MRI delta radiomics during chemoradiotherapy for prognostication in locally advanced cervical cancer
Kari S. Wagner‐Larsen, Njål Lura, Ankush Gulati, Stian Ryste, Erlend Hodneland, Kristine E. Fasmer, Kathrine Woie, Bjørn I. Bertelsen, Øyvind Salvesen, Mari K. Halle, Noeska Smit, Camilla Krakstad, Ingfrid S. Haldorsen
Abstract
Abstract Background Effective diagnostic tools for prompt identification of high-risk locally advanced cervical cancer (LACC) patients are needed to facilitate early, individualized treatment. The aim of this work was to assess temporal changes in tumor radiomics (delta radiomics) from T2-weighted imaging (T2WI) during concurrent chemoradiotherapy (CCRT) in LACC patients, and their association with progression-free survival (PFS). Furthermore, to develop, validate, and compare delta- and pretreatment radiomic signatures for prognostic modeling. Methods A total of 110 LACC patients undergoing CCRT with MRI at baseline and mid-treatment were divided into training (cohort T : n = 73) and validation (cohort V : n = 37) cohorts. Radiomic features were extracted from tumors segmented on pre-CCRT and mid-CCRT T2WI and radiomic deltas (delta features) were computed. Two radiomic signatures for predicting PFS were constructed by least absolute shrinkage and selection operator (LASSO) Cox regression: Delta rad (from delta features) and Pre-CCRT rad (from pre-CCRT features). Prognostic performance of the radiomic signatures, 2018 International Federation of Gynecology and Obstetrics (FIGO) stage (I–IV), and baseline MRI-derived maximum tumor diameter (Tumor max : ≤2 cm; >2 and ≤ 4 cm; >4 cm) was evaluated by area under time-dependent receiver operating characteristics (tdROC) curves (AUC) in cohort T and cohort V (AUC T /AUC V ). Mann–Whitney U tests assessed differences in radiomic delta features. PFS was evaluated using the Kaplan–Meier method with log-rank tests. Results Delta rad (AUC T /AUC V : 0.74/0.79) marginally outperformed Pre-CCRT rad (0.72/0.75) for predicting 5-year PFS, and both signatures clearly surpassed that of FIGO (0.61/0.61) and Tumor max (0.58/0.65). In total, four features within Delta rad and Pre-CCRT rad significantly differed in delta feature values between progressors and non-progressors, being consistently lower in progressors ( p ≤ 0.03 for all). High Delta rad and Pre-CCRT rad radiomic scores were associated with poor PFS ( p ≤ 0.04 for Delta rad in cohort T /Pre-CCRT rad in both cohorts; p = 0.11 for Delta rad in cohort V ). Conclusions Delta- and pretreatment radiomic signatures equally allow early prognostication in LACC, outperforming FIGO stage and MRI-assessed maximum tumor diameter.