Automatic placental maturity grading via hybrid learning

Fetal viability, gestational age, and complicated image processing have made evaluating placental maturity a tedious and time-consuming task. Despite various developments, automatic placental maturity still remains as a challenging issue. To address this issue, we propose a new method to automatically grade placental maturity from B-mode ultrasound (BUS) and color Doppler energy (CDE) images based on a hybrid learning architecture. We also apply an improved pyramidal shift invariant feature transform (IPSIFT) descriptor using a coarse-to-fine scale representation for visual feature extraction. These local features are then clustered by a generative Gaussian mixture model (GMM) to incorporate high order statistics. Next, the clustering representatives are encoded and aggregated via Fisher vector (FV). Instead of using traditional FV, an end-to-end deep training strategy is developed to fine-tune the GMM parameters to boost evaluation performance. A multi-view fusion technique is also developed for feature complementarity exploration. Extensive experimental results demonstrate that our method delivers promising performance in placental maturity evaluation and outperforms competing methods.