Automatic Recognition of Fetal Facial Standard Plane in Ultrasound Image via Fisher Vector

• Published in: PloS one Vol. 10; no. 5; p. e0121838
• Main Authors: Lei, Baiying, Tan, Ee-Leng, Chen, Siping, Zhuo, Liu, Li, Shengli, Ni, Dong, Wang, Tianfu
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.05.2015; Public Library of Science (PLoS)
• Subjects: Algorithms; Artificial intelligence; Biomedical engineering; Classification; Coding; Engineering; Face - anatomy & histology; Face recognition; Feature extraction; Fetuses; Humans; Image acquisition; Image retrieval; Information processing; International conferences; Laboratories; Mathematical programming; Medicine; Object recognition; Pattern recognition; Pattern Recognition, Automated - methods; Planes; Principal Component Analysis; ROC Curve; Spatial data; Stochasticity; Support vector machines; Ultrasonic imaging; Ultrasonics - methods; Ultrasonography, Prenatal - methods; Ultrasound
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0121838

Acquisition of the standard plane is the prerequisite of biometric measurement and diagnosis during the ultrasound (US) examination. In this paper, a new algorithm is developed for the automatic recognition of the fetal facial standard planes (FFSPs) such as the axial, coronal, and sagittal planes. Specifically, densely sampled root scale invariant feature transform (RootSIFT) features are extracted and then encoded by Fisher vector (FV). The Fisher network with multi-layer design is also developed to extract spatial information to boost the classification performance. Finally, automatic recognition of the FFSPs is implemented by support vector machine (SVM) classifier based on the stochastic dual coordinate ascent (SDCA) algorithm. Experimental results using our dataset demonstrate that the proposed method achieves an accuracy of 93.27% and a mean average precision (mAP) of 99.19% in recognizing different FFSPs. Furthermore, the comparative analyses reveal the superiority of the proposed method based on FV over the traditional methods.