SavedAdd your journal

Journals / Mühendislik Bilimleri ve Araştırmaları Dergisi / 2026 / Cilt: 8 Sayı: 2

A Novel Deep Learning-Based Approach for Automatic Determination of Acute Kidney Injury Stage in Pathology Images

Patoloji Görüntülerinde Akut Böbrek Hasarı Evresinin Otomatik Belirlenmesi için Derin Öğrenme Tabanlı Yeni Bir Yaklaşım

Fatma Tuana Doğu(KARADENİZ TEKNİK ÜNİVERSİTESİ, FEN BİLİMLERİ ENSTİTÜSÜ, ELEKTRONİK MÜHENDİSLİĞİ (YL) (TEZLİ))0009-0008-0916-9394
Mehmet Öztürk(KARADENİZ TEKNİK ÜNİVERSİTESİ)0000-0002-8535-3088
Hülya Doğan(KARADENİZ TEKNİK ÜNİVERSİTESİ)0000-0003-3695-8539
Pages
135–144
Publication Date
2026-10-27
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results obtained demonstrate that the proposed approach offers high performance compared to studies in the literature and has the potential for standardization in clinical decision support processes.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Kidney diseases are a critical health problem that is widespread globally and difficult to diagnose early.
📊
Key Findings & Data:The proposed deep learning-based approach combines multi-scale feature extraction and attention mechanisms, achieving an accuracy of 0.7668 and a macro F1-score of 0.7252 according to experimental results.
💡
Conclusion & Impact:The results obtained demonstrate that the proposed approach offers high performance compared to studies in the literature and has the potential for standardization in clinical decision support processes.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Derin öğrenme · Patoloji görüntüleri · Akut böbrek hasarı

Abstract

Kidney diseases are a critical health problem that is widespread globally and difficult to diagnose early. The pathological examination process of kidney biopsies is complicated by the fact that it depends on the experience of the specialist and is time-consuming. Various image analysis approaches exist in the literature, but there is a gap in the field regarding the automated determination of acute kidney injury (AKI) stages using deep learning. This study presents a deep learning approach that can automatically determine AKI stages from pathology images. The proposed deep learning-based approach combines multi-scale feature extraction and attention mechanisms, achieving an accuracy of 0.7668 and a macro F1-score of 0.7252 according to experimental results. The results obtained demonstrate that the proposed approach offers high performance compared to studies in the literature and has the potential for standardization in clinical decision support processes.

Özet

Böbrek hastalıkları, dünya genelinde yaygın görülen ve erken teşhisi zor olan kritik bir sağlık sorunudur. Böbrek biyopsilerinin patolojik inceleme süreci, uzmanın deneyimine bağlı olması ve zaman alması nedeniyle tanı sürecini zorlaştırmaktadır. Literatürde çeşitli görüntü analizi yaklaşımları bulunmaktadır ancak derin öğrenme ile akut böbrek hasarı (ABH) evrelerinin otomatik belirlenmesine yönelik bir boşluk mevcuttur. Bu çalışma, ABH evrelerini patoloji görüntülerinden otomatik olarak belirleyebilen bir derin öğrenme yaklaşımı sunmaktadır. Önerilen derin öğrenme tabanlı yaklaşım, çok ölçekli özellik çıkarımı ve dikkat mekanizmalarını bir araya getirerek deneysel sonuçlara göre 0.7668 doğruluk ve 0.7252 makro F1-skoru elde etmektedir. Elde edilen sonuçlar, önerilen yaklaşımın literatürdeki çalışmalara kıyasla yüksek bir performans sunduğunu ve klinik karar destek süreçlerinde standardizasyon potansiyeli taşıdığını göstermektedir.

🔖

Cite This Article

Doğu, F. T., Öztürk, M., Doğan, H. (2026). A Novel Deep Learning-Based Approach for Automatic Determination of Acute Kidney Injury Stage in Pathology Images. Mühendislik Bilimleri ve Araştırmaları Dergisi, Cilt: 8 Sayı: 2, 135–144. https://doi.org/10.46387/bjesr.1905905

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (22)

