Automated Fetal Femur Segmentation and Length Measurement in Ultrasound Images: A Key Tool for Accurate Gestational Age Assessment

Accurate gestational age (GA) estimation in the second and third trimesters is crucial for effective prenatal care. It is typically determined by measuring fetal femur length (FL) in ultrasound (US) images. However, manual FL measurements are time-consuming and require expertise, leading to the need for automation. This study aims to develop an automated multi-step approach to improve FL measurement accuracy while addressing common US challenges such as speckle noise, shadows, and low signal-to-noise ratio (SNR). The proposed method includes image acquisition, preprocessing for contrast enhancement, speckle noise reduction using a bilateral filter, k-means clustering for initial femur segmentation, and morphological analysis to isolate the femur for precise FL measurement. The approach achieved a Dice similarity coefficient of 93.18±9.54% and a mean measurement difference of 0.062 cm compared to manual assessments, with 95% limits of agreement from -1.06 cm to 1.19 cm, confirming its accuracy and clinical reliability. These results demonstrate that the proposed method enhances FL measurement accuracy, reduces manual workload, and contributes to more reliable GA estimation, making it a valuable tool for prenatal care.