基于3D ResNet50改进模型的TOF-MRA脑动脉瘤分类方法

薛培阳, 耿辰, 李郁欣, 鲍奕仿, 鲁宇澄, 戴亚康

A Classification Method for Cerebral Aneurysms in TOF-MRA Based on Improved 3D ResNet50 Model

XUE Peiyang, GENG Chen, LI Yuxin, BAO Yifang, LU Yucheng, DAI Yakang

图6 PMAF-Net与其他网络模型的ROC曲线.黑色对角线表示一个完全随机的分类器表现，其余分别为ResNet18（红色）、ResNet50（绿色）、DenseNet（蓝色）、MobileNet（橙色）、EfficientNet（紫色）和PMAF-Net（棕色）的ROC曲线

Fig. 6 ROC curves of PMAF-Net compared with other network models. The black diagonal line represents the performance of a completely randomized classifier, and the rest are the ROC curves for ResNet18 (red), ResNet50 (green), DenseNet (blue), MobileNet (orange), EfficientNet (purple), and PMAF-Net (brown), respectively