磁共振成像2025，Vol.16Issue(10)：60-67,8.DOI:10.12015/issn.1674-8034.2025.10.010
基于深度学习分割肿瘤区域的影像组学特征预测直肠癌区域淋巴结状态
Prediction of regional lymph node status in rectal cancer with radiomics features based on deep learning segmented tumor area
摘要
Abstract
Objective:To predict regional lymph node metastasis(LNM)in rectal cancer(RC)using deep learning-based tumor auto-segmentation and radiomics.Materials and Methods:This single-center research retrospectively analyzed T2WI and DWI of 282 rectal cancers from two MR scanners.The deep learning-based auto-segmentation models were constructed on T2WI and DWI with 3D U-Net,3D V-Net,and nnU-Net v2 and assessed with the dice similarity coefficient(DSC).Radiomics features on manual-based volume of interest(MbV)and deep learning-based volume of interest(DbV,with the highest DSC)were extracted respectively.After feature normalization and selection,five machine learning algorithms were used for radiomics model building and then for LNM prediction.The optimal model was evaluated with area under the curve(AUC),accuracy,specificity,and sensitivity.Results:The DSC of the nnU-Net v2 was significantly higher than that of the 3D U-Net and 3D V-Net(T2WI:0.886 vs.0.548 vs.0.616,P<0.001;DWI:0.906 vs.0.583 vs.0.433,P<0.001)in test set.The AUC of DbV based-radiomics models constructed with logistic regression algorithm were comparable to those of the corresponding MbV-based radiomics models(T2WI:0.700 vs.0.633,P=0.638;DWI:0.667 vs.0.700,P=0.544;T2WI+DWI:0.800 vs.0.833,P=0.248)in LNM prediction in validation set.Conclusions:Radiomics features of T2WI and DWI based on nnU-net v2 segmented tumor area showed a reliable performance in predicting LNM in RC.关键词
直肠癌/深度学习/影像组学/磁共振成像/淋巴结转移Key words
rectal cancer/deep learning/radiomics/magnetic resonance imaging/lymph node metastasis分类
医药卫生引用本文复制引用
赵婉婷,李婉清,郝勇飞,乔小爱,侯国瑞,杜少华,张广文,张劲松..基于深度学习分割肿瘤区域的影像组学特征预测直肠癌区域淋巴结状态[J].磁共振成像,2025,16(10):60-67,8.基金项目
National Natural Science Foundation of China(No.82371918) （No.82371918）
Xijing Hospital Clinical New Technology Projects(No.2024XJSY43). 国家自然科学基金项目(编号:82371918) （No.2024XJSY43）
西京医院临床新技术项目(编号:2024XJSY43) （编号:2024XJSY43）
