Deep adaptive feature blending system for automated nail disease detection

⁶ Department of Computer Engineering and Information, College of Engineering - Wadi Addawasir, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia

IJOCTA, 026090032 https://doi.org/10.36922/IJOCTA026090032

Received: 27 February 2026 | Revised: 13 April 2026 | Accepted: 13 April 2026 | Published online: 2 July 2026

© 2026 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )

Download PDF

XML

Cite

Abstract

Nail diseases present significant diagnostic challenges due to their wide variability invisual appearance, overlapping morphological characteristics, and often subtle earlystagesymptoms. Conventional diagnosis largely relies on subjective assessment bydermatology specialists, which can be time-consuming and prone to inter-observervariability. This limitation is particularly critical for serious conditions such asacral lentiginous melanoma, where delayed or inaccurate detection may lead tosuboptimal clinical outcomes. To address these challenges, this study proposes a deeplearning framework termed deep adaptive feature blending (DAFB). The approachintegrates the EfficientNetV2-S architecture with an AFB module that recalibratesdiscriminative features to improve classification performance. The AFB mechanismemploys a dual-path attention strategy that emphasizes salient visual patterns whilesuppressing noise and irrelevant artifacts commonly present in dermatoscopic nailimagery. When evaluated on a multi-class nail disease dataset, the DAFB modelachieved a validation accuracy of 97.8%, demonstrating strong performance acrossall disease categories. Experimental results indicate that the framework is effectivein distinguishing between morphologically similar conditions while maintainingcomputational efficiency. However, given the limited dataset size and lack of externalvalidation, these results should be interpreted as preliminary. Overall, the proposedapproach shows promising potential as a research-oriented tool for automated naildisease classification, warranting further validation on larger, more diverse clinicaldatasets.

Keywords

Nail disease detection

Adaptive feature blending

Medical imaging

Transfer learning

References

1. Alharbi LA. Artificial Rabbits Optimizer With Machine Learning Based Emergency Department Monitoring and Medical Data Classification at KSA Hospitals. IEEE Access. 2023;11:59133-59141. https://www.doi.org/10.1109/access.2023.3284390

2. Alanazi AS, Mezher MA. Using Machine Learning Algorithms for Prediction of Diabetes Mellitus. In: Proceedings of the 2020 International Conference on Computing and Information Technology(ICCIT-1441). IEEE; 2020:1-3. https://www.doi.org/10.1109/iccit-144147971.2020.9213708

3. Manimurugan S, Al-Mutairi S, Aborokbah MM, Chilamkurti N, Ganesan S, Patan R. Effective Attack Detection in Internet of Medical Things Smart Environment Using a Deep Belief Neural Network. IEEE Access. 2020;8:77396-77404. https://www.doi.org/10.1109/access.2020.2986013

4. Taouali O, Bacha S, Ben Abdellafou K, et al. Intelligent Intrusion Detection System for the Internet of Medical Things Based on Data-Driven Techniques. Comput Syst Sci Eng. 2023;47(2):1593-1609. https://www.doi.org/10.32604/csse.2023.039984

5. Sechi A, Wortsman X, Tosti A, Iorizzo M. Advances in image‐based diagnosis of nail disorders. Acad Dermatol Venereol. 2024;39(4):759-774. https://www.doi.org/10.1111/jdv.20309

6. Almutairi SM, Manimurugan S, Aborokbah MM, Narmatha C, Ganesan S, Karthikeyan P. An Efficient USE‐Net Deep Learning Model for Cancer Detection. Int J Intell Syst. 2023;2023(1),8509433. https://www.doi.org/10.1155/2023/8509433

7. Hamim MA, Sajim SH, Ur Rahman F, Tanmoy FM. Multiple Skin-Disease Classification Based on Machine Vision Using Transfer Learning Approach. In: Proceedings of the 2023 14thInternational Conference on Computing Communication and Networking Technologies (ICCCNT). IEEE; 2023:1-8. https://www.doi.org/10.1109/icccnt56998.2023.10307018

8. Gaurav V, Grover C, Tyagi M, Saurabh S. Artificial Intelligence in Diagnosis and Management of Nail Disorders: A Narrative Review. Indian Dermatol Online J. 2024;16(1):40-49. https://www.doi.org/10.4103/idoj.idoj_460_24

9. Wang Z, Jiang JX, Wang HR, Zhou L, Li Y. Localized Adaptive Style Mixing for feature statistics manipulation in medical image translation with limited Data. Expert Syst Appl. 2025;277:127217. https://www.doi.org/10.1016/j.eswa.2025.127217

10. Xu Y, Zhang T. Boundless Across Domains: ANew Paradigm of Adaptive Feature and Cross-Attention for Domain Generalization in Medical Image Segmentation. arXiv. https://www.doi.org/10.48550/ARXIV.2411.14883

11. Zhao H, Zhang X, Gao Y, et al. Diagnostic performance of EfficientNetV2-S method for staging liver fibrosis based on multi parametric MRI. Heliyon. 2024;10(15):e35115. https://www.doi.org/10.1016/j.heliyon.2024.e35115

