Automatic classification method for standard sections of fetus faces

Abstract

The invention provides an automatic classification method for a standard section of a fetal face in the field of ultrasonic image classification, and the method comprises the following steps: S10, obtaining a plurality of ultrasonic images of the fetal face, carrying out the preprocessing of each ultrasonic image, and respectively generating standard sections; S20, extracting textural features, including a local binary pattern and a direction gradient histogram, in the standard tangent plane; S30, performing Euclidean distance normalization on the texture features to obtain feature vectors; and S40, based on the feature vectors, learning and classifying the standard tangent planes by utilizing a support vector machine. The method has the advantages that the precision and efficiency of fetal face standard section classification are greatly improved, the clinical diagnosis efficiency is greatly improved, and the clinical diagnosis cost is reduced.

Description

technical field [0001] The invention relates to the field of ultrasonic image classification, in particular to an automatic classification method for standard sections of the fetal face. Background technique [0002] The objects of medical ultrasound images are mainly different levels of human physiological tissues and structures, ranging from molecules and atoms at the micro level to human organs at the macro level. Compared with ordinary images, the standard section of the fetal face of medical ultrasound images is a good section for observing the contour of the fetus's face and screening for various fetal cleft lips. Many abnormalities of the lips and face are clearly displayed on the standard section of the fetal face, such as Retruded forehead, protruding forehead, flat forehead, no nose, split nose, proboscis and oblique cleft deformities. [0003] In recent years, with the popularity of prenatal diagnosis, ultrasound imaging has been widely used due to its advantages...

Images