Wagner-Larsen Kari S, Lura Njål, Gulati Ankush, Ryste Stian, Hodneland Erlend, Fasmer Kristine E, Woie Kathrine, Bertelsen Bjørn I, Salvesen Øyvind, Halle Mari K, Smit Noeska, Krakstad Camilla, Haldorsen Ingfrid S
Mohn Medical Imaging and Visualization Centre (MMIV), Department of Radiology, Haukeland University Hospital, Jonas Lies vei 65, Bergen, 5021, Norway.
Section for Radiology, Department of Clinical Medicine, University of Bergen, Bergen, Norway.
BMC Cancer. 2025 Jan 22;25(1):122. doi: 10.1186/s12885-025-13509-1.
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.
A total of 110 LACC patients undergoing CCRT with MRI at baseline and mid-treatment were divided into training (cohort: n = 73) and validation (cohort: 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 (from delta features) and Pre-CCRT (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: ≤2 cm; >2 and ≤ 4 cm; >4 cm) was evaluated by area under time-dependent receiver operating characteristics (tdROC) curves (AUC) in cohort and cohort (AUC/AUC). Mann-Whitney U tests assessed differences in radiomic delta features. PFS was evaluated using the Kaplan-Meier method with log-rank tests.
Delta (AUC/AUC: 0.74/0.79) marginally outperformed Pre-CCRT (0.72/0.75) for predicting 5-year PFS, and both signatures clearly surpassed that of FIGO (0.61/0.61) and Tumor (0.58/0.65). In total, four features within Delta and Pre-CCRT significantly differed in delta feature values between progressors and non-progressors, being consistently lower in progressors (p ≤ 0.03 for all). High Delta and Pre-CCRT radiomic scores were associated with poor PFS (p ≤ 0.04 for Delta in cohort/Pre-CCRT in both cohorts; p = 0.11 for Delta in cohort).
Delta- and pretreatment radiomic signatures equally allow early prognostication in LACC, outperforming FIGO stage and MRI-assessed maximum tumor diameter.
需要有效的诊断工具来迅速识别高危局部晚期宫颈癌(LACC)患者,以促进早期个体化治疗。本研究的目的是评估LACC患者同步放化疗(CCRT)期间,肿瘤在T2加权成像(T2WI)上的时间变化(放射组学变化)及其与无进展生存期(PFS)的关系。此外,开发、验证和比较用于预后建模的放射组学变化特征和治疗前放射组学特征。
110例接受CCRT且在基线期和治疗中期进行MRI检查的LACC患者被分为训练组(队列:n = 73)和验证组(队列:n = 37)。从CCRT前和CCRT中期T2WI上分割的肿瘤中提取放射组学特征,并计算放射组学变化(变化特征)。通过最小绝对收缩和选择算子(LASSO)Cox回归构建两个预测PFS的放射组学特征:变化特征(来自变化特征)和CCRT前特征(来自CCRT前特征)。通过时间依赖性受试者工作特征(tdROC)曲线下面积(AUC)在训练队列和验证队列中评估放射组学特征、2018年国际妇产科联合会(FIGO)分期(I-IV期)以及基线MRI得出的最大肿瘤直径(肿瘤:≤2 cm;>2且≤4 cm;>4 cm)的预后性能(AUC/AUC)。Mann-Whitney U检验评估放射组学变化特征的差异。使用Kaplan-Meier方法和对数秩检验评估PFS。
在预测5年PFS方面,变化特征(AUC/AUC:0.74/0.79)略优于CCRT前特征(0.72/0.75),且两个特征均明显优于FIGO分期(0.61/0.61)和肿瘤直径(0.58/0.65)。总体而言,变化特征和CCRT前特征中的四个特征在进展者和非进展者之间的变化特征值存在显著差异,进展者中的这些特征值始终较低(所有p≤0.03)。高变化特征和CCRT前放射组学评分与较差的PFS相关(训练队列中变化特征p≤0.04/两个队列中CCRT前特征p≤0.04;验证队列中变化特征p = 0.11)。
变化特征和治疗前放射组学特征同样能够对LACC进行早期预后评估,优于FIGO分期和MRI评估的最大肿瘤直径。