometrial cancer cohort. Methods: Radiomic features were extracted from preoperative [18F]FDG PET scans of 489 endometrial cancer patients using a standardized uptake value (SUV) threshold > 2.5 to define primary metabolic tumor volumes (MTVs). A second reader extracted features in 154/489 patients, in which intraclass correlation coefficients (ICCs) were calculated. Radiomic features with ICCs > 0.75 were retained and ComBat harmonization was applied to reduce scanner/protocol effects on the extracted features. Patients were divided into training (n = 343) and test (n = 146) sets. A radiomic DSS score (Rdss) was developed in the training set using least absolute shrinkage and selection operator (LASSO) Cox regression. A combined model (Cdss), incorporating Rdss, PET positive lymph nodes (LNPET) and preoperative histology risk was constructed using multivariable Cox hazard analyses. Prediction performances were assessed by comparing areas under time-dependent receiver operating characteristic curves (tdROCs AUCs) for Rdss, Cdss, and conventional PET markers: SUVmax, SUVmean, MTV, tumor lesion glycolysis (TLG) and LNPET. Results: In the test set, AUCs for 2- and 5-year DSS were higher for Rdss (0.855, 0.720) compared to SUVmax (0.548, 0.572) and SUVmean (0.549, 0.554) (p ≤ 0.04 for all), while similar to MTV (0.863, 0.696), TLG (0.814, 0.672) and LNPET (0.802, 0.626) (p ≥ 0.12 for all). Cdss predicted 2-year DSS with AUC of 0.909 in the test set, outperforming all conventional imaging markers (p ≤ 0.04 for all) except MTV (p = 0.29). For 5-year DSS, Cdss (AUC: 0.817) outperformed all conventional imaging markers, including MTV (AUC ≤ 0.696, p ≤ 0.05, for all). Conclusion: Rdss predicts short-term survival with high accuracy, outperforming tumor SUVmax/mean, but not MTV, TLG and LNPET. The combined Cdss model yields high accuracy for predicting both short- and long-term survival, outperforming all conventional PET imaging markers. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|