Otoimmün Hastalık Tanısında Hep-2 Hücre Desenlerinin Hibrit DenseNet-ViT Mimarisi ile Sınıflandırılması

Öz

Otoimmün hastalıkların tanısında altın standart olarak kabul edilen HEp-2 hücre desenlerinin doğru ve tutarlı şekilde yorumlanması, uzmanlar arasında değişkenlik gösterebilmektedir. Bu çalışma, HEp-2 hücre görüntülerinin otomatik ve yüksek doğrulukla sınıflandırılması amacıyla hibrit bir derin öğrenme mimarisi geliştirmeyi amaçlamaktadır. Önerilen yaklaşımda, lokal morfolojik özelliklerin çıkarımında güçlü performans sergileyen DenseNet-121 mimarisi ile global dokusal bağıntıları modellemede üstün Vision Transformer (ViT-B16) yapısı birleştirilmiştir. Bu iki model, ağırlıklı bir topluluk (ensemble) stratejisi ile entegre edilmiştir. Modelin performansı, literatürde sıkça göz ardı edilen nesne düzeyindeki veri sızıntısını (data leakage) kesin olarak engelleyen katı bir kaynak-görüntü (source-image split) ayırma protokolü ile MIVIA (ICPR 2012) veri seti üzerinde değerlendirilmiştir. Önerilen hibrit model, herhangi bir sentetik veri artırımı kullanılmadan bu zorlu test koşulları altında %96.01 genel doğruluk elde etmiştir. Modelin en dikkat çekici başarısı, uzmanlar tarafından sıklıkla karıştırılan Homogeneous ve Fine Speckled desenleri arasında yüksek doğrulukla ayrım yapabilmesidir. Özellikle Fine Speckled sınıfında %100 kesinlik (precision) değeri elde edilmiştir. Ayrıca, küçük batch boyutunun (Batch Size=8) ince dokulu biyomedikal görüntülerde model genellemesini artırdığı deneysel olarak gösterilmiştir. Elde edilen bulgular, önerilen hibrit mimarinin sağlam özellik çıkarma kapasitesini kanıtlamakta ve gelecekteki bilgisayar destekli tanı (CAD) sistemleri için güvenilir, gerçekçi ve metodolojik açıdan şeffaf bir temel oluşturduğunu göstermektedir.

Anahtar Kelimeler

• HEp-2 Hücre Sınıflandırması
• Vision Transformer
• Hibrit Derin Öğrenme
• Otoimmün Tanı
• Topluluk Öğrenmesi

Classification of HEp-2 Cell Patterns in Autoimmune Disease Diagnosis Using Hybrid DenseNet-ViT Architecture

Öz

Background/Aim: Accurate and consistent interpretation of HEp-2 cell patterns, considered the gold standard in autoimmune disease diagnosis, remains challenging due to inter-expert variability. This study aims to develop a hybrid deep learning architecture for the automated and highly accurate classification of HEp-2 cell images. Methods: The proposed approach integrates DenseNet-121, which excels at capturing local morphological features, with Vision Transformer (ViT-B16), known for modeling global contextual relationships. These models are combined using a weighted ensemble strategy. The performance of the model was evaluated on the MIVIA (ICPR 2012) dataset under a strict source-image split protocol, which explicitly prevents the object-level data leakage frequently overlooked in the literature. Results: The proposed hybrid model achieved an overall accuracy of 96.01% under these rigorous test conditions, without the use of synthetic data augmentation. A key methodological contribution is its ability to effectively distinguish between Homogeneous and Fine Speckled patterns, which are frequently misclassified by experts. Notably, the model achieved 100% precision for the Fine Speckled class. Additionally, it was empirically demonstrated that a small batch size (Batch Size = 8) improves generalization performance in fine-textured biomedical images. Conclusion: These findings demonstrate the robust feature extraction capabilities of the proposed hybrid architecture, establishing a reliable, realistic, and methodologically transparent baseline for future computer-aided diagnosis (CAD) systems.

