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

2025-06-25

AI Summary

This study addresses the clinical challenges of manual, operator-dependent, and time-consuming gestational age (GA) estimation from fetal ultrasound images. We propose a fully automated GA estimation method that requires no manual annotations. Our approach introduces a novel multimodal fusion framework integrating radiomics features with deep learning representations: a pre-trained CNN extracts global high-level semantic features, while interpretable radiomics features are concurrently derived from fetal brain structures; an adaptive weighting strategy enables robust cross-trimester feature fusion. Evaluated on multicenter data, our model achieves a mean absolute error of 8.0 days—significantly outperforming existing machine learning methods—and demonstrates strong generalizability and robustness across diverse geographic populations. This work provides a reliable, efficient, and clinically deployable tool for precision prenatal assessment.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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}{GitHub}.

Problem

• Estimating gestational age accurately from fetal ultrasound images
• Reducing operator-dependent manual fetal biometric measurements
• Combining radiomic features and deep learning for improved GA estimation

Innovation

• Fuses radiomic and deep learning features
• Estimates gestational age without manual measurements
• Achieves 8.0 days mean absolute error