Modified YOLOv4-DenseNet Algorithm for Detection of Ventricular Septal Defects in Ultrasound Images.

Shih Hsin Chen; Chun Wei Wang; I Hsin Tai; Ken Pen Weng; Yi Hui Chen; Kai Sheng Hsieh

doi:10.9781/ijimai.2021.06.001

Authors

Shih Hsin Chen Cheng Shiu University
Chun Wei Wang Cheng Shiu University
I Hsin Tai China Medical University Hospital
Ken Pen Weng Kaohsiung Veterans General Hospital
Yi Hui Chen Chang Gung University
Kai Sheng Hsieh Taipei Medical University-Shuang Ho Hospital

DOI:

https://doi.org/10.9781/ijimai.2021.06.001

Keywords:

Ventricular Septal Defect (VSD), Doppler Echocardiographic Images, Object Detection, Deep Learning, YOLOv

Supporting Agencies

The data used in this study are restricted by the Research Ethics Review Committee of the Kaohsiung Veterans General Hospital with the number 19-CT8-10(190701-2) to protect participant privacy. We thank the Ministry of Science and Technology for supporting this research with ID MOST 108-2221-E-230-004. We thank the co-author of YOLOv4, Dr. Chien-Yao Wang of the Institute of Information Science, Academia Sinica, Taiwan (R.O.C), clarified their proposed algorithm of CSPDenseNet Ref.-PRN [20]. Finally, we also thank Miss. Wen Mei of Kaohsiung Veterans General Hospital, Miss. Chin Yu worked on the patience data collection and medical images preparations, and Miss. Yu-Chi Lin further enhanced the Fig. 1 quality.

Abstract

Doctors conventionally analyzed echocardiographic images for diagnosing congenital heart diseases (CHDs). However, this process is laborious and depends on the experience of the doctors. This study investigated the use of deep learning algorithms for the image detection of the ventricular septal defect (VSD), the most common type. Color Doppler echocardiographic images containing three types of VSDs were tested with color doppler ultrasound medical images. To the best of our knowledge, this study is the first one to solve this object detection problem by using a modified YOLOv4–DenseNet framework. Because some techniques of YOLOv4 are not suitable for echocardiographic object detection, we revised the algorithm for this problem. The results revealed that the YOLOv4–DenseNet outperformed YOLOv4, YOLOv3, YOLOv3–SPP, and YOLOv3–DenseNet in terms of metric mAP-50. The F1-score of YOLOv4-DenseNet and YOLOv3-DenseNet were better than those of others. Hence, the contribution of this study establishes the feasibility of using deep learning for echocardiographic image detection of VSD investigation and a better YOLOv4-DenseNet framework could be employed for the VSD detection.

Downloads

Download data is not yet available.

References

M.-H. Wu, H.-C. Chen, C.-W. Lu, J.-K. Wang, S.-C. Huang, S.-K. Huang, “Prevalence of congenital heart disease at live birth in Taiwan,” The Journal of pediatrics, vol. 156, no. 5, pp. 782–785, 2010.

S.-J. Yeh, H.-C. Chen, C.-W. Lu, J.-K. Wang, L.-M. Huang, S.-C. Huang, S.-K. Huang, M.-H. Wu, “National database study of survival of pediatric congenital heart disease patients in Taiwan,” Journal of the Formosan Medical Association, vol. 114, no. 2, pp. 159–163, 2015.

J. Carvalho, L. Allan, R. Chaoui, J. Copel, G. DeVore, K. Hecher, W. Lee, H. Munoz, D. Paladini, B. Tutschek, et al., “Isuog practice guidelines (updated): sonographic screening examination of the fetal heart,” Ultrasound in Obstetrics & Gynecology, vol. 41, no. 3, pp. 348–359, 2013.

M. Avendi, A. Kheradvar, H. Jafarkhani, “A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac mri,” Medical image analysis, vol. 30, pp. 108–119, 2016.

H. Chen, Y. Zheng, J.-H. Park, P.-A. Heng, S. K. Zhou, “Iterative multidomain regularized deep learning for anatomical structure detection and segmentation from ultrasound images,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2016, pp. 487–495, Springer.

