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. Manual measurement of fetal head circumference during prenatal ultrasound exams requires significant expertise, posing limitations in accuracy and consistency, which can impact clinical decision-making and fetal health assessments. We developed a state-of-the-art image processing algorithm that utilizes biometry and segmented images and employed a fast ellipse fitting method to measure the HC, head orientation (angle) along with biparietal (BPD), and occipitofrontal (OFD) diameter automatically. Our approach offers automation and precision in measuring fetal biometrics, surpassing the limitations of manual measurement by ensuring consistent and accurate assessments, thus enhancing clinical efficiency and facilitating timely interventions for optimal fetal health management. 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 findings of this study benefit prenatal care by enhancing the accuracy and efficiency of fetal biometric measurements, thereby facilitating improved clinical decision-making and optimizing fetal health assessments.
Read full abstract