Rong Chang, Zhu Chao, He Li, Hu Jing, Gao Yankun, Li Cuiping, Qian Baoxin, Li Jianying, Wu Xingwang
Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei 230022, People's Republic of China (C.R., C.Z., L.H., Y.G., C.L., X.W.).
Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei 230022, People's Republic of China (C.R., C.Z., L.H., Y.G., C.L., X.W.); Department of Radiology, The Lu'an People's Hospital, Lu'an, Anhui 237000, People's Republic of China (L.H.).
Acad Radiol. 2023 Sep;30 Suppl 1:S199-S206. doi: 10.1016/j.acra.2023.04.022. Epub 2023 May 18.
To develop computed tomography enterography (CTE)-based radiomics models to assess mucosal healing (MH) in patients with Crohn's disease (CD).
CTE images were retrospectively collected from 92 confirmed cases of CD at the post-treatment review. Patients were randomly divided into developing (n = 73) and testing (n = 19) groups. Radiomics features were extracted from the enteric phase images, and the least absolute shrinkage and selection operator (LASSO) logistic regression was applied for feature selection using 5-fold cross-validation on the developing group. The selected features were further identified from the top-ranked features and used to create improved radiomics models. Machine learning models were constructed to compare radiomics models with different radiomics features. The area under the ROC curve (AUC) was calculated to assess the predictive performance for identifying MH in CD.
Among the 92 CD patients included in our study, 36 patients achieved MH. The AUC of the radiomics model 1, which was based on the 26 selected radiomics features, was 0.976 for evaluating MH in the testing cohort. The AUCs of radiomics models 2 and 4, based on the top 10 and top 5 positive and negative radiomics features, were 0.974 and 0.952 in the testing cohort, respectively. The AUC of the radiomics model 3, built by removing features with r > 0.5, was 0.956 in the testing cohort. The clinical utility of the clinical radiomics nomogram was confirmed by the decision curve analysis (DCA).
The CTE-based radiomics models have demonstrated favorable performance in assessing MH in patients with CD. Radiomics features can be used as a promising imaging biomarker for MH.
开发基于计算机断层扫描小肠造影（CTE）的放射组学模型，以评估克罗恩病（CD）患者的黏膜愈合（MH）情况。
回顾性收集92例确诊为CD的患者在治疗后复查时的CTE图像。患者被随机分为建模组（n = 73）和验证组（n = 19）。从小肠期图像中提取放射组学特征，并在建模组中使用最小绝对收缩和选择算子（LASSO）逻辑回归结合五折交叉验证进行特征选择。从排名靠前的特征中进一步筛选出选定特征，用于创建改进的放射组学模型。构建机器学习模型，比较具有不同放射组学特征的放射组学模型。计算ROC曲线下面积（AUC），以评估识别CD患者MH的预测性能。
在我们纳入研究的92例CD患者中，36例实现了MH。基于26个选定放射组学特征的放射组学模型1在验证队列中评估MH的AUC为0.976。基于前10个和前5个正负放射组学特征的放射组学模型2和4在验证队列中的AUC分别为0.974和0.952。通过去除r>0.5的特征构建的放射组学模型3在验证队列中的AUC为0.956。决策曲线分析（DCA）证实了临床放射组学列线图的临床实用性。
基于CTE的放射组学模型在评估CD患者的MH方面表现出良好性能。放射组学特征可作为一种有前景的MH成像生物标志物。
