Related Experiment Video
Updated: Jul 31, 2025
State of the Art Cranial Ultrasound Imaging in Neonates
Published on: February 2, 2015
White matter injury detection based on preterm infant cranial ultrasound images
Juncheng Zhu1, Shifa Yao2,3, Zhao Yao1
1School of Information Science and Technology, Fudan University, Shanghai, China.
Insights
A new ultrasound radiomics system accurately predicts white matter injury (WMI) risk in preterm infants. This AI-driven approach aids in early detection, potentially preventing conditions like cerebral palsy.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neonatology
Background:
- White matter injury (WMI) is a leading cause of cerebral palsy in preterm infants.
- Current diagnostic methods for WMI lack precision and timeliness.
- Periventricular leuko-malacia (PVL) is a severe consequence of WMI.
Purpose of the Study:
- To develop an automated diagnostic system for evaluating WMI risk in preterm infants using cranial ultrasound images.
- To enhance early detection and management of WMI.
- To improve long-term outcomes for preterm infants.
Main Methods:
- Development of an ultrasound radiomics diagnostic system.
- Implementation of a multi-task deep learning model for simultaneous white matter segmentation and WMI risk prediction.
- Analysis of 807 cranial ultrasound images from 158 preterm infants.
Main Results:
- The ultrasound radiomics system achieved an AUC of 0.845 for WMI risk prediction.
- The deep learning model demonstrated strong performance in white matter segmentation (Dice coefficient 0.78) and WMI risk prediction (AUC 0.863).
- WMI was identified in 20.3% of the enrolled preterm infants.
Conclusions:
- A data-driven diagnostic system combining multi-task deep learning and radiomics shows promise for WMI detection.
- The system offers stable and efficient diagnostic performance for WMI in preterm infants.
- This approach facilitates automatic detection of white matter abnormalities and risk stratification.
Introduction:
White matter injury (WMI) is now the major disease that seriously affects the quality of life of preterm infants and causes cerebral palsy of children, which also causes periventricular leuko-malacia (PVL) in severe cases. The study aimed to develop a method based on cranial ultrasound images to evaluate the risk of WMI.
Methods:
This study proposed an ultrasound radiomics diagnostic system to predict the WMI risk. A multi-task deep learning model was used to segment white matter and predict the WMI risk simultaneously. In total, 158 preterm infants with 807 cranial ultrasound images were enrolled. WMI occurred in 32preterm infants (20.3%, 32/158).
Results:
Ultrasound radiomics diagnostic system implemented a great result with AUC of 0.845 in the testing set. Meanwhile, multi-task deep learning model preformed a promising result both in segmentation of white matter with a Dice coefficient of 0.78 and prediction of WMI risk with AUC of 0.863 in the testing cohort.
Discussion:
In this study, we presented a data-driven diagnostic system for white matter injury in preterm infants. The system combined multi-task deep learning and traditional radiomics features to achieve automatic detection of white matter regions on the one hand, and design a fusion strategy of deep learning features and manual radiomics features on the other hand to obtain stable and efficient diagnostic performance.
More Related Videos
05:52Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy
Published on: October 28, 2022
06:36Author Spotlight: High-Resolution Imaging of Mouse Neonate Brains – A Micro-CT Protocol with Lugol's Solution Contrast Agent
Published on: May 19, 2023