Support for the Diagnosis of Pneumonia and Detection of Pulmonary Opacities Using Semantic Instance Segmentation in Chest X-ray Images
DOI:
https://doi.org/10.14482/inde.39.2.621.367Keywords:
convolutional neural networks, data augmentation, junctional intersection, radiological society of North America, ResNet50Abstract
Pneumonia is a disease that has caused many deaths worldwide. Pneumonia detection methods: blood tests, sputum test, CT scan, and chest X-rays, generally require a specialist doctor for analysis. The objective of this research was to generate a model, based on semantic instances and deep learning (Mask-RCNN), that allows for support in the diagnosis of pulmonary opacities and pneumonia, using 12 024 images of chest X-ray radiographs. 3 experiments were carried out, where the conditions of the dataset images were varied (exp1: patients with pneumonia, exp2: healthy, and, also, pneumonia patients, exp3: healthy, and, also, pneumonia patients, plus data augmentation). For all 3 experiments, a histogram equalization pre-processing technique was performed. In order to evaluate the performance of the models, the parameters Intersection on the Union, Precision, Recall, F1 score, and Accuracy were used. In the identification of pulmonary opacities in the images, and for the classification of patients with pneumonia from healthy ones, Recall was found to be the best performing metric for experiment 1, for both opacity and neumonia detection.
References
Organizacion Mundial de la Salud, «Organizacion Mundial de la Salud,» OMS, 7 04 2019. [En línea]. Available: https://www.who.int/es/news-room/fact-sheets/detail/pneumonia. [Último acceso: 7 04 2021].
Biblioteca Nacional de Medicina de EE. UU, «MedlinePlus,» Biblioteca Nacional de Medicina de EE. UU, 8 03 2020. [En línea]. Available: https://medlineplus.gov/spanish/ency/article/000145.htm#:~:text=Las%20formas%20como%20se%20puede,microbios%20directamente%20hacia%20los%20pulmones. [Último acceso: 7 04 2021].
Mayo Clinic, «Mayo Clinic,» 2 05 2020. [En línea]. Available: https://www.mayoclinic.org/es-es/tests-procedures/chest-x-rays/about/pac-20393494. [Último acceso: 7 04 2021].
M. I. Neuman, E. Y. Lee, . S. Bixby, S. Diperna, . J. Hellinger, R. Markowitz, S. Servaes, M. C. Monuteaux y S. S. Shah, «Variability in the interpretation of chest radiographs for the diagnosis of pneumonia in children,» Journal of hospital medicine, vol. 7, nº 4, pp. 294-298, 2012. https://doi.org/10.1002/jhm.955.
M. d. C. Expósito Gallardo y . R. Ávila Ávila, «Aplicaciones de la inteligencia artificial en la Medicina: perspectivas y problemas,» ACIMED, vol. 17, nº 5, 2008.
R. Jain, P. Nagrath, G. Kataria, S. Kaushik and D. J. Hemanth, "Pneumonia detection in chest X-ray images using convolutional neural networks and transfer learning," Measurement, vol. 165, p. 10, 21 5 2019. https://doi.org/10.1016/j.measurement.2020.108046.
X. Yu, S. HuaWang and Y. DongZhang, "CGNet: A graph-knowledge embedded convolutional neural network for detection of pneumonia," Information Processing & Management, vol. 58, no. 1, p. 25, 2021. https://doi.org/10.1016/j.ipm.2020.102411.
S. Militante y B. Sibbaluca, «Pneumonia Detection Using Convolutional Neural Networks,» Revista Internacional de Investigación Científica y Tecnológica, vol. 9, nº 04, pp. 1332-1337, 2020. https://doi.org/10.46501/ijmtst070117.
P. Rajpurkar, J. Irvin, . K. Zhu, B. Yang, H. Mehta, T. Duan, . D. Ding, A. Bagul, C. Langlotz, K. Shpanskaya, L. Matthew and A. Ng, "CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning," ArXiv, vol. 1711.05225, 2017.
Q. Guan, Y. Huang, Z. Zhong, Z. Zheng, L. Zheng and Y. Yang, "Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification," ArXiv, vol. 1801.09927, 2018.
L. Yao, E. Poblenz, D. Dagunts, B. Covington, . D. Bernard y . K. Lyman, «Learning to diagnose from scratch by exploiting dependencies among labels,» ArXiv, vol. 1710.10501, 2018.
I. Sirazitdinov, M. Kholiavchenko, T. Mustafaev, Y. Yixuan, R. Kuleev and B. Ibragimov, "Deep neural network ensemble for pneumonia localization from a large-scale chest x-ray database," Computers and Electrical Engineering, vol. 78, p. 388–399, 2019. https://doi.org/10.1016/j.compeleceng.2019.08.004.
S. Chen, Y. Han, J. Lin, X. Zhao and P. Kong, "Pulmonary nodule detection on chest radiographs using balanced convolutional neural network and classic candidate detection," Artificial Intelligence in Medicine, vol. 107, no. 101881, 07 2020. https://doi.org/10.1016/j.artmed.2020.101881.
C. Li, G. Zhu, X. Wu y Y. Wang, «False-Positive Reduction on Lung Nodules Detection in Chest Radiographs by Ensemble of Convolutional Neural Networks,» IEEE Access, vol. 6, pp. 16060-16067, 2018. https://doi.org/10.1109/ACCESS.2018.2817023.
X. Li, L. Shen and S. Luo, "A Solitary Feature-Based Lung Nodule Detection Approach for Chest X-Ray Radiographs," IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 2, pp. 516-524, 2018. https://doi.org/10.1109/JBHI.2017.2661805.
Radiological Society of North America, «Kaggle,» 31 10 2018. [En línea]. Available: https://www.kaggle.com/c/rsna-pneumonia-detection-challenge. [Último acceso: 21 05 2021].
MD.ai, «Public MD.ai,» 2018. [En línea]. Available: https://public.md.ai/annotator/project/LxR6zdR2/workspace. [Último acceso: 25 08 2021].
S. Militante and B. Sibbaluca, "Pneumonia Detection Using Convolutional Neural Networks," Revista Internacional de Investigación Científica y Tecnológica, vol. 9, no. 04, pp. 1332-1337, 2020.
F. Luis, . D. Daniel y . D. Roberto, «Optimización de la ecualización del histograma en el procesamiento de imágenes digitales,» de VII Workshop de Investigadores en Ciencias de la Computación, Florencio Varela, 2005.
L. Taylor y G. Nitschke, «Improving Deep Learning using Generic Data Augmentation,» de 2018 IEEE Symposium Series on Computational Intelligence (SSCI), Bangalore, India, 2018. https://doi.org/10.1109/SSCI.2018.8628742.
K. He, G. Gkioxari, P. Dollar y R. Girshick, «Mask R-CNN,» de 2017 Proceedings of the IEEE international conference on computer vision, 2017. https://doi.org/10.1109/ICCV.2017.322.
A. K. Jaiswal, P. Tiwari, S. Kumar, D. Gupta, A. Khanna y J. Rodrigues, «Identifying pneumonia in chest X-rays: A deep learning approach,» Measurement, vol. 145, pp. 511-518, 2019. https://doi.org/10.1016/j.measurement.2019.05.076.
X. Wang, . Y. Peng, . L. Lu, . Z. Lu, M. Bagheri and . R. Summers, "ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. https://doi.org/10.1109/CVPR.2017.369.
