Multi-modal and multi-layout discriminative learning for placental maturity staging

To address this issue, we extract features not only from B-mode gray-scale ultrasound (US) images, but also from color Doppler energy (CDE) images. Based on these features, we propose a method to automatically determine the placental maturity by harnessing multi-view and multi-layout discriminative learning fusion. Specifically, we devise a multi-view technique to generate features of complementary information. Scale invariant features are extracted from image locally, and a Gaussian mixture model (GMM) is then applied to summarize the high-level information features. The clustering representatives from GMM are encoded via a multi-layout Fisher vector (MFV) instead of traditional Fisher vector (FV) to aggregate features based on their spatial information. We apply a multi-layout feature encoding method to improve the staging performance using discriminative learning technique. Extensive experimental results demonstrate that our method achieves promising performance in placental maturity staging and outperforms existing methods.