An Efficient Lung Disease Classification from X-ray Image Using Graph Neural Network and Transformer

Jiang Zhihao (1), Noridayu Bt Manshor (2), Hazlina Hamdan (3), Chen Limi (4)
(1) Hainan Vocational University of Science and Technology, Hainan, China
(2) Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Malaysia
(3) Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Malaysia
(4) Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Malaysia
Fulltext View | Download
How to cite (IJASEIT) :
[1]
J. Zhihao, N. Bt Manshor, H. Hamdan, and C. Limi, “An Efficient Lung Disease Classification from X-ray Image Using Graph Neural Network and Transformer”, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 275–282, Feb. 2025.
This research addresses the need for improved accuracy and efficiency in lung disease classification from X-ray images by developing a novel approach that integrates Graph Neural Networks (GNNs) with Transformer models. Using the extensive ChestX-ray14 dataset, which includes a wide array of lung disease cases, this study introduces and validates the TransGNN model. TransGNN harnesses the complementary strengths of GNNs and Transformers through advanced attention mechanisms and a dual-branch architecture, effectively capturing the complex and variable characteristics inherent in medical imaging data. The methodological framework includes rigorous data preprocessing, the application of weighted focus loss functions to address significant class imbalances, and extensive data augmentation techniques to bolster the model’s robustness during testing. Results show that TransGNN surpasses conventional models by achieving superior classification accuracy across multiple lung diseases, demonstrating substantial improvements in diagnostic precision and reliability. Furthermore, the model’s continuous learning mechanisms enable it to adapt seamlessly to new data and advances in medical imaging technology, making it highly versatile. This study highlights the potential of GNNs and Transformers to revolutionize the diagnostic landscape, offering a powerful, precise, and efficient tool for lung disease diagnosis. Future research should aim to incorporate additional patient-specific data, explore more advanced neural network architectures, and validate the model across diverse patient populations to enhance diagnostic accuracy further and expand its practical applicability in clinical settings, paving the way for a new standard in AI-driven medical diagnostics.

M. Gori, G. Monfardini, and F. Scarselli, “A new model for learning in graph domains,” in Proc. IEEE Int. Joint Conf. Neural Netw., vol. 2, 2005, pp. 729–734, doi: 10.1109/ijcnn.2005.1555942.

F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neural network model,” IEEE Trans. Neural Netw., vol. 20, no. 1, pp. 61–80, Jan. 2009, doi: 10.1109/tnn.2008.2005605.

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., "Attention is all you need", Proc. 31st Int. Conf. Neural Information Processing Systems, pp. 6000-6010, 2017.

W. Peebles and S. Xie, “Scalable diffusion models with transformers,” in 2023 IEEE/CVF Int. Conf. Comput. Vis. (ICCV), 2023, pp. 4172–4182, doi: 10.1109/iccv51070.2023.00387.

D. Ahmedt-Aristizabal, M. A. Armin, S. Denman, C. Fookes, and L. Petersson, “Graph-based deep learning for medical diagnosis and analysis: Past, present and future,” Sensors, vol. 21, no. 14, p. 4758, Jul. 2021, doi: 10.3390/s21144758.

L. Zhang, Y. Zhao, T. Che, S. Li, and X. Wang, “Graph neural networks for image-guided disease diagnosis: A review,” iRadiolog,vol. 1, no. 2, pp. 151–166, Jun. 2023, doi:10.1002/ird3.20.

J. Zhou et al., “Graph neural networks: A review of methods and applications,” AI Open, vol. 1, pp. 57–81, 2020, doi:10.1016/j.aiopen.2021.01.001.

A. Zanfei, B. M. Brentan, A. Menapace, M. Righetti, and M. Herrera, “Graph convolutional recurrent neural networks for water demand forecasting,” Water Resour. Res., vol. 58, no. 7, Jul. 2022, doi:10.1029/2022wr032299.

R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional neural networks: An overview and application in radiology,” Insights Imaging, vol. 9, no. 4, pp. 611–629, Jun. 2018, doi: 10.1007/s13244-018-0639-9.

L. Wu et al., “Graph neural networks for natural language processing: A survey,” Found. Trends Mach. Learn., vol. 16, no. 2, pp. 119–328, 2023, doi: 10.1561/2200000096.

L. Wu, P. Cui, J. Pei, L. Zhao, and X. Guo, “Graph neural networks: Foundation, frontiers and applications,” in Proc. 29th ACM SIGKDD Conf. Knowl. Discov. Data Min., 2023, pp. 5831–5832, doi:10.1145/3580305.3599560.

S. Thirumalaisamy et al., “Breast cancer classification using synthesized deep learning model with metaheuristic optimization algorithm,” Diagnostics, vol. 13, no. 18, p. 2925, Sep. 2023, doi:10.3390/diagnostics13182925.