12. Al Moteri M, Mahesh TR, Thakur A, Vinoth Kumar V, Khan SB, Alojail M. Enhancing accessibility for improved diagnosis with modifiedEfficientNetV2-S and cyclic learning rate strategy in women with disabilities and breast cancer. Front Med. 2024;11. https://www.doi.org/10.3389/fmed.2024.1373244

13. Zhao J, Feng X, Tran MK, Fowler M, Ouyang M, Burke AF. Battery safety: Fault diagnosis from laboratory to real world. J Power Sources. 2024;598:234111. https://www.doi.org/10.1016/j.jpowsour.2024.234111

14. Hassan E, Saber A, Elbedwehy S. Knowledge distillation model for Acute Lymphoblastic Leukemia Detection: Exploring the impact of nesterov-accelerated adaptive moment estimation optimizer. Biomed Signal Process Control.2024;94:106246.

15. Elbedwehy S, Hassan E, Saber A, Elmonier R. Integrating neural networks with advanced optimization techniques for accurate kidney disease diagnosis. Sci Rep. 2024;14(1). https://www.doi.org/10.1038/s41598-024-71410-6

16. Shandilya G, Gupta S, Bharany S, et al. Autonomous detection of nail disorders using a hybrid capsule CNN: a novel deep learning approach for early diagnosis. BMC Med Inform Decis Mak. 2024;24(1). https://www.doi.org/10.1186/s12911-024-02840-5

17. Hadiyoso S, Aulia S. Classification of Koilonychia, Beaus Lines, and Leukonychia based on Nail Image using Transfer Learning VGG-16. JRE. 2022;18(2). https://www.doi.org/10.17529/jre.v18i2.25694

18. Saber A, Elbedwehy S, Awad WA, Hassan E.An optimized ensemble model based on metaheuristic algorithms for effective detection and classification of breast tumors. Neural ComputAppl. 2024;37(6):4881-4894. https://www.doi.org/10.1007/s00521-024-10719-9

19. Ardianto R, Yusuf D, Sumantri RBB, Febrina D, Al-Hakim RR, Ariyanto ASS. Bioinformatics driven deep learning for nail disease diagnosis: A novel approach to improve healthcare outcomes. BIO Web Conf. 2025;152:01024. https://www.doi.org/10.1051/bioconf/202515201024

20. Hussain M, Fiza M, Khalil A, et al. Transfer learning-based quantized deep learning models for nail melanoma classification. Neural Comput Appl. 2023;35(30):22163-22178. https://www.doi.org/10.1007/s00521-023-08925-y

21. Krizhevsky A, Sutskever I, Hinton GE. Image Net Classification with Deep Convolutional Neural Networks. In: Proceedings of the NIPS’12: Proceedings of the 26th International Conference on Neural Information Processing Systems -Volume 1. 2012;60(6):84-90.

22. Ren Q, Wang Y, Xu J, Hou F, Cui G, Ding G.REN-GAN: Generative adversarial network driven rebar clutter elimination network in GPR image for tunnel defect identification. Expert Syst Appl. 2024;255:124395. https://www.doi.org/10.1016/j.eswa.2024.124395

23. Zarpalas D, Gkontra P, Daras P, Maglaveras N. Segmentation through a local and adaptive weighting scheme, for contour-based blending of image and prior information. In: Proceedings of the 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).IEEE; 2012:1-4. https://www.doi.org/10.1109/cbms.2012.6266319

24. Abd El-Aziz AA, Mahmood MA, Abd El-GhanyS. A Robust EfficientNetV2-S Classifier for Predicting Acute Lymphoblastic Leukemia Based on Cross Validation. Symmetry. 2024;17(1):24. https://www.doi.org/10.3390/sym17010024

25. Cheng R, Razani R, Taghavi E, Li E, Liu B.(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network. In: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE;2021:12542-12551. https://www.doi.org/10.1109/cvpr46437.2021.01236

26. Liu T, Luo R, Xu L, et al. Spatial Channel Attention for Deep Convolutional Neural Networks. Mathematics. 2022;10(10):1750. https://www.doi.org/10.3390/math10101750

27. Alnaggar MH, El-Dosuky MA, Rashad MZ. A Novel Multimodal Biometric Template Security Based on Nano-Scale Reaction-Diffusion Morphogenesis. J Comput Theor Nanosci. 2018;15(6):1979-1982. https://www.doi.org/10.1166/jctn.2018.7522

28. Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv. 2015. https://arxiv.org/abs/1503.02531

29. Yousef Saleh Al Alawi, Albalawi IAJ, AlamraniSAS, et al. Knowledge of diabetic foot care management among medical students at Tabuk University, Tabuk, Saudi Arabia. SMHJ.2023;3(2):58-71. https://www.doi.org/10.54293/smhj.v3i2.73

