Objectives

To propose multiparametric MRI-based machine learning models and assess their ability to preoperatively predict rectal adenoma with canceration.

Materials and methods

A total of 53 patients with postoperative pathology confirming rectal adenoma (n = 29) and adenoma with canceration (n = 24) were enrolled in this retrospective study. All patients were divided into a training cohort (n = 42) and a test cohort (n = 11). All patients underwent preoperative pelvic MR examination, including high-resolution T2-weighted imaging (HR-T2WI) and diffusion-weighted imaging (DWI). A total of 1396 radiomics features were extracted from the HR-T2WI and DWI sequences, respectively. The least absolute shrinkage and selection operator (LASSO) was utilized for feature selection from the radiomics feature sets from the HR-T2WI and DWI sequences and from the combined feature set with 2792 radiomics features incorporating two sequences. Five-fold cross-validation and two machine learning algorithms (logistic regression, LR; support vector machine, SVM) were utilized for model construction in the training cohort. The diagnostic performance of the models was evaluated by sensitivity, specificity and area under the curve (AUC) and compared with the Delong’s test.

Results

Ten, 8, and 25 optimal features were selected from 1396 HR-T2WI, 1396 DWI and 2792 combined features, respectively. Three group models were constructed using the selected features from HR-T2WI (Model_T2), DWI (Model_DWI) and the two sequences combined (Model_combined). Model_combined showed better prediction performance than Model_T2 and Model_DWI. In Model_combined, there was no significant difference between the LR and SVM algorithms (p = 0.4795), with AUCs in the test cohort of 0.867 and 0.900, respectively.

Conclusions

Multiparametric MRI-based machine learning models have the potential to predict rectal adenoma with canceration. Compared with Model_T2 and Model_DWI, Model_combined showed the best performance. Moreover, both LR and SVM have equal excellent performance for model construction.

中文翻译：

---

基于多参数 MRI 的机器学习模型用于术前预测直肠腺瘤癌变

目标

提出基于多参数 MRI 的机器学习模型并评估其术前预测直肠腺瘤癌变的能力。

材料和方法

共有 53 名术后病理证实为直肠腺瘤 ( n  = 29) 和癌变的腺瘤 ( n  = 24) 患者参加了这项回顾性研究。所有患者被分为训练队列 ( n  = 42) 和测试队列 ( n = 11）。所有患者均接受术前盆腔 MR 检查，包括高分辨率 T2 加权成像（HR-T2WI）和弥散加权成像（DWI）。分别从 HR-T2WI 和 DWI 序列中提取了总共 1396 个放射组学特征。最小绝对收缩和选择算子 (LASSO) 用于从 HR-T2WI 和 DWI 序列的放射组学特征集中以及从包含两个序列的 2792 个放射组学特征的组合特征集中进行特征选择。五折交叉验证和两种机器学习算法（逻辑回归，LR；支持向量机，SVM）用于训练队列中的模型构建。模型的诊断性能通过敏感性、特异性和曲线下面积 (AUC) 进行评估，并与 Delong 检验进行比较。

结果

分别从 1396 个 HR-T2WI、1396 个 DWI 和 2792 个组合特征中选择了 10、8 和 25 个最优特征。使用从 HR-T2WI（模型_T2）、DWI（模型_DWI）和两个序列组合（模型_组合）中选择的特征构建三组模型。模型_组合显示出比模型_T2和模型_DWI更好的预测性能。在模型_组合中，LR 和 SVM 算法之间没有显着差异（p  = 0.4795），测试队列中的 AUC 分别为 0.867 和 0.900。

结论

基于多参数 MRI 的机器学习模型有可能预测直肠腺瘤癌变。与模型_T2和模型_DWI相比，模型_组合表现出最好的性能。此外，LR 和 SVM 在模型构建方面都具有同样出色的性能。