Multi-Task Learning Approach for Unified Biometric Estimation from Fetal Ultrasound Anomaly Scans

TL;DR

This paper introduces a multi-task learning model that simultaneously classifies fetal ultrasound regions and estimates biometric parameters, achieving high accuracy and low error rates, thus improving automated fetal biometry analysis.

Contribution

The study presents a novel multi-task learning framework combining classification and segmentation for fetal biometric estimation from ultrasound images.

Findings

Achieved mean absolute errors of 1.08 mm for head circumference

Achieved mean absolute errors of 1.44 mm for abdomen circumference

Classification accuracy of 99.91% on fetal ultrasound dataset

Abstract

Precise estimation of fetal biometry parameters from ultrasound images is vital for evaluating fetal growth, monitoring health, and identifying potential complications reliably. However, the automated computerized segmentation of the fetal head, abdomen, and femur from ultrasound images, along with the subsequent measurement of fetal biometrics, remains challenging. In this work, we propose a multi-task learning approach to classify the region into head, abdomen and femur as well as estimate the associated parameters. We were able to achieve a mean absolute error (MAE) of 1.08 mm on head circumference, 1.44 mm on abdomen circumference and 1.10 mm on femur length with a classification accuracy of 99.91\% on a dataset of fetal Ultrasound images. To achieve this, we leverage a weighted joint classification and segmentation loss function to train a U-Net architecture with an added classification head. The code can be accessed through \href{https://github.com/BioMedIA-MBZUAI/Multi-Task-Learning-Approach-for-Unified-Biometric-Estimation-from-Fetal-Ultrasound-Anomaly-Scans.git}{\texttt{Github}