Zobrazit v EDS

Preliminary Results on Automated Binary Classification of Congenital Heart Defects in Fetal Ultrasound Images Using Deep Learning Algorithm

Uloženo v:
Podrobná bibliografie
Název: Preliminary Results on Automated Binary Classification of Congenital Heart Defects in Fetal Ultrasound Images Using Deep Learning Algorithm
Autoři: Horvat, Marko, Božek, Jelena, Šarčević, Ana, Zmijanović, Ivan
Zdroj: 48th ICT and Electronics Convention MIPRO 2025. :1498-1503
Informace o vydavateli: 2025.
Rok vydání: 2025
Témata: Deep Learning, Congenital Heart Disease, Medical Image Analysis, Fetal Ultrasound, ResNet-18
Popis: Congenital heart defects (CHDs) are the most prevalent congenital anomalies, affecting approximately 0.8% of live births and representing the leading cause of neonatal mortality. More than 300 children are born annually with CHDs in Croatia, most undiagnosed before birth. Early fetal detection of CHDs using ultrasound significantly improves survival rates and enhances results through timely medical intervention. In this study, we explore the potential of artificial intelligence to improve fetal diagnostics of CHDs. The goal of this research is to apply a deep learning-based method to classify fetal ultrasound images as normal or indicative of CHDs. The dataset used in the experiment included N = 86 ultrasound images, comprising 57 images of normal hearts (from 23 fetuses) and 29 images of CHDs (from 8 fetuses). These images were obtained from routine prenatal gynecological examinations conducted in a general hospital in Croatia between the 18th and 22nd weeks of pregnancy. Data normalization and augmentation were performed to standardize the dataset and enhance its diversity. The ResNet-18 classifier was trained and validated using five-fold cross-validation, ensuring that images from the same fetus were not included in both training and validation sets to prevent data leakage. Preliminary results indicate that the proposed deep learning model achieves an accuracy of 74% in distinguishing normal fetal hearts from those with CHDs. Future work will focus on expanding the dataset, exploring alternative deep learning algorithms and techniques, and integrating post-hoc explainability methods to enhance the interpretability and clinical applicability of predictions for fetal CHDs.
Druh dokumentu: Conference object
ISSN: 1847-3946
Přístupové číslo: edsair.dris...01492..68c3c834b24f73041d5006aa98f0c51b
Databáze: OpenAIRE
Popis
Abstrakt:Congenital heart defects (CHDs) are the most prevalent congenital anomalies, affecting approximately 0.8% of live births and representing the leading cause of neonatal mortality. More than 300 children are born annually with CHDs in Croatia, most undiagnosed before birth. Early fetal detection of CHDs using ultrasound significantly improves survival rates and enhances results through timely medical intervention. In this study, we explore the potential of artificial intelligence to improve fetal diagnostics of CHDs. The goal of this research is to apply a deep learning-based method to classify fetal ultrasound images as normal or indicative of CHDs. The dataset used in the experiment included N = 86 ultrasound images, comprising 57 images of normal hearts (from 23 fetuses) and 29 images of CHDs (from 8 fetuses). These images were obtained from routine prenatal gynecological examinations conducted in a general hospital in Croatia between the 18th and 22nd weeks of pregnancy. Data normalization and augmentation were performed to standardize the dataset and enhance its diversity. The ResNet-18 classifier was trained and validated using five-fold cross-validation, ensuring that images from the same fetus were not included in both training and validation sets to prevent data leakage. Preliminary results indicate that the proposed deep learning model achieves an accuracy of 74% in distinguishing normal fetal hearts from those with CHDs. Future work will focus on expanding the dataset, exploring alternative deep learning algorithms and techniques, and integrating post-hoc explainability methods to enhance the interpretability and clinical applicability of predictions for fetal CHDs.
ISSN:18473946