30. Alqahtani M, Alanazi A, Elbadawi A, Qahtani A, Alqahtani M, Alanazi A. Prevalent and risk factors of depression among Saudi medical residents in the Tabuk City, Saudi Arabia. IJMDC. 2024:2347-2351. https://www.doi.org/10.24911/ijmdc.51-1726583030

31. Alatawi MN. Machine Learning-Based Usage Evaluation Strategy for Mobile E-Learning Systems in KSA Institutions. In: Proceedings of the 2023 3rd International Conference on Computing and Information Technology (ICCIT).IEEE; 2023:510-516. https://www.doi.org/10.1109/iccit58132.2023.10273888

32. Almasoudi FM. Grid Distribution Fault Occurrence and Remedial Measures Prediction/Forecasting through Different Deep Learning Neural Networks by Using Real Time Data from Tabuk City Power Grid. Energies. 2023;16(3):1026. https://www.doi.org/10.3390/en1603102624

33. Ibrahim M, Ali M, Ahmed M, et al. A Low-Cost Approach for Drowning Detection and Alertness. Egypt J Artif Intell. 2024;3(1):0-0. https://www.doi.org/10.21608/ejai.2024.223796.1012

34. Hassan E, Bhatnagar R, Shams MY. Advancing Scientific Research in Computer Science by ChatGPT and LLaMA—A Review. In: Smart Innovation, Systems and Technologies. Singapore: Springer Nature; 2023:23-37. https://www.doi.org/10.1007/978-981-99-6774-2_3

35. Hassan E, El-Rashidy N, Elbedwehy S, AbdEl-Hafeez T, Saber A, Shams MY. Exploring the frontiers of image super-resolution: a review of modern techniques and emerging applications. Neural Comput Appl. 2025;37(22):17913-17961. https://www.doi.org/10.1007/s00521-025-11331-1

36. Hassan E, Bhatnagar R, El-Hafeez TA, Shams MY. Detection of Suicide and Depression forEarly Intervention and Initiative-taking Mental Healthcare. In: Proceedings of the 2025 7thInternational Conference on Signal Processing, Computing and Control (ISPCC). IEEE; 2025:99-104. https://www.doi.org/10.1109/ispcc66872.2025.11039547

37. Shams MY, Hassan E, Gamil S, et al. Skin Disease Classification: A Comparison of ResNet50, MobileNet, and Efficient-B0. J Curr Multidiscip Res. 2025;1(1):1-7. https://www.doi.org/10.21608/jcmr.2025.327880.1002

38. Saber A, Hassan E, Elbedwehy S, Awad WA, Emara TZ. Leveraging ensemble convolutional neural networks and meta heuristic strategies for advanced kidney disease screening andclassification. Sci Rep. 2025;15(1). https://www.doi.org/10.1038/s41598-025-93950-1

39. Marode TP, Bhangdiya VK, Nemane S, et al. Artificial Intelligence Meets Nail Diagnostics: Emerging Image-Based Sensing Platforms for Non-Invasive Disease Detection. Bioengineering. 2026;13(1):75. https://www.doi.org/10.3390/bioengineering13010075

40. Zhou P, Xie X, Lin Z, Yan S. Towards Understanding Convergence and Generalization of Adam W. IEEE Trans Pattern Anal Mach Intell. 2024;46(9):6486-6493. https://www.doi.org/10.1109/tpami.2024.3382294

41. Eisa MM, Alnaggar MH. Hybrid Rough-Genetic Classification Model for IoT Heart Disease Monitoring System. In: Lecture Notes in Networks and Systems. Singapore: Springer; 2021:437-451. https://www.doi.org/10.1007/978-981-16-2275-5_27

42. Abdella M, Hawash A, Zahran O, et al. Smart Tour Guide: A Novel Artificial Intelligence Systemfor Replacing Human Guides in Cultural Heritage Sites. Egypt J Artif Intell. 2024;3(1):0-0. https://www.doi.org/10.21608/ejai.2024.226751.1017

43. Abbas S, Alsubai S, Haque MIU, et al. Active Machine Learning for Heterogeneity Activity Recognition Through Smartwatch Sensors. IEEE Access. 2024;12:22595-22607. https://www.doi.org/10.1109/access.2024.3362676

44. Almurtadha Y, Mohammed OS, Mirghani H, Ghaleb M. Investigating the Relationship Between Medicine Student’s Lifestyle and Their Academic Performance. In: Lecture Notes in Networks and Systems. Springer International Publishing; 2021:455-464. https://www.doi.org/10.1007/978-3-030-85990-9_37

45. Hassan Abbas Gondal C, Irfan M, Shafique S, Salman Bashir M, Ahmed M, M. Alshehri O, et al. Automated Leukemia Screening and Sub-types Classification Using Deep Learning. Comput Syst Sci Eng. 2023;46(3):3541-3558. https://www.doi.org/10.32604/csse.2023.036476

Previous article in this issue

Next article in this issue

An International Journal of Optimization and Control: Theories & Applications, Electronic ISSN: 2146-5703 Print ISSN: 2146-0957, Published by AccScience Publishing