论文部分内容阅读
In this paper,we propose a new method to evaluate the placental maturity by feature fusion and discriminative learning.Specifically,we extract feature not only from B-mode grayscale ultrasound(US)images,but also from color Doppler energy(CDE)images.We extract both the gray-scale intensity and blood flow information by the visual feature detector and descriptor.After fusing information,we apply the feature encoding method to improve the staging performance using discriminative learning technique.Instead of using traditional Fisher vector(FV),we develop a multi-layout FV(MFV)for spatial information extraction.Experimental results show that the proposed method has achieved promising performance for placental maturity staging and outperformed the traditional methods.