{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:50:30Z","timestamp":1787313030326,"version":"build-2736575974"},"reference-count":48,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Traditional medical image analysis methods often suffer from locality bias, limiting their ability to model long-range contextual relationships between spatially distributed anatomical structures. To overcome this challenge, this study proposes SPX-GNN (Superpixel Explainable Graph Neural Network). This novel method reformulates image analysis as a structural graph learning problem, capturing both local anomalies and global topological patterns in a holistic manner. Methods: The proposed framework decomposes images into semantically coherent superpixel regions, converting them into graph nodes that preserve topological relationships. Each node is enriched with a comprehensive feature vector encoding complementary diagnostic clues, including colour (CIELAB), texture (LBP and Haralick), shape (Hu moments), and spatial location. A Graph Neural Network is then employed to learn the relational dependencies between these enriched nodes. The method was rigorously evaluated using 5-fold stratified cross-validation on a public dataset comprising 4200 chest X-ray images. Results: SPX-GNN demonstrated exceptional performance in tuberculosis classification, achieving a mean accuracy of 99.82%, an F1-score of 99.45%, and a ROC-AUC of 100.00%. Furthermore, an integrated Explainable Artificial Intelligence module addresses the black box problem by generating semantic importance maps, which illuminate the decision mechanism and enhance clinical reliability. Conclusions: SPX-GNN offers a novel approach that successfully combines high diagnostic accuracy with methodological transparency. By providing a robust and interpretable workflow, this study presents a promising solution for medical imaging tasks where structural information is critical, paving the way for more reliable clinical decision support systems.<\/jats:p>","DOI":"10.3390\/diagnostics15243236","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T09:15:21Z","timestamp":1766049321000},"page":"3236","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["SPX-GNN: An Explainable Graph Neural Network for Harnessing Long-Range Dependencies in Tuberculosis Classifications in Chest X-Ray Images"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8153-7971","authenticated-orcid":false,"given":"Muhammed Ali","family":"Pala","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Faculty of Technology, Sakarya University of Applied Sciences, Sakarya 54050, T\u00fcrkiye"},{"name":"Biomedical Technologies Application and Research Center (BIYOTAM), Sakarya University of Applied Sciences, Sakarya 54050, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9069-5816","authenticated-orcid":false,"given":"Muhammet Burhan","family":"Navdar","sequence":"additional","affiliation":[{"name":"Biomedical Technologies Application and Research Center (BIYOTAM), Sakarya University of Applied Sciences, Sakarya 54050, T\u00fcrkiye"},{"name":"Department of Civil Engineering, Faculty of Engineering, Sakarya University, Sakarya 54050, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Silva, M.L., C\u00e1, B., Os\u00f3rio, N.S., Rodrigues, P.N.S., Maceiras, A.R., and Saraiva, M. (2022). Tuberculosis caused by Mycobacterium africanum: Knowns and unknowns. PLoS Pathog., 18.","DOI":"10.1371\/journal.ppat.1010490"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e20","DOI":"10.1016\/S2666-5247(22)00359-7","article-title":"WHO\u2019s global tuberculosis report 2022","volume":"4","author":"Bagcchi","year":"2023","journal-title":"Lancet Microbe"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"S26","DOI":"10.1016\/j.ijid.2022.03.011","article-title":"The WHO Global Tuberculosis 2021 Report\u2013not so good news and turning the tide back to End TB","volume":"124","author":"Chakaya","year":"2022","journal-title":"Int. J. Infect. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1007\/s42979-024-02610-0","article-title":"Efficient segmentation of vessels and disc simultaneously using multi-channel generative adversarial network","volume":"5","author":"Kar","year":"2024","journal-title":"SN Comput. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","article-title":"Machine learning for medical imaging: Methodological failures and recommendations for the future","volume":"5","author":"Varoquaux","year":"2022","journal-title":"npj Digit. Med."},{"key":"ref_6","first-page":"24","article-title":"Computer vision and machine learning for medical image analysis: Recent advances, challenges, and way forward","volume":"2","author":"Elyan","year":"2022","journal-title":"Artif. Intell. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"40905","DOI":"10.1007\/s11042-025-20703-7","article-title":"Efficient segmentation of exudates in color fundus images using wavelets and generative adversarial network","volume":"84","author":"Kar","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2430001","DOI":"10.1142\/S0218348X24300010","article-title":"Chaos Theory, Advanced Metaheuristic Algorithms And Their Newfangled Deep Learning Architecture Optimization Applications: A Review","volume":"32","author":"Akgul","year":"2024","journal-title":"Fractals"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Salehi, A.W., Khan, S., Gupta, G., Alabduallah, B.I., Almjally, A., Alsolai, H., Siddiqui, T., and Mellit, A. (2023). A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope. Sustainability, 15.","DOI":"10.3390\/su15075930"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"110920","DOI":"10.1016\/j.optlastec.2024.110920","article-title":"Improving cellular analysis throughput of lens-free holographic microscopy with circular Hough transform and convolutional neural networks","volume":"176","author":"Pala","year":"2024","journal-title":"Opt. Laser Technol."