Related Experiment Video
Updated: Aug 22, 2025
Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
Published on: May 5, 2018
Deep Learning for Improving the Effectiveness of Routine Prenatal Screening for Major Congenital Heart Diseases
Siti Nurmaini1, Radiyati Umi Partan2, Nuswil Bernolian3
1Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang 30139, Indonesia.
Insights
Deep learning models can now automatically screen fetal ultrasounds for congenital heart diseases (CHDs), improving diagnostic accuracy and supporting clinicians in early detection to reduce newborn mortality.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Cardiology
Background:
- Congenital heart diseases (CHDs) are a leading cause of newborn mortality.
- Early prenatal screening via ultrasound (US) is crucial but limited by expert availability and case volume.
- Automated screening tools are needed to enhance diagnostic capabilities.
Purpose of the Study:
- To evaluate deep learning (DL) techniques for automated diagnosis of CHDs in fetal US.
- To identify the optimal DL architecture for classifying various CHDs and normal cases.
Main Methods:
- Comparison of four convolutional neural network architectures.
- Selection and implementation of DenseNet201 for classifying seven CHDs and a normal control.
- Validation of the DL model against expert fetal cardiologist predictions.
Main Results:
- DenseNet201 achieved high sensitivity, specificity, and accuracy (100% intra-patient, 99%, 97%, 98% inter-patient).
- The DL model's performance was comparable to expert cardiologists.
- The model demonstrated potential for supporting clinical decision-making in CHD diagnostics.
Conclusions:
- Automated DL-based screening of fetal US for CHDs is feasible and effective.
- This technology can assist front-line sonographers and improve population-level CHD diagnosis.
- The developed model shows promise in enhancing early detection and reducing mortality from CHDs.
Abstract:
Early prenatal screening with an ultrasound (US) can significantly lower newborn mortality caused by congenital heart diseases (CHDs). However, the need for expertise in fetal cardiologists and the high volume of screening cases limit the practically achievable detection rates. Hence, automated prenatal screening to support clinicians is desirable. This paper presents and analyses potential deep learning (DL) techniques to diagnose CHDs in fetal USs. Four convolutional neural network architectures were compared to select the best classifier with satisfactory results. Hence, dense convolutional network (DenseNet) 201 architecture was selected for the classification of seven CHDs, such as ventricular septal defect, atrial septal defect, atrioventricular septal defect, Ebstein's anomaly, tetralogy of Fallot, transposition of great arteries, hypoplastic left heart syndrome, and a normal control. The sensitivity, specificity, and accuracy of the DenseNet201 model were 100%, 100%, and 100%, respectively, for the intra-patient scenario and 99%, 97%, and 98%, respectively, for the inter-patient scenario. We used the intra-patient DL prediction model to validate our proposed model against the prediction results of three expert fetal cardiologists. The proposed model produces a satisfactory result, which means that our model can support expert fetal cardiologists to interpret the decision to improve CHD diagnostics. This work represents a step toward the goal of assisting front-line sonographers with CHD diagnoses at the population level.