  1. World Health Organization. (2024, Aug.). The top 10 causes of death. WHO [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death
  2. S. Hacking and V. Bijol, “Deep learning for the classification of medical kidney disease: a pilot study for electron microscopy,” Ultrastruct. Pathol., vol. 45, no. 2, pp. 118–127, Mar. 2021.
  3. P. Chagas, L. Souza, I. Araújo, N. Aldeman, A. Duarte, M. Angelo, and L. Oliveira, “Classification of glomerular hypercellularity using convolutional features and support vector machine,” Artif. Intell. Med., vol. 103, pp. 101808, Mar. 2020.
  4. Q. Zheng, R. Yang, H. Xu, J. Fan, P. Jiao, X. Ni, and X. Liu, “A weakly supervised deep learning model and human–machine fusion for accurate grading of renal cell carcinoma from histopathology slides,” Cancers, vol. 15, no. 12, pp. 3198, Jun. 2023.
  5. S. Shubham, N. Jain, V. Gupta, S. Mohan, M. M. Ariffin, and A. Ahmadian, “Identify glomeruli in human kidney tissue images using a deep learning approach,” Soft Comput., vol. 27, no. 5, pp. 2705–2716, Mar. 2023.
  6. N. Bouteldja, B. M. Klinkhammer, R. D. Bülow, P. Droste, S. W. Otten, S. F. von Stillfried, and D. Merhof, “Deep learning–based segmentation and quantification in experimental kidney histopathology,” J. Am. Soc. Nephrol., vol. 32, no. 1, pp. 52–68, Jan. 2021.
  7. T. T. U. Nguyen, A. T. Nguyen, H. Kim, Y. J. Jung, W. Park, K. M. Kim, and W. Kim, “Deep-learning model for evaluating histopathology of acute renal tubular injury,” Sci. Rep., vol. 14, no. 1, pp. 9010, Apr. 2024.
  8. Y. Zheng, C. A. Cassol, S. Jung, D. Veerapaneni, V. C. Chitalia, K. Y. Ren, and V. B. Kolachalama, “Deep-learning–driven quantification of interstitial fibrosis in digitized kidney biopsies,” Am. J. Pathol., vol. 191, no. 8, pp. 1442–1453, Aug. 2021.
  9. J. N. Marsh, T. C. Liu, P. C. Wilson, S. J. Swamidass, and J. P. Gaut, “Development and validation of a deep learning model to quantify glomerulosclerosis in kidney biopsy specimens,” JAMA Netw. Open, vol. 4, no. 1, pp. e2030939, Jan. 2021.
  10. C. F. Juang, Y. W. Chuang, G. W. Lin, I. F. Chung, and Y. C. Lo, “Deep learning-based glomerulus detection and classification with generative morphology augmentation in renal pathology images,” Comput. Med. Imaging Graph., vol. 115, pp. 102375, Jul. 2024.
  11. N. Tomašev et al., “A clinically applicable approach to continuous prediction of future acute kidney injury,” Nature, vol. 572, no. 7767, pp. 116–119, Aug. 2019.
  12. S. Yue, S. Li, X. Huang, J. Liu, X. Hou, Y. Zhao, D. Niu, Y. Wang, W. Tan, and J. Wu, “Machine learning for the prediction of acute kidney injury in patients with sepsis,” J. Transl. Med., vol. 20, no. 1, pp. 215, May. 2022.
  13. J. He, J. Lin, and M. Duan, “Application of machine learning to predict acute kidney disease in patients with sepsis associated acute kidney injury,” Front. Med., vol. 8, pp. 792974, Dec. 2021.
  14. Kidney Precision Medicine Project. (2026, Feb.). KPMP Atlas Repository [Online]. Available: https://atlas.kpmp.org/repository/
  15. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. Miami, USA, 2009.
  16. C. Szegedy et al., “Going deeper with convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9. Boston, USA, 2015.
  17. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. Las Vegas, USA, 2016.
  18. S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, (2017, Nov.). “Aggregated residual transformations for deep neural networks.” arXiv [Online]. Available: https://arxiv.org/abs/1611.05431.
  19. F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer. (2016, Feb.). "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size." arXiv [Online]. Available: https://arxiv.org/abs/1602.07360.
  20. N. Ma, X. Zhang, H.-T. Zheng, and J. Sun, “ShuffleNet V2: Practical guidelines for efficient CNN architecture design,” in Proceedings of the European Conference on Computer Vision (ECCV), pp. 116–131. Munich, Germany, 2018.
  21. A. G. Howard et al. (2017, Apr.). “MobileNets: Efficient convolutional neural networks for mobile vision applications,” arXiv [Online]. Available: https://arxiv.org/abs/1704.04861
  22. M. Tan and Q. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proceedings of the International Conference on Machine Learning (ICML), pp. 6105–6114. Long Beach, USA, 2019.