| Author(s) | Collection number | Pages | Download abstract | Download full text |
|---|---|---|---|---|
| Pikh I. V., Михайлевич Н. М., Познухов К. Ю. | № 1 (68) | 107-121 |
|
|
Medical diagnostics has always been an important branch of health care. The ability to quickly and accurately determine a patient’s condition is critical for providing effective medical care and treatment. In this regard, in recent decades there has been a growing interest in the use of neural networks in medicine. Neural networks show significant potential in the classification of lung images for early diagnosis of diseases and contribute to the automation of this process. The use of neural networks allows one to improve the accuracy and speed of classification, and also makes it possible to detect pathological changes in the early stages of the development of diseases. Thus, the use of neural networks in medical diagnostics can significantly improve the quality of medical services and improve treatment outcomes.
This article discusses the application of neural networks for the classification of lung images in medical diagnostics. Various neural network architectures, including convolutional neural networks and pretrained models, are explored to help improve classification performance. The article provides an overview of previous research in the field of application of neural networks in medical diagnostics using images. The process of data preparation for training models, methods of validation and evaluation of their effectiveness, including the use of various metrics and cross-validation, are described. In addition, possible applications of neural networks in medicine are considered, such as early detection of lung diseases, decision support, automated screening system, and personalized medicine. Recommendations are given for further research and improvements, such as expanding datasets, improving neural network architectures, ensuring interpretability of results, and comparing with other diagnostic methods. In general, the article opens up new opportunities for improving medical diagnosis and treatment of lung diseases using neural networks.
Keywords: neural networks, image classification, medical diagnostics, deep learning, model validation, performance evaluation, performance metrics, cross-validation, error matrix, error analysis, training data preparation, data set expansion.
doi: 10.32403/1998-6912-2024-1-68-107-121
- 1. Tajbakhsh, N., Shin, J. Y., & Gurudu, S. R. (2017). Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? IEEE Transactions on Medical Imaging (in English).
- 2. Rajpurkar, P., Irvin, J., & Zhu, K. (2017). CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning (in English).
- 3. Hemdan, H., Shouman, M., & Karar, M. (2020). Automatic Detection of COVID-19 from Chest X-ray Images using Deep Learning. IEEE (in English).
- 4. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going Deeper with Convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (in English).
- 5. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Berg, A. C. (2015). ImageNet Large Scale Visual Recognition Challenge: International Journal of Computer Vision (IJCV) (in English).
- 6. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (in English).
- 7. Pikh, I., Senkivskyy, V., Kudriashova, A., & Senkivska, N. Prognostic Assessment of COVID-19 Vaccination Levels. In International Scientific Conference «Intellectual Systems of Decision Making and Problem of Computational Intelligence». 2022. (pp. 246-265). Springer, Cham. ISSN 2367-4512 ISSN 2367-4520 (electronic) ISBN 978-3-031-16202-2 ISBN 978-3-031-16203-9 (eBook) doi: https://doi.org/10.1007/978-3-031-16203-9 (in English).