Deep Learning Technique for Congenital Heart Disease Detection Using Stacking-Based CNN-LSTM Models from Fetal Echocardiogram: A Pilot Study
Author | Rahman, Tawsifur |
Author | Al-Ruweidi, Mahmoud Khatib A.A. |
Author | Sumon, Md Shaheenur Islam |
Author | Kamal, Reema Yousef |
Author | Chowdhury, Muhammad E.H. |
Author | Yalcin, Huseyin C. |
Available date | 2023-11-05T05:39:06Z |
Publication Date | 2023-01-01 |
Publication Name | IEEE Access |
Identifier | http://dx.doi.org/10.1109/ACCESS.2023.3316719 |
Citation | T. Rahman, M. K. A. A. Al-Ruweidi, M. S. I. Sumon, R. Y. Kamal, M. E. H. Chowdhury and H. C. Yalcin, "Deep Learning Technique for Congenital Heart Disease Detection Using Stacking-Based CNN-LSTM Models From Fetal Echocardiogram: A Pilot Study," in IEEE Access, vol. 11, pp. 110375-110390, 2023, doi: 10.1109/ACCESS.2023.3316719. |
Abstract | Congenital heart defects (CHDs) are a leading cause of death in infants under 1 year of age. Prenatal intervention can reduce the risk of postnatal serious CHD patients, but current diagnosis is based on qualitative criteria, which can lead to variability in diagnosis between clinicians. Objectives: To detect morphological and temporal changes in cardiac ultrasound (US) videos of fetuses with hypoplastic left heart syndrome (HLHS) using deep learning models. A small cohort of 9 healthy and 13 HLHS patients were enrolled, and ultrasound videos at three gestational time points were collected. The videos were preprocessed and segmented to cardiac cycle videos, and five different deep learning CNN-LSTM models were trained (MobileNetv2, ResNet18, ResNet50, DenseNet121, and GoogleNet). The top-performing three models were used to develop a novel stacking CNN-LSTM model, which was trained using five-fold cross-validation to classify HLHS and healthy patients. The stacking CNN-LSTM model outperformed other pre-trained CNN-LSTM models with the accuracy, precision, sensitivity, F1 score, and specificity of 90.5%, 92.5%, 92.5%, 92.5%, and 85%, respectively for video-wise classification, and with the accuracy, precision, sensitivity, F1 score, and specificity of 90.5%, 92.5%, 92.5%, 92.5%, and 85%, respectively for subject-wise classification using ultrasound videos. This study demonstrates the potential of using deep learning models to classify CHD prenatal patients using ultrasound videos, which can aid in the objective assessment of the disease in a clinical setting. |
Sponsor | This study was funded by Qatar National Research Fund (QNRF), National Priorities Research Program (NPRP 10-0123-170222). The open access publication of this article was funded by the Qatar National Library. |
Language | en |
Publisher | IEEE |
Subject | CNN-LSTM Congenital heart defects (CHDs) deep learning fetal echocardiogram hypoplastic left heart syndrome (HLHS) stacking machine learning |
Type | Article |
Pagination | 110375 - 110390 |
Volume Number | 11 |
ESSN | 2169-3536 |
Files in this item
This item appears in the following Collection(s)
-
Biomedical Research Center Research [727 items ]
-
Electrical Engineering [2616 items ]
-
Pharmacy Research [1261 items ]