基于全局和局部特征信息的生成对抗网络在海马体分割中的应用
魏志宏, 孔旭东, 孔燕, 闫士举, 丁阳, 魏贤顶, 孔栋, 杨波

Application of Generative Adversarial Networks Based on Global and Local Feature Information in Hippocampus Segmentation
WEI Zhihong, KONG Xudong, KONG Yan, YAN Shiju, DING Yang, WEI Xianding, KONG Dong, YANG Bo
表5 不同方法的分割性能表
Table 5 Segmentation performance of different methods
方法 Dice IOU
u-net[17] 0.631 0.461
GGAN(u-net) 0.716 0.558
GGAN(v-net) 0.678 0.513
GLGAN(本文方法) 0.804 0.672