BiometryNet: Landmark-based Fetal Biometry Estimation from Standard Ultrasound Planes
This work addresses the time-consuming and operator-dependent variability in fetal growth assessment for clinical ultrasound practitioners, representing a strong domain-specific improvement rather than a foundational advance.
The paper tackles the problem of manual fetal biometry estimation from ultrasound images by introducing BiometryNet, an end-to-end landmark regression framework that directly estimates biometric measurements without segmentation. The method achieves errors lower than clinically permissible thresholds and outperforms existing automated methods on a dataset of 3,398 images from multiple clinical sites and devices.
Fetal growth assessment from ultrasound is based on a few biometric measurements that are performed manually and assessed relative to the expected gestational age. Reliable biometry estimation depends on the precise detection of landmarks in standard ultrasound planes. Manual annotation can be time-consuming and operator dependent task, and may results in high measurements variability. Existing methods for automatic fetal biometry rely on initial automatic fetal structure segmentation followed by geometric landmark detection. However, segmentation annotations are time-consuming and may be inaccurate, and landmark detection requires developing measurement-specific geometric methods. This paper describes BiometryNet, an end-to-end landmark regression framework for fetal biometry estimation that overcomes these limitations. It includes a novel Dynamic Orientation Determination (DOD) method for enforcing measurement-specific orientation consistency during network training. DOD reduces variabilities in network training, increases landmark localization accuracy, thus yields accurate and robust biometric measurements. To validate our method, we assembled a dataset of 3,398 ultrasound images from 1,829 subjects acquired in three clinical sites with seven different ultrasound devices. Comparison and cross-validation of three different biometric measurements on two independent datasets shows that BiometryNet is robust and yields accurate measurements whose errors are lower than the clinically permissible errors, outperforming other existing automated biometry estimation methods. Code is available at https://github.com/netanellavisdris/fetalbiometry.