Anahtar Kelimeler

• HEp-2 Cell Classification
• Vision Transformer
• Hybrid Deep Learning
• Autoimmune Disease Diagnosis
• Ensemble Learning

Kaynakça

1. Wang, L., Wang, F. S., & Gershwin, M. E. (2015). Human autoimmune diseases: a comprehensive update. Journal of Internal Medicine, 278(4), 369–395. https://doi.org/10.1111/joim.12395
2. Mohamed-Ahmed, O., Shang, L., Wang, L., Chen, Z., Kartsonaki, C., & Bragg, F. (2024). Incidence and prevalence of autoimmune diseases in China: A systematic review and meta-analysis of epidemiological studies. Global Epidemiology, 8, 100158. https://doi.org/10.1016/j.gloepi.2024.100158
3. Lee, Y. H., & Song, G. G. (2024). Mortality in patients with systemic lupus erythematosus: A meta-analysis of overall and cause-specific effects. Lupus, 33(9), 929–937. https://doi.org/10.1177/09612033241257134
4. Chan, E. K. L., Damoiseaux, J., Carballo, O. G., Conrad, K., Cruvinel, W. M., Francescantonio, P. L. C., Fritzler, M. J., Garcia-De La Torre, I., Herold, M., Mimori, T., Satoh, M., von Mühlen, C. A., & Andrade, L. E. C. (2015). Report of the First International Consensus on Standardized Nomenclature of Antinuclear Antibody HEp-2 Cell Patterns 2014–2015. Frontiers in Immunology, 6, 412. https://doi.org/10.3389/fimmu.2015.00412
5. Damoiseaux, J., Andrade, L. E. C., Carballo, O. G., Conrad, K., Francescantonio, P. L. C., Fritzler, M. J., Garcia de la Torre, I., Herold, M., Klotz, W., Cruvinel, W. M., Mimori, T., von Muhlen, C., Satoh, M., & Chan, E. K. (2019). Clinical relevance of HEp-2 indirect immunofluorescent patterns: the International Consensus on ANA patterns (ICAP) perspective. Annals of the Rheumatic Diseases, 78(7), 879–889. https://doi.org/10.1136/annrheumdis-2018-214436
6. Agmon-Levin, N., Damoiseaux, J., Kallenberg, C., Sack, U., Witte, T., Herold, M., Bossuyt, X., Musset, L., Cervera, R., Plaza-Lopez, A., Dias, C., Sousa, M. J., Radice, A., Eriksson, C., Hultgren, O., Viander, M., Khamashta, M., Regenass, S., Andrade, L. E. C., Wiik, A., Tincani, A., Rönnelid, J., Bloch, D. B., Fritzler, M. J., Chan, E. K. L., Garcia-De La Torre, I., Konstantinov, K. N., Lahita, R., Wilson, M., Vainio, O., Fabien, N., Sinico, R. A., Meroni, P., & Shoenfeld, Y. (2014). International recommendations for the assessment of autoantibodies to cellular antigens referred to as anti-nuclear antibodies. Annals of the Rheumatic Diseases, 73(1), 17–23. https://doi.org/10.1136/annrheumdis-2013-203863
7. Meroni, P. L., & Schur, P. H. (2010). ANA screening: an old test with new recommendations. Annals of the Rheumatic Diseases, 69(8), 1420–1422. https://doi.org/10.1136/ard.2009.127100
8. Van Hoovels, L., Broeders, S., Chan, E. K. L., Andrade, L. E. C., de Melo Cruvinel, W., Damoiseaux, J., Viander, M., Herold, M., Coucke, W., Heijnen, I., Bogdanos, D., Calvo-Alén, J., Eriksson, C., Kozmar, A., Kuhi, L., Bonroy, C., Lauwerys, B., Schouwers, S., Lutteri, L., Vercammen, M., & Bossuyt, X. (2020). Current laboratory and clinical practices in reporting and interpreting anti-nuclear antibody indirect immunofluorescence (ANA IIF) patterns: results of an international survey. Autoimmunity Highlights, 11, 17. https://doi.org/10.1186/s13317-020-00139-9

