Automatic placental maturity grading via hybrid learning

详细信息    查看全文

• 作者：Baiying Lei^aAuthor Vitae ; Ee-Leng Tan^b ; ¹Author Vitae ; Siping Chen^aAuthor Vitae ; Wanjun Li^aAuthor Vitae ; Dong Ni^aAuthor Vitae ; Yuan Yao^c ; ^{yaoyuan90@126.com}Author Vitae ; Tianfu Wang^a ; ^{tfwang@szu.edu.cn}Author Vitae
• 关键词：Placental maturity evaluation ; Pyramidal descriptor ; Deep feature training ; Hybrid learning ; Normalization
• 刊名：Neurocomputing
• 出版年：2017
• 出版时间：5 February 2017
• 年：2017
• 卷：223
• 期：Complete
• 页码：86-102
• 全文大小：2604 K
• 卷排序：223

文摘

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.