},{"key":"ref_11","first-page":"1","article-title":"Metaheuristic Algorithms for Convolution Neural Network","volume":"2016","author":"Fanany","year":"2016","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pala, M.A. (2025). Graph-Aware AURALSTM: An Attentive Unified Representation Architecture with BiLSTM for Enhanced Molecular Property Prediction. Mol. Divers., online ahead of print.","DOI":"10.1007\/s11030-025-11197-4"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1109\/TCBB.2024.3385796","article-title":"A Network Enhancement Method to Identify Spurious Drug-Drug Interactions","volume":"21","author":"Wang","year":"2024","journal-title":"IEEE ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Vanitha, K., Mahesh, T.R., Kumar, V.V., and Guluwadi, S. (2025). Enhanced tuberculosis detection using Vision Transformers and explainable AI with a Grad-CAM approach on chest X-rays. BMC Med. Imaging, 25.","DOI":"10.1186\/s12880-025-01630-3"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pala, M.A. (2025). XP-GCN: Extreme Learning Machines and Parallel Graph Convolutional Networks for High-Throughput Prediction of Blood-Brain Barrier Penetration based on Feature Fusion. Comput. Biol. Chem., 120.","DOI":"10.1016\/j.compbiolchem.2025.108755"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nyamabo, A.K., Yu, H., Liu, Z., and Shi, J.Y. (2022). Drug-drug interaction prediction with learnable size-Adaptive molecular substructures. Brief. Bioinform., 23.","DOI":"10.1093\/bib\/bbab441"},{"key":"ref_17","first-page":"245","article-title":"DeepInsulin-Net: A Deep Learning Model for Identifying Drug Interactions Leading to Specific Insulin-Related Adverse Events","volume":"8","author":"Pala","year":"2025","journal-title":"Sak. Univ. J. Comput. Inf. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Veli\u010dkovi\u0107, P. (2023). Everything is connected: Graph neural networks. Curr. Opin. Struct. Biol., 79.","DOI":"10.1016\/j.sbi.2023.102538"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hadhoud, Y., Mekhaznia, T., Bennour, A., Amroune, M., Kurdi, N.A., Aborujilah, A.H., and Al-Sarem, M. (2024). From binary to multi-class classification: A two-step hybrid cnn-vit model for chest disease classification based on x-ray images. Diagnostics, 14.","DOI":"10.3390\/diagnostics14232754"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e66029","DOI":"10.2196\/66029","article-title":"Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning: Comparative Study of Convolutional Neural Network Architectures","volume":"6","author":"Mirugwe","year":"2025","journal-title":"JMIRx Med"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Khater, O.H., Shuaibu, A.S., Haq, S.U., and Siddiqui, A.J. (2025, January 17\u201320). AttCDCNet: Attention-enhanced Chest Disease Classification using X-Ray Images. Proceedings of the 2025 IEEE 22nd International Multi-Conference on Systems, Signals & Devices (SSD), Monastir, Tunisia.","DOI":"10.1109\/SSD64182.2025.10989974"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Yulvina, R., Putra, S.A., Rizkinia, M., Pujitresnani, A., Tenda, E.D., Yunus, R.E., Djumaryo, D.H., Yusuf, P.A., and Valindria, V. (2024). Hybrid Vision Transformer and Convolutional Neural Network for Multi-Class and Multi-Label Classification of Tuberculosis Anomalies on Chest X-Ray. Computers, 13.","DOI":"10.3390\/computers13120343"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Reddy, K.D., and Patil, A. (2025). CXR-MultiTaskNet a unified deep learning framework for joint disease localization and classification in chest radiographs. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-16669-z"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"El-Ghany, S.A., Elmogy, M., Mahmood, M.A., and Abd El-Aziz, A.A. (2024). A Robust Tuberculosis Diagnosis Using Chest X-Rays Based on a Hybrid Vision Transformer and Principal Component Analysis. Diagnostics, 14.","DOI":"10.3390\/diagnostics14232736"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Siddharth, G., Ambekar, A., and Jayakumar, N. (2025). Enhanced CoAtNet based hybrid deep learning architecture for automated tuberculosis detection in human chest X-rays. BMC Med. Imaging, 25.","DOI":"10.1186\/s12880-025-01901-z"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ashraf, S.M.N., Mamun, M.A., Abdullah, H.M., and Alam, M.G.R. (2023, January 13\u201315). SynthEnsemble: A fusion of CNN, vision transformer, and Hybrid models for multi-label chest X-ray classification. Proceedings of the 2023 26th International Conference on Computer and Information Technology (ICCIT), Cox\u2019s Bazar, Bangladesh.","DOI":"10.1109\/ICCIT60459.2023.10441433"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Natarajan, S., Sampath, P., Arunachalam, R., Shanmuganathan, V., Dhiman, G., Chakrabarti, P., Chakrabarti, T., and Margala, M. (2023). Early diagnosis and meta-agnostic model visualization of tuberculosis based on radiography images. