Back to Search Start Over

MRI-based radiomic signatures for pretreatment prognostication in cervical cancer.

Authors :
Wagner-Larsen KS
Hodneland E
Fasmer KE
Lura N
Woie K
Bertelsen BI
Salvesen Ø
Halle MK
Smit N
Krakstad C
Haldorsen IS
Source :
Cancer medicine [Cancer Med] 2023 Oct; Vol. 12 (20), pp. 20251-20265. Date of Electronic Publication: 2023 Oct 16.
Publication Year :
2023

Abstract

Background: Accurate pretherapeutic prognostication is important for tailoring treatment in cervical cancer (CC).<br />Purpose: To investigate whether pretreatment MRI-based radiomic signatures predict disease-specific survival (DSS) in CC.<br />Study Type: Retrospective.<br />Population: CC patients (n = 133) allocated into training <subscript>(T)</subscript> (n <subscript>T</subscript>  = 89)/validation <subscript>(V)</subscript> (n <subscript>V</subscript>  = 44) cohorts.<br />Field Strength/sequence: T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) at 1.5T or 3.0T.<br />Assessment: Radiomic features from segmented tumors were extracted from T2WI and DWI (high b-value DWI and apparent diffusion coefficient (ADC) maps).<br />Statistical Tests: Radiomic signatures for prediction of DSS from T2WI (T2 <subscript>rad</subscript> ) and T2WI with DWI (T2 + DWI <subscript>rad</subscript> ) were constructed by least absolute shrinkage and selection operator (LASSO) Cox regression. Area under time-dependent receiver operating characteristics curves (AUC) were used to evaluate and compare the prognostic performance of the radiomic signatures, MRI-derived maximum tumor size ≤/> 4 cm (MAX <subscript>size</subscript> ), and 2018 International Federation of Gynecology and Obstetrics (FIGO) stage (I-II/III-IV). Survival was analyzed using Cox model estimating hazard ratios (HR) and Kaplan-Meier method with log-rank tests.<br />Results: The radiomic signatures T2 <subscript>rad</subscript> and T2 + DWI <subscript>rad</subscript> yielded AUC <subscript>T</subscript> /AUC <subscript>V</subscript> of 0.80/0.62 and 0.81/0.75, respectively, for predicting 5-year DSS. Both signatures yielded better or equal prognostic performance to that of MAX <subscript>size</subscript> (AUC <subscript>T</subscript> /AUC <subscript>V</subscript> : 0.69/0.65) and FIGO (AUC <subscript>T</subscript> /AUC <subscript>V</subscript> : 0.77/0.64) and were significant predictors of DSS after adjusting for FIGO (HR <subscript>T</subscript> /HR <subscript>V</subscript> for T2 <subscript>rad</subscript> : 4.0/2.5 and T2 + DWI <subscript>rad</subscript> : 4.8/2.1). Adding T2 <subscript>rad</subscript> and T2 + DWI <subscript>rad</subscript> to FIGO significantly improved DSS prediction compared to FIGO alone in cohort <subscript>(T)</subscript> (AUC <subscript>T</subscript> 0.86 and 0.88 vs. 0.77), and FIGO with T2 + DWI <subscript>rad</subscript> tended to the same in cohort <subscript>(V)</subscript> (AUC <subscript>V</subscript> 0.75 vs. 0.64, p = 0.07). High radiomic score for T2 + DWI <subscript>rad</subscript> was significantly associated with reduced DSS in both cohorts.<br />Data Conclusion: Radiomic signatures from T2WI and T2WI with DWI may provide added value for pretreatment risk assessment and for guiding tailored treatment strategies in CC.<br /> (© 2023 The Authors. Cancer Medicine published by John Wiley & Sons Ltd.)

Details

Language :
English
ISSN :
2045-7634
Volume :
12
Issue :
20
Database :
MEDLINE
Journal :
Cancer medicine
Publication Type :
Academic Journal
Accession number :
37840437
Full Text :
https://doi.org/10.1002/cam4.6526