9. Foggia, P., Percannella, G., Saggese, A., & Vento, M. (2014). Pattern recognition in stained HEp-2 cells: Where are we now? Pattern Recognition, 47(7), 2305–2314. https://doi.org/10.1016/j.patcog.2014.01.010
10. Anaam, A., Al-antari, M.A., Hussain, J., Abdel Samee, N., Alabdulhafith, M., & Gofuku, A. (2023). Deep Active Learning for Automatic Mitotic Cell Detection on HEp-2 Specimen Medical Images. Diagnostics, *13*(8), 1416. https://doi.org/10.3390/diagnostics13081416
11. Lei, H., Han, T., Zhou, F., Yu, Z., Qin, J., Elazab, A., & Lei, B. (2018). A deeply supervised residual network for HEp-2 cell classification via cross-modal transfer learning. Pattern Recognition, 79, 290–302. https://doi.org/10.1016/j.patcog.2018.02.006
12. Iwata, A., & Okuda, M. (2024). Quantifying Shape and Texture Biases for Enhancing Transfer Learning in Convolutional Neural Networks. Signals, 5(4), 721–735. https://doi.org/10.3390/signals5040040
13. Fang, K., Li, C., & Wang, J. (2023). An automatic immunofluorescence pattern classification framework for HEp-2 image based on supervised learning. Briefings in Bioinformatics, *24*(3), bbad144. https://doi.org/10.1093/bib/bbad144
14. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv, abs/2010.11929. https://doi.org/10.48550/arXiv.2010.11929
15. Liu, Y., Wen, Y., Yang, L., He, L., & Zhou, M. (2025). A General Framework for Efficient Medical Image Analysis via Shared Attention Vision Transformer. IEEE Transactions on Medical Imaging, PP(99), 1–1. https://doi.org/10.1109/TMI.2025.3644949
16. Foggia, P., Percannella, G., Soda, P., & Vento, M. (2013). Benchmarking HEp-2 Cells Classification Methods. IEEE Transactions on Medical Imaging, 32(10), 1878–1889. https://doi.org/10.1109/TMI.2013.2268163
17. Manivannan, S., Li, W., Akbar, S., Wang, R., Zhang, J., & McKenna, S. J. (2016). An automated pattern recognition system for classifying indirect immunofluorescence images of HEp-2 cells and specimens. Pattern Recognition, 51, 12–26. https://doi.org/10.1016/j.patcog.2015.09.015
18. Gao, Z., Wang, L., Zhou, L., & Zhang, J. (2017). HEp-2 Cell Image Classification With Deep Convolutional Neural Networks. IEEE Journal of Biomedical and Health Informatics, 21(2), 416–428. https://doi.org/10.1109/JBHI.2016.2526603
19. Bayramoglu, N., & Heikkilä, J. (2016). Transfer Learning for Cell Nuclei Classification in Histopathology Images. In Computer Vision – ECCV 2016 Workshops. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-319-49409-8_46
20. Rodrigues, L. F., Naldi, M. C., & Mari, J. F. (2020). Comparing convolutional neural networks and preprocessing techniques for HEp-2 cell classification in immunofluorescence images. Computers in Biology and Medicine, 116, 103542. https://doi.org/10.1016/j.compbiomed.2019.103542
21. Lei, H., Han, T., Huang, W., Kuo, J. Y., Yu, Z., He, X., & Lei, B. (2017). Cross-Modal Transfer Learning for HEp-2 Cell Classification Based on Deep Residual Network. In 2017 IEEE International Symposium on Multimedia (ISM) (pp. 465–468). IEEE. https://doi.org/10.1109/ISM.2017.92
22. Rahman, S., Wang, L., Sun, C., & Zhou, L. (2020). Deep learning based HEp-2 image classification: A comprehensive review. Medical Image Analysis, 65, 101764. https://doi.org/10.1016/j.media.2020.101764
23. Jensen, M., Al-Dulaimi, K., Abduljabbar, K.S., & Banks, J. (2023). Automated Classification of Cell Level of HEp-2 Microscopic Images Using Deep Convolutional Neural Networks-Based Diameter Distance Features. JUCS - Journal of Universal Computer Science, *29*(5), 432-445. https://doi.org/10.3897/jucs.96293
24. Chen, C. F. R., Fan, Q., & Panda, R. (2021). CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification. In *2021 IEEE/CVF International Conference on Computer Vision (ICCV)* (pp. 347–356). IEEE. https://doi.org/10.1109/ICCV48922.2021.00041
25. Takahashi, S., Sakaguchi, Y., Kouno, N., Takemura, R., Okamoto, K., & Suzuki, H. (2024). Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review. Journal of Medical Systems, 48, 84. https://doi.org/10.1007/s10916-024-02105-8
26. Wu, P., Liu, Z., Zhao, Z. et al. (2025). LCPT: A lightweight cell classification method for microscope images based on vicinityViT and channel-position attention. SIViP, *19*, 1240. https://doi.org/10.1007/s11760-025-04829-7
27. Xie, H., He, Y., Lei, H., Kuo, J., & Lei, B. (2019). Segmentation Guided HEp-2 Cell Classification with Adversarial Networks. In ComComAP (pp. 374–379). IEEE. https://doi.org/10.1109/ComComAp46287.2019.9018850
