Use of Computer Vision in the Analysis of Thoracic Radiological Examinations

• Rafael Augusto Vasconcelos da Silva UDC
• Miguel Diogenes Matrakas UDC https://orcid.org/0000-0002-7047-5437
• Alessandra Bussador UDC https://orcid.org/0000-0002-5900-9398

DOI: https://doi.org/10.5753/latinoware.2024.245751

Abstract

This project explores the planned application of computer vision, specifically Convolutional Neural Networks (CNNs), in the analysis and classification of thoracic radiological examinations. The primary goal is to develop and train a model capable of differentiating between healthy and diseased X-rays, contributing to more accurate and timely diagnostics of pulmonary diseases. The research will employ the ChestX-ray14 dataset, comprising over 100,000 annotated images, as the primary data source. The project is currently in the development phase, with future work focusing on model implementation, evaluation.

Keywords: Computer Vision, Convolutional Neural Networks, Medical Image Analysis, Pulmonary Discases

References

X. Wang, Y. Peng, L. Lu, M. Bagheri, and R. M. Summers, “Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases,” inProceedings of the IEEE Conference on Computer Vision

and Pattern Recognition (CVPR), 2017, pp. 3462–3471

T. Bai, Y. Pang, and T. H. Meen, “Fusion high-resolution network for diagnosing chest x-ray images,” Electronics, vol. 9, no. 1, p. 190, 2020.

P. Rajpurkar, J. Irvin, K. Zhu, B. Yang, H. Mehta, and A. Y. Ng, “Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning,” arXiv preprint, 2017. [Online]. Available: [link]

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [Online]. Available: [link]

M. Nielsen, Neural Networks and Deep Learning. Self-published, 2018. [Online]. Available: [link]

K. Hammoudi, H. Benhabiles, M. Melkemi, F. Dornaika, and I. Arganda-Carreras, “Deep learning on chest x-ray images to detect and evaluate pneumonia cases at the era of covid-19,” HAL Archives, 2020. [Online]. Available: [link]

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014, acessado em: 22 setembro 2024. [Online]. Available: [link]

J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. (2024) Imagenet: A large-scale hierarchical image database. Acessado em: 22 setembro 2024. [Online]. Available: [link]

A. Krizhevsky. (2024) Learning multiple layers of features from tiny images, cifar-10 and cifar-100 datasets. Acessado em: 22 setembro 2024. [Online]. Available: [link]

C. Dataset. (2024) Coco - common objects in context. Acessado em: 22 setembro 2024. [Online]. Available: [link]