Department of Radiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, #17 Panjiayuan nanli, Chaoyang district, Beijing, China, 100021.
Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, #17 Panjiayuan nanli, Chaoyang district, Beijing, China, 100021.
Acad Radiol. 2021 Nov;28 Suppl 1:S95-S104. doi: 10.1016/j.acra.2020.10.026. Epub 2020 Nov 12.
To investigate the capability of delta-radiomics to predict pathological complete response (pCR) after neoadjuvant chemoradiotherapy (nCRT) in patients with locally advanced rectal cancer (LARC).
This retrospective study enrolled 165 consecutive patients with LARC (training set, n = 116; test set, n = 49) who received nCRT before surgery. All patients underwent pre- and post-nCRT MRI examination from which radiomics features were extracted. A delta-radiomics feature was defined as the percentage change in a radiomics feature from pre- to post-nCRT MRI. A data reduction and feature selection process including the least absolute shrinkage and selection operator algorithm was performed for building T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) delta-radiomics signature. Logistic regression was used to build a T2WI and DWI combined radiomics model. Receiver operating characteristic analysis was performed to assess diagnostic performance. Delong method was used to compare the performance of delta-radiomics model with that of magnetic resonance tumor regression grade (mrTRG).
Twenty-seven of 165 patients (16.4%) achieved pCR. T2WI and DWI delta-radiomics signature, and the combined model showed good predictive performance for pCR. The combined model achieved the highest areas under the receiver operating characteristic curves of 0.91 (95% confidence interval: 0.85-0.98) and 0.91 (95% confidence interval: 0.83-0.99) in the training and test sets, respectively (significantly greater than those for mrTRG; training set, p < 0.001; test set, p = 0.04).
MRI-based delta-radiomics can help predict pCR after nCRT in patients with LARC with better performance than mrTRG.
探究放射组学 delta 特征在预测接受新辅助放化疗（nCRT）的局部进展期直肠癌（LARC）患者病理完全缓解（pCR）中的作用。
本回顾性研究纳入了 165 例接受 nCRT 治疗的 LARC 患者（训练集，n=116；测试集，n=49），所有患者均在术前接受了 nCRT 前后的 MRI 检查，并从中提取了放射组学特征。放射组学 delta 特征定义为 nCRT 前后 MRI 上放射组学特征的百分比变化。采用最小绝对收缩和选择算子算法进行数据降维和特征选择，构建 T2 加权成像（T2WI）和弥散加权成像（DWI）的 delta 放射组学特征。采用逻辑回归构建 T2WI 和 DWI 联合放射组学模型。采用受试者工作特征曲线分析评估诊断效能。采用 Delong 方法比较 delta 放射组学模型与磁共振肿瘤退缩分级（mrTRG）的性能。
165 例患者中有 27 例（16.4%）达到 pCR。T2WI 和 DWI 的 delta 放射组学特征和联合模型对 pCR 均具有较好的预测性能。联合模型在训练组和测试组中的受试者工作特征曲线下面积最高，分别为 0.91（95%置信区间：0.85-0.98）和 0.91（95%置信区间：0.83-0.99）（均显著大于 mrTRG；训练集，p<0.001；测试集，p=0.04）。
基于 MRI 的 delta 放射组学有助于预测接受 nCRT 的 LARC 患者的 pCR，其性能优于 mrTRG。
