Automatic evaluation of fetal head biometry from ultrasound images using machine learning

TL;DR

This paper presents a deep learning approach for automatic fetal head biometry from ultrasound images, achieving high accuracy and reliability in measuring head circumference and biparietal diameter, thus reducing operator dependency.

Contribution

It introduces a novel deep learning method that effectively identifies fetal head boundaries and estimates biometric measurements with improved accuracy over existing automated techniques.

Findings

92.31% success rate for HC and BPD estimation

87.14% accuracy in plane acceptance check

Effective differentiation of tissue patterns in ultrasound images

Abstract

Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are commonly used to evaluate the gestational age and diagnose fetal central nervous system (CNS) pathology. Since manual measurements are operator-dependent and time-consuming, there have been numerous researches on automated methods. However, existing automated methods still are not satisfactory in terms of accuracy and reliability, owing to difficulties in dealing with various artifacts in ultrasound images. This paper focuses on fetal head biometry and develops a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability. The proposed method effectively identifies the head boundary by differentiating tissue image patterns with respect to the ultrasound propagation direction. The proposed method was trained with 102 labeled data set and tested to 70 ultrasound images. We achieved a success rate of 92.31% for HC and BPD estimations, and an accuracy of 87.14 % for the plane acceptance check.