基于影像组学和临床因素的联合预测模型的开发，用于预测局部晚期直肠癌患者对新辅助放化疗的肿瘤反应

Development of a Joint Prediction Model Based on Both the Radiomics and Clinical Factors for Predicting the Tumor Response to Neoadjuvant Chemoradiotherapy in Patients with Locally Advanced Rectal Cancer.

作者信息

Liu Yang, Zhang Feng-Jiao, Zhao Xi-Xi, Yang Yuan, Liang Chun-Yi, Feng Li-Li, Wan Xiang-Bo, Ding Yi, Zhang Yao-Wei

机构信息

Department of Radiation Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, People's Republic of China.

Shanghai Concord Medical Cancer Center, Shanghai, 200001, People's Republic of China.

出版信息

Cancer Manag Res. 2021 Apr 13;13:3235-3246. doi: 10.2147/CMAR.S295317. eCollection 2021.

DOI:10.2147/CMAR.S295317

PMID:33880066

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8053518/

Abstract

PURPOSE

Neoadjuvant chemoradiotherapy (nCRT) has become the standard treatment for locally advanced rectal cancer (LARC). However, the accuracy of traditional clinical indicators in predicting tumor response is poor. Recently, radiomics based on magnetic resonance imaging (MRI) has been regarded as a promising noninvasive assessment method. The present study was conducted to develop a model to predict the pathological response by analyzing the quantitative features of MRI and clinical risk factors, which might predict the therapeutic effects in patients with LARC as accurately as possible before treatment.

PATIENTS AND METHODS

A total of 82 patients with LARC were enrolled as the training cohort and internal validation cohort. The pre-CRT MRI after pretreatment was acquired to extract texture features, which was finally selected through the minimum redundancy maximum relevance (mRMR) algorithm. A support vector machine (SVM) was used as a classifier to classify different tumor responses. A joint radiomics model combined with clinical risk factors was then developed and evaluated by receiver operating characteristic (ROC) curves. External validation was performed with 107 patients from another center to evaluate the applicability of the model.

RESULTS

Twenty top image texture features were extracted from 6192 extracted-radiomic features. The radiomics model based on high-spatial-resolution T2-weighted imaging (HR-T2WI) and contrast-enhanced T1-weighted imaging (T1+C) demonstrated an area under the curve (AUC) of 0.8910 (0.8114-0.9706) and 0.8938 (0.8084-0.9792), respectively. The AUC value rose to 0.9371 (0.8751-0.9997) and 0.9113 (0.8449-0.9776), respectively, when the circumferential resection margin (CRM) and carbohydrate antigen 19-9 (CA19-9) levels were incorporated. Clinical usefulness was confirmed in an external validation cohort as well (AUC, 0.6413 and 0.6818).

CONCLUSION

Our study indicated that the joint radiomics prediction model combined with clinical risk factors showed good predictive ability regarding the treatment response of tumors as accurately as possible before treatment.

摘要

目的

新辅助放化疗（nCRT）已成为局部晚期直肠癌（LARC）的标准治疗方法。然而，传统临床指标预测肿瘤反应的准确性较差。近年来，基于磁共振成像（MRI）的放射组学被认为是一种很有前景的非侵入性评估方法。本研究旨在通过分析MRI的定量特征和临床危险因素来建立一个预测病理反应的模型，从而在治疗前尽可能准确地预测LARC患者的治疗效果。

患者和方法

共纳入82例LARC患者作为训练队列和内部验证队列。采集预处理后的CRT前MRI以提取纹理特征，最终通过最小冗余最大相关（mRMR）算法进行选择。使用支持向量机（SVM）作为分类器对不同的肿瘤反应进行分类。然后建立一个结合临床危险因素的联合放射组学模型，并通过受试者操作特征（ROC）曲线进行评估。使用来自另一个中心的107例患者进行外部验证，以评估该模型的适用性。

结果

从6192个提取的放射组学特征中提取了20个顶级图像纹理特征。基于高空间分辨率T2加权成像（HR-T2WI）和对比增强T1加权成像（T1+C）的放射组学模型的曲线下面积（AUC）分别为0.8910（0.8114-0.9706）和0.8938（0.8084-0.9792）。纳入环周切缘（CRM）和糖类抗原19-9（CA19-9）水平后，AUC值分别升至0.9371（0.8751-0.9997）和0.9113（0.8449-0.9776）。在外部验证队列中也证实了其临床实用性（AUC分别为0.6413和0.6818）。