Siam Tahsin Bhuiyan
- Intern, CCDS
Bachelors
Independent University, Bangladesh
Published at
Scientific Reports
Conference Paper2025
Effect of Augmentations on CNN Based Models for Congenital Heart Disease Detection from Chest X-Rays
Sauharda Sarkar, Farha Yesmin, Md Abrar Sayed Tasin, Fatin Israq, Siam Tahsin Bhuiyan, Rashedur Rahman, Saadia Binte Alam, Ashraful Islam
2025 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE)
IEEE, pp. 438-443
Abstract
Congenital heart disease is one of the most common cardiovascular diseases, and its early detection is critical for effective treatment. Although chest X-ray imaging is affordable and accessible in both rural and urban health centers, manual interpretation for the diagnosis of CHD is challenging and prone to incorrect diagnoses. In this study, we classify chest X-ray images into four classes: normal, atrial septal defect (ASD), ventricular septal defect (VSD), and patent ductus arteriosus (PDA) based on deep learning models. A publicly available Kaggle competition dataset was used in our study, which consists of 828 X-ray images. Four Convolutional Neural Network (CNN) models are trained and evaluated. Experimental results show that EfficientNetB1 with moderate augmentation achieved the highest test accuracy of 69.51 %, followed by DenseNet121 with 66.46 %, while MobileNetV2 yielded the worst performance at$\mathbf{6 0. 9 8 \%}$. These findings show the augmentation effect on deep learning models for automated CHD detection from chest X-ray images.
Keywords
- ventricular septal defect
- patent ductus arteriosus
- MobileNetV2
- DenseNet121
- EfficientNet-B1
- congenital heart disease
- atrial septal defect
- chest radiography
- convolutional neural networks
- automated diagnosis
CCDS Authors
Md. Rashedur Rahman, D. Eng.
- Co-Director, MIRA & NEST Wings
Assistant Professor
Department of Computer Science and Engineering
Independent University, Bangladesh
Published at
CHI, HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications
Saadia Binte Alam, PhD
- Director, MIRA & WiSE Wings
Associate Professor
Department of Computer Science and Engineering
Independent University, Bangladesh
Published at
HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications
Ashraful Islam, PhD
- Center Director, CCDS
- Director, HCI Wing
Assistant Professor
Department of Computer Science and Engineering
Independent University, Bangladesh (IUB)Published at
CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE
Research Interests
Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact
References
- 1.Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. (2016). Deep Residual Learning for Image Recognition. , 770–778[10.1109/cvpr.2016.90]
- 2.Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q. Weinberger. (2017). Densely Connected Convolutional Networks. , 2261–2269[10.1109/cvpr.2017.243]
- 3.Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. , 4510–4520[10.1109/cvpr.2018.00474]
- 4.Jintai Chen, Shuai Huang, Ying Zhang, Qing Chang, Yixiao Zhang, Dantong Li, Jia Qiu, Lianting Hu, Xiaoting Peng, Yunmei Du, Yunfei Gao, Danny Z. Chen, Abdelouahab Bellou, Jian Wu, Huiying Liang. (2024). Congenital heart disease detection by pediatric electrocardiogram based deep learning integrated with human concepts. Nature Communications, 15(1), 976[10.1038/s41467-024-44930-y]
- 5.Saeed Karimi-Bidhendi, Arghavan Arafati, Andrew L. Cheng, Yilei Wu, Arash Kheradvar, Hamid Jafarkhani. (2020). Fully‑automated deep‑learning segmentation of pediatric cardiovascular magnetic resonance of patients with complex congenital heart diseases. Journal of Cardiovascular Magnetic Resonance, 22(1), 80[10.1186/s12968-020-00678-0]
- 6.Xusheng Jiang, Jin Yu, Jingjing Ye, Weijie Jia, Weize Xu, Qiang Shu. (2023). A deep learning-based method for pediatric congenital heart disease detection with seven standard views in echocardiography. World Journal of Pediatric Surgery, 6(3), e000580[10.1136/wjps-2023-000580]
- 7.Xiaowei Xu, Tianchen Wang, Jian Zhuang, Haiyun Yuan, Meiping Huang, Jianzheng Cen, Qianjun Jia, Yuhao Dong, Yiyu Shi. (2020). ImageCHD: A 3D Computed Tomography Image Dataset for Classification of Congenital Heart Disease. Lecture notes in computer science, 77–87[10.1007/978-3-030-59719-1_8]
- 8.Amir A. Sepehri, Joel Hancq, Thierry Dutoit, Arash Gharehbaghi, Armen Kocharian, A. Kiani. (2008). Computerized screening of children congenital heart diseases. Computer Methods and Programs in Biomedicine, 92(2), 186–192[10.1016/j.cmpb.2008.06.015]
- 9.Rik Vullings. (2019). Fetal Electrocardiography and Deep Learning for Prenatal Detection of Congenital Heart Disease. Computing in cardiology, 45[10.22489/cinc.2019.072]
- 10.Taiseer Rakiin Ahad, Saadia Binte Alam, Farhan Ha-Mim, Ashad Nur, Sefatul Wasi, Rashedur Rahman. (2024). Comparative Analysis of Deep Learning Models for Intracerebral Hemorrhage Detection from Computed Tomography. , 328–333[10.1109/iccit64611.2024.11022361]
- 11.Kohei Nakatsu, Rashedur Rahman, Kento Morita, Daisuke Fujita, Syoji Kobashi. (2022). Automatic Carpal Site Detection Method for Evaluation of Rheumatoid Arthritis Using Deep Learning. Journal of Advanced Computational Intelligence and Intelligent Informatics, 26(1), 42–50[10.20965/jaciii.2022.p0042]
- 12.Rashedur Rahman, Naomi Yagi, Keigo Hayashi, Akihiro Maruo, Hirotsugu Muratsu, Syoji Kobashi. (2023). Fragility Fracture of Pelvis Prediction from Computed Tomography Using Boring Survey and Convolutional Neural Network. Journal of Advanced Computational Intelligence and Intelligent Informatics, 27(6), 1079–1085[10.20965/jaciii.2023.p1079]