Artificial Intelligence-based Estimation of Fetal Head Circumference with Biparietal and Occipitofrontal Diameters Using 2D Ultrasound Images

Abstract

Abstract One of the most essential biometrics for measuring fetal growth during prenatal ultrasound exams is the head circumference (HC). However, manual measurement of this biometric by doctors often needs substantial experience. We developed a state-of-the-art image processing algorithm that utilizes biometry and segmented image and employed a fast ellipse fitting method to measure the head circumference (HC), head orientation (angle) along with biparietal (BPD), and occipitofrontal (OFD) diameter automatically. Additionally, To the best of our knowledge, this is the first work that adopts a segmented image from any model or technique and provides significant fetal parameters during ultrasonography in a single shot. The suggested technique is lightweight, real-time, and easily integrate with any segmentation model or technique. We have used three well-known segmentation models for demonstration and compared their performance using dice scores as an evaluation parameter. Among the three, HRNET shows the best results with an average dice score of 0.96; due to the high dice score, we have chosen HRNET over the other two models and proceeded further and implemented our novel algorithm on that to predict the required fetal key measurements. The study's findings showed that our proposed technique estimates fetal head circumference along with biparietal and occipitofrontal diameter, which has significant use in fetal analysis and monitoring.