Deep Learning algorithms for the detection of pneumonia in infants through chest x-ray images
DOI:
https://doi.org/10.26439/ciis2021.5586Keywords:
neumonía infantil, deep learning, Xception, MobileNet, InceptionV3Abstract
Worldwide, large numbers of infants die of pneumonia each year. It is reported that approximately more than 1 million cases of pneumonia in infants occur between 0 and 5 years of age, of which 920 136 died in 2015. Therefore, pneumonia is one of the leading causes of death among infants, with a high level of mortality in Asia and Africa. Even in a developed country like the United States, pneumonia is among the top 10 causes of death. Early detection and treatment of pneumonia can significantly reduce mortality rates among infants in emerging countries. Therefore, this work presents deep learning algorithms to detect pneumonia using radiographic images. Three deep learning algorithms were trained to classify X-ray images into two classes: pneumonia and normal. Three algorithms are presented, to each one a 4x4 pooling layer was added, the data is vectorized with the flatten technique, six dense layers of 1024, 512, 256, 128, 64 and 32 of output value were added and each one with relu activation; A BatchNormalization is applied, finally a dense layer of 2 is added with a softmax activation for classification. The three algorithms are previously trained models, which are Xception, MobileNet and InceptionV3 obtained in the accuracy metric 94.4%, 96.2% and 95.3% respectively.
Downloads
References
Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1800-1807. https://doi.org/10.1109/CVPR.2017.195
Deng, J., Russakovsky, O., Krause, J., Bernstein, M., Berg, A., y Fei-Fei, L. (2014). Scalable MultiLabel Annotation. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI ‘14), 3099-3102. https://doi.org/10.1145/2556288.2557011
Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., y Aerts, H. J. W. L. (2018). Artificial Intelligence in Radiology. Nature Reviews Cancer, 18(8), 500-510. https://doi.org/10.1038/s41568-018-0016-5
Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L. C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., Adam, H., y Le, Q. (2019). Searching for MobileNetV3. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 1314-1324. https://doi.org/10.1109/iccv.2019.00140
Kallianos, K., Mongan, J., Antani, S., Henry, T., Taylor, A., Abuya, J., y Kohli, M. (2019). How Far Have We Come? Artificial Intelligence for Chest Radiograph Interpretation. Clinical Radiology, 74(5), 338-345. https://doi.org/10.1016/j.crad.2018.12.015
Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C., Liang, H., Baxter, S. L., McKeown, A., Yang, G., Wu, X., Yan, F., Dong, J., Prasadha, M. K., Pei, J., Ting, M., Zhu, J., Li, C., Hewett, S., Dong, J., Ziyar, I., … Zhang, K. (2018). Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. Cell, 172(5), 1122-1131.e9. https://doi.org/10.1016/j.cell.2018.02.010
Liang, G., y Zheng, L. (2020). A Transfer Learning Method with Deep Residual Network for Pediatric Pneumonia Diagnosis. Computer Methods and Programs in Biomedicine, 187. https://doi.org/10.1016/j.cmpb.2019.06.023
Liu, N., Wan, L., Zhang, Y., Zhou, T., Huo, H., y Fang, T. (2018). Exploiting Convolutional Neural Networks with Deeply Local Description for Remote Sensing Image Classification. IEEE Access, 6, 11215-11227. https://doi.org/10.1109/ACCESS.2018.2798799
WHO. (2019). Pneumonia. https://www.who.int/es/news-room/fact-sheets/detail/pneumonia
Song, S., Chaudhuri, K., y Sarwate, A. D. (2013). Stochastic Gradient Descent with Differentially Private Updates. 2013 IEEE Global Conference on Signal and Information Processing, 245-248. https://doi.org/10.1109/GlobalSIP.2013.6736861
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., y Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2818-2826. https://doi.org/10.1109/CVPR.2016.308