R.-K. Sheu and M. S. Pardeshi, “A survey on medical explainable AI (XAI): Recent progress, explainability approach, human interaction and scoring system,” Sensors, vol. 22, no. 20, p. 8068, Oct. 2022, doi:10.3390/s22208068.

Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, Nov. 1998, doi: 10.1109/5.726791.

M. Mamalakis et al., “DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays,” Comput. Med. Imaging Graph., vol. 94, p. 102008, Dec. 2021, doi: 10.1016/j.compmedimag.2021.102008.

O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Med. Image Comput. Comput.-Assist. Interv. (MICCAI), 2015, pp. 234–241, doi:10.1007/978-3-319-24574-4_28.

Y. Li, X. Wu, P. Yang, G. Jiang, and Y. Luo, “Machine learning for lung cancer diagnosis, treatment, and prognosis,” Genomics, Proteomics Bioinf., vol. 20, no. 5, pp. 850–866, Oct. 2022, doi:10.1016/j.gpb.2022.11.003.

J. Hanson et al., “SPOT-Disorder2: Improved protein intrinsic disorder prediction by ensembled deep learning,” Genomics, Proteomics Bioinf., vol. 17, no. 6, pp. 645–656, Dec. 2019, doi: 10.1016/j.gpb.2019.01.004.

L.-C. Chen, G. Papandreou, F. Schroff, and H. Adam, “Rethinking atrous convolution for semantic image segmentation,” arXiv, 2017. [Online]. Available: https://arxiv.org/abs/1706.05587.

T. Dhar, N. Dey, S. Borra, and R. S. Sherratt, “Challenges of deep learning in medical image analysis—Improving explainability and trust,” IEEE Trans. Technol. Soc., vol. 4, no. 1, pp. 68–75, Mar. 2023, doi: 10.1109/tts.2023.3234203.

K. He et al., “Transformers in medical image analysis,” Intell. Med., vol. 3, no. 1, pp. 59–78, Feb. 2023, doi: 10.1016/j.imed.2022.07.002.

M. H. Al-Sheikh et al., “Multi-class deep learning architecture for classifying lung diseases from chest X-ray and CT images,” Sci. Rep., vol. 13, no. 1, Nov. 2023, doi: 10.1038/s41598-023-46147-3.

M. Hajij et al., “Topological deep learning: Going beyond graph data,” arXiv, 2022. [Online]. Available: https://arxiv.org/abs/2206.00606

F. J. M. Shamrat, S. Azam, A. Karim, K. Ahmed, F. M. Bui, and F. De Boer, “High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images,” Comput. Biol. Med., vol. 155, p. 106646, Mar. 2023, doi:10.1016/j.compbiomed.2023.106646.

C. Metta, A. Beretta, R. Pellungrini, S. Rinzivillo, and F. Giannotti, “Towards transparent healthcare: Advancing local explanation methods in explainable artificial intelligence,” Bioengineering, vol. 11, no. 4, p. 369, Apr. 2024, doi: 10.3390/bioengineering11040369.

J. Shi, R. Wang, Y. Zheng, Z. Jiang, H. Zhang, and L. Yu, “Cervical cell classification with graph convolutional network,” Comput. Methods Programs Biomed., vol. 198, p. 105807, Jan. 2021, doi:10.1016/j.cmpb.2020.105807.

Y. Huang et al., “Transformer-based factorized encoder for classification of pneumoconiosis on 3D CT images,” Comput. Biol. Med., vol. 150, p. 106137, Nov. 2022, doi:10.1016/j.compbiomed.2022.106137.

D. Yao et al., “A mutual multi-scale triplet graph convolutional network for classification of brain disorders using functional or structural connectivity,” IEEE Trans. Med. Imaging, vol. 40, no. 4, pp. 1279–1289, Apr. 2021, doi: 10.1109/tmi.2021.3051604.

R. Najjar, “Redefining radiology: A review of artificial intelligence integration in medical imaging,” Diagnostics, vol. 13, no. 17, p. 2760, Aug. 2023, doi: 10.3390/diagnostics13172760.

W. Zhang et al., “HyGAnno: Hybrid graph neural network–based cell type annotation for single-cell ATAC sequencing data,” Brief. Bioinform., vol. 25, no. 3, Mar. 2024, doi: 10.1093/bib/bbae152.

F. Shamshad et al., “Transformers in medical imaging: A survey,” Med. Image Anal., vol. 88, p. 102802, Aug. 2023, doi:10.1016/j.media.2023.102802.

S. Bharati, P. Podder, and M. R. H. Mondal, “Hybrid deep learning for detecting lung diseases from X-ray images,” Inform. Med. Unlocked, vol. 20, p. 100391, 2020, doi: 10.1016/j.imu.2020.100391.

B. Hu, C. Zhou, H. Wang, and S. Chen, “Nonlinear tribo-dynamic model and experimental verification of a spur gear drive under loss-of-lubrication condition,” Mech. Syst. Signal Process., vol. 153, p. 107509, May 2021, doi: 10.1016/j.ymssp.2020.107509.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).