MRI-based radiomic signatures for pretreatment prognostication in cervical cancer

Kari S Wagner-Larsen; Erlend Hodneland; Kristine E Fasmer; Njål Lura; Kathrine Woie; Bjørn I Bertelsen; Øyvind Salvesen; Mari K Halle; Noeska Smit; Camilla Krakstad; Ingfrid S Haldorsen

doi:10.1002/cam4.6526

MRI-based radiomic signatures for pretreatment prognostication in cervical cancer

Cancer Med. 2023 Oct;12(20):20251-20265. doi: 10.1002/cam4.6526. Epub 2023 Oct 16.

Authors

Kari S Wagner-Larsen^{1

2}, Erlend Hodneland^{1

3}, Kristine E Fasmer^{1

2}, Njål Lura^{1

2}, Kathrine Woie⁴, Bjørn I Bertelsen⁵, Øyvind Salvesen⁶, Mari K Halle^{4

7}, Noeska Smit^{1

8}, Camilla Krakstad^{4

7}, Ingfrid S Haldorsen^{1

2}

Affiliations

¹ Mohn Medical Imaging and Visualization Centre (MMIV), Department of Radiology, Haukeland University Hospital, Bergen, Norway.
² Section for Radiology, Department of Clinical Medicine, University of Bergen, Bergen, Norway.
³ Department of Mathematics, University of Bergen, Bergen, Norway.
⁴ Department of Obstetrics and Gynecology, Haukeland University Hospital, Bergen, Norway.
⁵ Department of Pathology, Haukeland University Hospital, Bergen, Norway.
⁶ Clinical Research Unit, Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, Norway.
⁷ Centre for Cancer Biomarkers (CCBIO), Department of Clinical Science, University of Bergen, Bergen, Norway.
⁸ Department of Informatics, University of Bergen, Bergen, Norway.

Abstract

Background: Accurate pretherapeutic prognostication is important for tailoring treatment in cervical cancer (CC).

Purpose: To investigate whether pretreatment MRI-based radiomic signatures predict disease-specific survival (DSS) in CC.

Study type: Retrospective.

Population: CC patients (n = 133) allocated into training_(T) (n_T = 89)/validation_(V) (n_V = 44) cohorts.

Field strength/sequence: T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) at 1.5T or 3.0T.

Assessment: Radiomic features from segmented tumors were extracted from T2WI and DWI (high b-value DWI and apparent diffusion coefficient (ADC) maps).

Statistical tests: Radiomic signatures for prediction of DSS from T2WI (T2_rad ) and T2WI with DWI (T2 + DWI_rad ) 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_size ), 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.

Results: The radiomic signatures T2_rad and T2 + DWI_rad yielded AUC_T /AUC_V 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_size (AUC_T /AUC_V : 0.69/0.65) and FIGO (AUC_T /AUC_V : 0.77/0.64) and were significant predictors of DSS after adjusting for FIGO (HR_T /HR_V for T2_rad : 4.0/2.5 and T2 + DWI_rad : 4.8/2.1). Adding T2_rad and T2 + DWI_rad to FIGO significantly improved DSS prediction compared to FIGO alone in cohort_(T) (AUC_T 0.86 and 0.88 vs. 0.77), and FIGO with T2 + DWI_rad tended to the same in cohort_(V) (AUC_V 0.75 vs. 0.64, p = 0.07). High radiomic score for T2 + DWI_rad was significantly associated with reduced DSS in both cohorts.

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.

Keywords: biomarkers; magnetic resonance imaging; prognostication; radiomics; uterine cervical neoplasms.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Diffusion Magnetic Resonance Imaging / methods
Female
Humans
Magnetic Resonance Imaging / methods
Prognosis
Retrospective Studies
Uterine Cervical Neoplasms* / diagnostic imaging
Uterine Cervical Neoplasms* / pathology