28. Chen, B., Chen, J., Lu, H., & Chen, J. (2026). Cell classification based on affine transformed convolutional parallel networks. Biomedical Signal Processing and Control, *112*(Part A), 108163. https://doi.org/10.1016/j.bspc.2025.108163
29. Hosseinzadeh Kasani, P., Hosseinzadeh Kasani, S., Kim, H. W., Cho, K. H., Jang, J. W., & Yun, C. H. (2021). HEp-2 Cell Classification Using an Ensemble of Convolutional Neural Networks. In 2021 International Conference on Information and Communication Technology Convergence (ICTC) (pp. 1–6). IEEE. https://doi.org/10.1109/ICTC52510.2021.9621075
30. Vununu, C., Lee, S. H., & Kwon, K. R. (2019). A Deep Feature Extraction Method for HEp-2 Cell Image Classification. Electronics, 8(1), 20. https://doi.org/10.3390/electronics8010020
31. Anam, A. M., Al-antari, M. A., & Gofuku, A. (2022). A Hybrid Ensemble Learning with Generative Adversarial Networks for HEp-2 Cell Image Classification. In *2022 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)* (pp. 1–5). IEEE. https://doi.org/10.1109/IECBES54088.2022.10079623
32. Zhang, L., Zhang, M. Q., & Lv, X. (2022). HEp-2 image classification using a multi-class and multiple-binary classifier. Medical & Biological Engineering & Computing, 60, 3113–3124. https://doi.org/10.1007/s11517-022-02646-5
33. Nguyen, L.D., Gao, R., Lin, D. et al. (2023). Biomedical image classification based on a feature concatenation and ensemble of deep CNNs. Journal of Ambient Intelligence and Humanized Computing, *14*, 15455–15467. https://doi.org/10.1007/s12652-019-01276-4
34. Lei, B., Zhang, T., Li, J., Qu, J., Xiong, W., Yu, K., & Yang, L. (2025). Rapidly Antibiotic Susceptibility Prediction via Deep Learning From Bacterial Fluorescence Microscopy Images. IEEE Transactions on Automation Science and Engineering, *22*, 21469-21483. https://doi.org/10.1109/TASE.2025.3607484
35. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In K. Chaudhuri & R. Salakhutdinov (Eds.), Proceedings of the 36th International Conference on Machine Learning (ICML) (Vol. 97, pp. 6105–6114). PMLR. https://proceedings.mlr.press/v97/tan19a.html
36. Khaksar Ghalati, M., Nunes, A., Ferreira, H., Serranho, P., & Bernardes, R. (2022). Texture Analysis and Its Applications in Biomedical Imaging: A Survey. IEEE Reviews in Biomedical Engineering, 15, 222–246. https://doi.org/10.1109/RBME.2021.3115703
37. Xu, X., & Li, B. (2025). Multi scale supervised entropy weighted binary pattern for texture classification. Scientific Reports, 15, 26087. https://doi.org/10.1038/s41598-025-11245-x
38. Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022). Transformers in Vision: A Survey. ACM Computing Surveys, 54(10s), 1–41. https://doi.org/10.1145/3505244
39. Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., & Zhou, Y. (2021). TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv, abs/2102.04306. https://doi.org/10.48550/arXiv.2102.04306
40. Frid-Adar, M., Diamant, I., Klang, E., Amitai, M., Goldberger, J., & Greenspan, H. (2018). GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing, 321, 321–331. https://doi.org/10.1016/j.neucom.2018.09.013
41. Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6, 60. https://doi.org/10.1186/s40537-019-0197-0
42. Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2016). Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? IEEE Transactions on Medical Imaging, 35(5), 1299–1312. https://doi.org/10.1109/TMI.2016.2535302
43. Masters, D., & Luschi, C. (2018). Revisiting Small Batch Training for Deep Neural Networks. arXiv, abs/1804.07612. https://arxiv.org/abs/1804.07612
44. Keskar, N. S., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P. T. P. (2017). On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. arXiv, abs/1609.04836. https://arxiv.org/abs/1609.04836
45. Montavon, G., Orr, G. B., & Müller, K. R. (Eds.). (2012). Neural Networks: Tricks of the Trade (2nd ed.). Lecture Notes in Computer Science (Vol. 7700). Springer. https://doi.org/10.1007/978-3-642-35289-8
46. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 618–626). IEEE. https://doi.org/10.1109/ICCV.2017.74
47. Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., Ourselin, S., Sheller, M., Summers, R. M., Trask, A., Xu, D., Baust, M., & Cardoso, M. J. (2020). The future of digital health with federated learning. npj Digital Medicine, 3, 119. https://doi.org/10.1038/s41746-020-00323-1