基于深度学习的胰腺黏液性和浆液性囊性肿瘤的多源特征分类模型

徐真顺,袁小涵,黄子珩,邵成伟,武杰,边云

Multi-source Feature Classification Model of Pancreatic Mucinous and Serous Cystic Neoplasms Based on Deep Learning

XU Zhenshun,YUAN Xiaohan,HUANG Ziheng,SHAO Chengwei,WU Jie,BIAN Yun

图4 4个特征模型以及各分类器的ROC曲线.横坐标是假阳性率（fpr），纵坐标是真阳性率（tpr），4个分类器分别为SVM（支持向量机）、ADAboost（自适应提升算法）、Random Forest（随机森林）以及Logistic（逻辑回归）.(a) RAD特征模型的ROC曲线；(b) DL特征模型的ROC曲线；(c) RAD_DL特征模型的ROC曲线；(d) Clinical_RAD_DL特征模型的ROC曲线

Fig. 4 ROC curve of four characteristic models. The abscissa is fpr (false positive rate) and the ordinate is tpr (true positive rate). The four classifiers are SVM, adaboost (ADAboost), randomforest (Random Forest) and logistic (Logistic). (a) ROC curve used by RAD feature model; (b) ROC curve of DL feature model; (c) ROC curve of RAD_DL feature model; (d) ROC curve of Clinical _RAD_DL feature model