Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, Hunan, P.R. China.
Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, Hunan, P.R. China.
Acad Radiol. 2023 Sep;30 Suppl 1:S176-S184. doi: 10.1016/j.acra.2022.12.037. Epub 2023 Feb 2.
The 15%-27% of patients with locally advanced rectal cancer (LARC) achieved pathologic complete response (pCR) to neoadjuvant chemoradiotherapy (nCRT) and could avoid proctectomy. We aimed to investigate the effectiveness of treatment response prediction using MRI-based pre-, post-, and delta-radiomic features for LARC patients treated with nCRT and to compare these radiomic models with radiologists' visual assessment.
A total of 126 patients with LARC who received nCRT before surgery were included and randomly divided into a training set (n = 84) and a validation set (n = 42). 250 radiomic features were extracted from T2-weighted images from pre- and post-nCRT MRI. Pearson correlation analysis and AONVA or Relief were used to identify radiomic descriptors associated with pCR. Five machine-learning classifiers were compared to construct radiomic models. The radiomic nomogram was built via multivariate logistic regression analysis. Two senior radiologists independently rated tumor regression grades and compared with radiomic models. Area under the curve (AUC) of the models and pooled observers were compared by using the DeLong test.
The optimal pre-, post-, and delta-radiomic models yielded an AUC of 0.717 (95% CI: 0.639-0.795), 0.805 (95%CI: 0.736-0.874), and 0.724 (95%CI: 0.648-0.800), respectively. The radiomic nomogram based on pre-nCRT cN stage, pre-nCRT radscore, and post-nCRT radscore achieved an AUC of 0.852 (95%CI: 0.774-0.930), which was higher than the single radiomic models and pooled readers (all p < 0.05).
The radiomic nomogram is an effective and invasive tool to predict pCR in LARC patients after nCRT, which outperforms radiologists.
接受新辅助放化疗（nCRT）的局部晚期直肠癌（LARC）患者中有 15%~27%达到病理完全缓解（pCR），可避免直肠切除术。本研究旨在探讨 MRI 基线、治疗后及治疗前后差值的放射组学特征预测 LARC 患者 nCRT 治疗反应的有效性，并将这些放射组学模型与放射科医生的视觉评估进行比较。
共纳入 126 例接受 nCRT 治疗的 LARC 患者，随机分为训练集（n=84）和验证集（n=42）。从基线和治疗后 MRI 的 T2 加权图像中提取了 250 个放射组学特征。采用 Pearson 相关分析和 AONVA 或 Relief 来识别与 pCR 相关的放射组学特征。比较了 5 种机器学习分类器来构建放射组学模型。通过多变量逻辑回归分析构建放射组学列线图。两位资深放射科医生独立评估肿瘤消退分级，并与放射组学模型进行比较。采用 DeLong 检验比较模型和合并观察者的曲线下面积（AUC）。
最优的基线、治疗后和治疗前后差值的放射组学模型的 AUC 分别为 0.717（95%CI：0.6390.795）、0.805（95%CI：0.7360.874）和 0.724（95%CI：0.6480.800）。基于基线 nCRT cN 分期、基线 nCRT radscore 和治疗后 nCRT radscore 的放射组学列线图的 AUC 为 0.852（95%CI：0.7740.930），高于单一放射组学模型和合并观察者（均 P<0.05）。
放射组学列线图是一种有效的、非侵入性的预测 LARC 患者 nCRT 后 pCR 的工具，优于放射科医生。
