Fusing Radiomic Features with Deep Representations for Gestational Age Estimation in Fetal Ultrasound Images

TL;DR

This paper introduces a novel feature fusion framework combining radiomic features and deep representations to estimate gestational age from fetal ultrasound images, achieving high accuracy without manual measurements.

Contribution

The study presents a new method that fuses radiomic features with deep learning representations for automatic gestational age estimation from ultrasound images.

Findings

Achieves a mean absolute error of 8.0 days across trimesters.

Outperforms existing machine learning methods in gestational age estimation.

Demonstrates robustness across diverse populations.

Abstract

Accurate gestational age (GA) estimation, ideally through fetal ultrasound measurement, is a crucial aspect of providing excellent antenatal care. However, deriving GA from manual fetal biometric measurements depends on the operator and is time-consuming. Hence, automatic computer-assisted methods are demanded in clinical practice. In this paper, we present a novel feature fusion framework to estimate GA using fetal ultrasound images without any measurement information. We adopt a deep learning model to extract deep representations from ultrasound images. We extract radiomic features to reveal patterns and characteristics of fetal brain growth. To harness the interpretability of radiomics in medical imaging analysis, we estimate GA by fusing radiomic features and deep representations. Our framework estimates GA with a mean absolute error of 8.0 days across three trimesters, outperforming current machine learning-based methods at these gestational ages. Experimental results demonstrate the robustness of our framework across different populations in diverse geographical regions. Our code is publicly available on \href{https://github.com/13204942/RadiomicsImageFusion_FetalUS}.