Zhong Jim, Davey Angela, Frood Russell, McWilliam Alan, Shortall Jane, Reardon Mark, Reaves Kimberley, Swinton Martin, Hulson Oliver, West Catharine, Buckley David, Brown Sarah, Choudhury Ananya, Hoskin Peter, Henry Ann, Scarsbrook Andrew
Leeds Institute of Medical Research, University of Leeds, Leeds, UK.
Department of Radiology, Leeds Cancer Centre, St James's University Hospital, Leeds Teaching Hospitals National Health Service (NHS) Trust, Beckett Street, Leeds, LS9 7TF, UK.
Radiol Med. 2025 Jul 2. doi: 10.1007/s11547-025-02037-4.
To investigate the value of combining MRI radiomic and hypoxia-associated gene signature information with clinical data for predicting biochemical recurrence-free survival (BCRFS) after radiotherapy for prostate cancer.
Patients with biopsy-proven prostate cancer, hypoxia-associated gene signature scores and pre-treatment MRI who received radiotherapy between 01/12/2007 and 31/08/2013 at two cancer centres were included in this retrospective cohort analysis. Prostate segmentation was performed on axial T2-weighted sequences using RayStation (v9.1). Histogram standardisation was applied prior to radiomic feature (RF) extraction. PyRadiomics (v3.0.1) was used to extract RFs for analysis. Four multivariable Cox proportional hazards BCRFS prediction models using clinical information alone and in combination with RFs and/or hypoxia scores were evaluated using concordance index (C-index) [confidence intervals (CI)]. Akaike Information Criterion (AIC) was used to assess model fit.
178 patients were included. The clinical-only model performance C-index score was 0.69 [0.64-0.7]. The combined clinical-radiomics model (C-index 0.70[0.66-0.73]) and clinical-radiomics-hypoxia model (C-index 0.70[0.65-0.73]) both had higher model performance. The clinical-hypoxia model (C-index 0.68 [0.63-0.7) had lower model performance. Based on AIC, addition of RFs to clinical variables alone improved model performance (p = 0.027), whereas adding hypoxia gene signature scores did not (p = 0.625). The selected features of the combined clinical-radiomics model included age, ISUP grade, tumour stage, and wavelet-derived grey level co-occurrence matrix (GLCM) RFs.
Adding pre-treatment prostate MRI-derived radiomic features to a clinical model improves accuracy of predicting BCRFS after prostate radiotherapy, however addition of hypoxia gene signatures does not improve model accuracy.
探讨将MRI影像组学和缺氧相关基因特征信息与临床数据相结合，用于预测前列腺癌放疗后无生化复发生存期（BCRFS）的价值。
本回顾性队列分析纳入了2007年12月1日至2013年8月31日期间在两个癌症中心接受放疗的经活检证实为前列腺癌、具有缺氧相关基因特征评分和治疗前MRI的患者。使用RayStation（v9.1）在轴向T2加权序列上进行前列腺分割。在提取影像组学特征（RF）之前进行直方图标准化。使用PyRadiomics（v3.0.1）提取RFs进行分析。使用一致性指数（C指数）[置信区间（CI）]评估四个使用单独临床信息以及与RFs和/或缺氧评分相结合的多变量Cox比例风险BCRFS预测模型。使用赤池信息准则（AIC）评估模型拟合度。
共纳入178例患者。仅临床模型的性能C指数评分为0.69[0.64 - 0.7]。临床-影像组学联合模型（C指数0.70[0.66 - 0.73]）和临床-影像组学-缺氧模型（C指数0.70[0.65 - 0.73]）均具有更高的模型性能。临床-缺氧模型（C指数0.68[0.63 - 0.7]）的模型性能较低。基于AIC，仅在临床变量中添加RFs可改善模型性能（p = 0.027），而添加缺氧基因特征评分则不能（p = 0.625）。临床-影像组学联合模型选择的特征包括年龄、ISUP分级、肿瘤分期以及小波衍生的灰度共生矩阵（GLCM）RFs。
在临床模型中添加治疗前前列腺MRI衍生的影像组学特征可提高预测前列腺癌放疗后BCRFS的准确性，然而添加缺氧基因特征并不能提高模型准确性。