R. P. Poudel, P. Lamata, G. Montana, “Recurrent fully convolutional neural networks for multi-slice mri cardiac segmentation,” in International Workshop on Reconstruction and Analysis of Moving Body Organs, 2016, pp. 83–94, Springer.

G. Sutherland, M. Stewart, K. Groundstroem, C. Moran, A. Fleming, F. Guell-Peris, R. Riemersma, L. Fenn, K. Fox, W. McDicken, “Color doppler myocardial imaging: a new technique for the assessment of myocardial function,” Journal of the American Society of Echocardiography, vol. 7, no. 5, pp. 441–458, 1994.

P. Pézard, L. Bonnemains, F. Boussion, L. Sentilhes, P. Allory, C. Lepinard, A. Guichet, S. Triau, F. Biquard, M. Leblanc, et al., “Influence of ultrasonographers training on prenatal diagnosis of congenital heart diseases: a 12-year population-based study,” Prenatal diagnosis, vol. 28, no. 11, pp. 1016–1022, 2008.

G. Hill, J. Block, J. Tanem, M. Frommelt, “Disparities in the prenatal detection of critical congenital heart disease,” Prenatal diagnosis, vol. 35, no. 9, pp. 859–863, 2015.

C. P. Bridge, C. Ioannou, J. A. Noble, “Automated annotation and quantitative description of ultrasound videos of the fetal heart,” Medical image analysis, vol. 36, pp. 147–161, 2017.

F. C. Ghesu, E. Krubasik, B. Georgescu, V. Singh, Y. Zheng,J. Hornegger, D. Comaniciu, “Marginal space deep learning: efficient architecture for volumetric image parsing,” IEEE transactions on medical imaging, vol. 35, no. 5, pp. 1217–1228, 2016.

A. Madani, R. Arnaout, M. Mofrad, R. Arnaout, “Fast and accurate view classification of echocardiograms using deep learning,” npj Digital Medicine, vol. 1, no. 1, p. 6, 2018.

M. Moradi, Y. Guo, Y. Gur, M. Negahdar, T. Syeda-Mahmood, “A cross-modality neural network transform for semi-automatic medical image annotation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2016, pp. 300–307, Springer.

J. C. Nascimento, G. Carneiro, “Multi-atlas segmentation using manifold learning with deep belief networks,” in Biomedical Imaging (ISBI), 2016 IEEE 13th International Symposium on, 2016, pp. 867–871, IEEE.

F. A. Saiz, I. Barandiaran, “Covid-19 detection in chest x-ray images using a deep learning approach,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 6, no. 2, pp. 11–14, 2020.

J. Redmon, S. Divvala, R. Girshick, A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779–788.

A. Bochkovskiy, C.-Y. Wang, H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.

T.-Y. Lin, P. Goyal, R. Girshick, K. He, P. Dollár, “Focal loss for dense object detection,” IEEE transactions on pattern analysis and machine intelligence, 2018.

S. Ren, K. He, R. Girshick, J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” in Advances in neural information processing systems, 2015, pp. 91–99.

C.-Y. Wang, H.-Y. Mark Liao, Y.-H. Wu, P.-Y. Chen, J.-W. Hsieh, I.-H. Yeh, “Cspnet: A new backbone that can enhance learning capability of cnn,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 390–391.

J. Redmon, “Darknet: Open source neural networks in c.” http://pjreddie.com/darknet/, 2013–2016.

H. Gao, Z. Liu, L. van der Maaten, K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.

D. Xu, Y. Wu, “Improved yolo-v3 with densenet for multi-scale remote sensing target detection,” Sensors, vol. 20, no. 15, p. 4276, 2020.

Y. Tian, G. Yang, Z. Wang, H. Wang, E. Li, Z. Liang, “Apple detection during different growth stages in orchards using the improved yolo-v3 model,” Computers and electronics in agriculture, vol. 157, pp. 417–426, 2019.

Z. Liao, M. H. Jafari, H. Girgis, K. Gin, R. Rohling, P. Abolmaesumi, T. Tsang, “Echocardiography view classification using quality transfer star generative adversarial networks,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, 2019, pp. 687–695, Springer.

Q. Nie, Y.-b. Zou, J. C.-W. Lin, “Feature extraction for medical ct images of sports tear injury,” Mobile Networks and Applications, pp. 1–11, 2020.