Classification of Lung Diseases in X-Ray Images Using Transformer-Based Deep Learning Models

Nyoman Sarasuartha Mahajaya; Putu Desiana Wulaning Ayu; Roy Rudolf Huizen

doi:10.23887/janapati.v13i3.81425

Authors

Nyoman Sarasuartha Mahajaya Institut Teknologi dan Bisnis Stikom Bali
Putu Desiana Wulaning Ayu Institut Teknologi dan Bisnis STIKOM Bali
Roy Rudolf Huizen Institut Teknologi dan Bisnis STIKOM Bali

DOI:

https://doi.org/10.23887/janapati.v13i3.81425

Keywords:

vision transformer, swin , chest x-ray, deep learning

Abstract

This research evaluates the performance of two Transformer models, the Vision Transformer (ViT) and Swin Transformer, in the analysis of thoracic X-ray images. The study's objective is to determine whether Transformer models can enhance diagnostic accuracy for lung diseases, considering challenges such as early symptom variability and similar radiological signs. The dataset includes 21,165 X-ray images, featuring 3,616 COVID-19 cases, 10,192 normal images, 6,012 images of Lung Opacity, and 1,345 pneumonia images. Model development involved tuning hyperparameters such as epoch numbers and optimizer choice. The results indicate that using the AdamW and Adamax optimizers achieves an optimal balance between computational efficiency and accuracy. The Swin Transformer model, using the Adamax optimizer, reached the highest testing accuracy of 96.10% in 33,802.70 seconds, while the Vision Transformer achieved a testing accuracy of 95.10% in 33,503.10 seconds.

References

T. W. Ferkol and D. E. Schraufnagel, “The global burden of respiratory disease,” Ann. Am. Thorac. Soc., vol. 11, no. 3, pp. 404–406, 2014, doi: 10.1513/ANNALSATS.201311-405PS.

J. P. Wisnivesky and J. P. de-Torres, “The Global Burden of Pulmonary Diseases: Most Prevalent Problems and Opportunities for Improvement,” Ann. Glob. Heal., vol. 85, no. 1, 2019, doi: 10.5334/AOGH.2411.

L. B. Tolle, “Challenges in the Diagnosis and Management of Patients with Fibrosing Interstitial Lung Disease,” Case Rep. Pulmonol., vol. 2022, 2022, doi: 10.1155/2022/9942432.

C. Xu, L. Li, and W. Wang, “Challenges in Advanced Lung Cancer Diagnosis During the COVID-19 Pandemic,” Technol. Cancer Res. Treat., vol. 21, 2021, doi: 10.1177/15330338211050764.

Y. Tang et al., “Automated abnormality classi fi cation of chest radiographs using deep convolutional neural networks,” npj Digit. Med., doi: 10.1038/s41746-020-0273-z.

N. Adithyaram, “Early Detection of Lung Disease Using Deep Learning Algorithms on Image Data,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 11, no. 7, pp. 466–469, 2023, doi: 10.22214/ijraset.2023.53802.

A. W. Salehi et al., “A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope,” Sustain., vol. 15, no. 7, 2023, doi: 10.3390/su15075930.

A. Dosovitskiy et al., “an Image Is Worth 16X16 Words: Transformers for Image Recognition At Scale,” ICLR 2021 - 9th Int. Conf. Learn. Represent., 2021.

Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” Proc. IEEE Int. Conf. Comput. Vis., pp. 9992–10002, 2021, doi: 10.1109/ICCV48922.2021.00986.

D. Nam and A. Pak, “Overview of Transformer-Based Models for Medical Image Segmentation,” Sci. J. Astana IT Univ., pp. 64–75, 2023, doi: 10.37943/13bkbf2003.

K. He, F. Gou, and J. Wu, “Image segmentation technology based on transformer in medical decision-making system,” IET Image Process., vol. 17, no. 10, pp. 3040–3054, 2023, doi: https://doi.org/10.1049/ipr2.12854.

W. Li, “A Swin Transformer with Dynamic High-Pass Preservation for Remote Sensing Image Pansharpening,” 2023.

Y. Peng, J. Ren, J. Wang, and M. Shi, “Spectral-Swin Transformer with Spatial Feature Extraction Enhancement for Hyperspectral Image Classification,” pp. 1–19, 2023.

J. Huang et al., “Swin transformer for fast MRI,” Neurocomputing, vol. 493, pp. 281–304, 2022, doi: 10.1016/j.neucom.2022.04.051.

I. Sonata, Y. Heryadi, A. Wibowo, and W. Budiharto, “End-to-End Steering Angle Prediction for Autonomous Car Using Vision Transformer,” vol. 17, no. 2, pp. 221–234, 2023.

Y. Zhang, J. Wang, and J. M. Gorriz, “Deep Learning and Vision Transformer for Medical Image Analysis,” pp. 9–12, 2023.

J. A. Figo, N. Yudistira, and A. W. Widodo, “Deteksi Covid-19 dari Citra X-ray menggunakan Vision Transformer,” vol. 7, no. 3, pp. 1116–1125, 2023.

G. G. Tahyudin, “Klasifikasi Gender Berdasarkan Citra Wajah Menggunakan Vision Transformer,” vol. 10, no. 2, pp. 1808–1823, 2023.

“CHEST X-RAY DATABASE.” https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database (accessed Feb. 01, 2024).

Y. Zhang and W. H. Id, “Vision Transformer with hierarchical structure and windows shifting for person re- identification,” pp. 1–16, 2023, doi: 10.1371/journal.pone.0287979.

S. Aburass and O. Dorgham, “Performance Evaluation of Swin Vision Transformer Model Using Gradient Accumulation Optimization Technique,” pp. 56–64, 2023, doi: 10.1007/978-3-031-47448-4_5.

P. D. Wulaning Ayu and G. A. Pradipta, “U-Net Tuning Hyperparameter for Segmentation in Amniotic Fluid Ultrasonography Image,” 2022 4th Int. Conf. Cybern. Intell. Syst. ICORIS 2022, no. June, 2022, doi: 10.1109/ICORIS56080.2022.10031294.

Tamil, “Biomedical Signal Processing and Control Deep learning-based approach for detecting COVID-19 in chest X-rays,” Biomed. Signal Process. Control, vol. 78, no. January, p. 103977, 2022, [Online]. Available: https://doi.org/10.1016/j.bspc.2022.103977

B. T. Magar, K. Shrestha, and M. A. Rahman, “CNN-based Clinical Diagnosis and Decision Support System for Chest X-ray,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1305, no. 1, p. 012027, 2024, doi: 10.1088/1757-899x/1305/1/012027.

A. W. Setiawan, “Perbandingan Arsitektur Convolutional Neural Network Pada Klasifikasi Pneumonia, COVID-19, Lung Opacity, dan Normal Menggunakan Citra Sinar-X Thoraks,” J. Teknol. Inf. dan Ilmu Komput., vol. 9, no. 7, pp. 1563–1570, 2022, doi: 10.25126/jtiik.2022976742.