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-49195-x"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Bhandari, M., Shahi, T.B., Siku, B., and Neupane, A. (2022). Explanatory classification of CXR images into COVID-19, Pneumonia and Tuberculosis using deep learning and XAI. Comput. Biol. Med., 150.","DOI":"10.1016\/j.compbiomed.2022.106156"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"100499","DOI":"10.1016\/j.dajour.2024.100499","article-title":"An explainable artificial intelligence model for multiple lung diseases classification from chest X-ray images using fine-tuned transfer learning","volume":"12","author":"Mahamud","year":"2024","journal-title":"Decis. Anal. J."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s00521-022-07258-6","article-title":"Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence","volume":"36","author":"Nafisah","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Maheswari, B.U., Sam, D., Mittal, N., Sharma, A., Kaur, S., Askar, S.S., and Abouhawwash, M. (2024). Explainable deep-neural-network supported scheme for tuberculosis detection from chest radiographs. BMC Med. Imaging, 24.","DOI":"10.1186\/s12880-024-01202-x"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"191586","DOI":"10.1109\/ACCESS.2020.3031384","article-title":"Bin Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization","volume":"8","author":"Rahman","year":"2020","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","article-title":"SLIC superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"Achanta","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Jiang, X., Tan, L., and Zou, Q. (2024). DGCL: Dual-graph neural networks contrastive learning for molecular property prediction. Brief. Bioinform., 25.","DOI":"10.1093\/bib\/bbae474"},{"key":"ref_36","first-page":"907","article-title":"CNS-DDI: An Integrated Graph Neural Network Framework for Predicting Central Nervous System Related Drug-Drug Interactions","volume":"14","author":"Pala","year":"2025","journal-title":"Bitlis Eren \u00dcniv. Bilim. Derg."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1208\/s12248-025-01059-0","article-title":"GCN-BBB: Deep Learning Blood-Brain Barrier (BBB) Permeability PharmacoAnalytics with Graph Convolutional Neural (GCN) Network","volume":"27","author":"Jing","year":"2025","journal-title":"AAPS J."},{"key":"ref_38","unstructured":"Kipf, T.N. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.patrec.2021.06.030","article-title":"Perturbation-based methods for explaining deep neural networks: A survey","volume":"150","author":"Ivanovs","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Singh, V., Gourisaria, M.K., Harshvardhan, G.M., and Singh, V. (2021). Mycobacterium tuberculosis detection using CNN ranking approach. Advanced Computational Paradigms and Hybrid Intelligent Computing, Proceedings of the ICACCP 2021, Sikkim, India, 22\u201324 March 2021, Springer.","DOI":"10.1007\/978-981-16-4369-9_56"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2399428","DOI":"10.1155\/2022\/2399428","article-title":"AI-assisted tuberculosis detection and classification from chest X-rays using a deep learning normalization-free network model","volume":"2022","author":"Acharya","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Prasitpuriprecha, C., Jantama, S.S., Preeprem, T., Pitakaso, R., Srichok, T., Khonjun, S., Weerayuth, N., Gonwirat, S., Enkvetchakul, P., and Kaewta, C. (2022). Drug-resistant tuberculosis treatment recommendation, and multi-class tuberculosis detection and classification using ensemble deep learning-based system. Pharmaceuticals, 16.","DOI":"10.3390\/ph16010013"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"31515","DOI":"10.1007\/s11042-019-07984-5","article-title":"Automated TB classification using ensemble of deep architectures","volume":"78","author":"Hooda","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"429","DOI":"10.11591\/ijai.v8.i4.pp429-435","article-title":"Ensemble deep learning for tuberculosis detection using chest X-ray and canny edge detected images","volume":"8","author":"Hijazi","year":"2019","journal-title":"IAES Int. J. Artif. Intell."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Heo, S.-J., Kim, Y., Yun, S., Lim, S.-S., Kim, J., Nam, C.-M., Park, E.-C., Jung, I., and Yoon, J.-H. (2019). Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers\u2019 health examination data. Int. J. Environ. Res. Public Health, 16.","DOI":"10.3390\/ijerph16020250"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1016\/j.aej.2022.10.053","article-title":"A deep learning architecture for multi-class lung diseases classification using chest X-ray (CXR) images","volume":"64","author":"Alshmrani","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"103632","DOI":"10.1109\/ACCESS.2022.3208882","article-title":"Stochastic learning-based artificial neural network model for an automatic tuberculosis detection system using chest X-ray images","volume":"10","author":"Urooj","year":"2022","journal-title":"IEEE Access"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"42839","DOI":"10.1109\/ACCESS.2023.3270774","article-title":"An improved densenet deep neural network model for tuberculosis detection using chest x-ray images","volume":"11","author":"Huy","year":"2023","journal-title":"IEEE Access"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/24\/3236\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T09:36:40Z","timestamp":1766050600000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/24\/3236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":48,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["diagnostics15243236"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15243236","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]}}}