EUVIMEDEUVIMED entdecken
Crossref

Deep adaptive feature blending system for automated nail disease detection

Nora Elrashidy, Eman Allogmani, Samar Elbedwehy, Jawhara Aljabri, Rana Albelaihi, Esraa Hasan, Zahraa Tarek

An International Journal of Optimization and Control: Theories & Applications (IJOCTA) · 02.07.2026 · 16 (4) · 1489

DOI: 10.36922/ijocta026090032 ↗

Kurz gefasst

Fachartikel in der Zeitschrift An International Journal of Optimization and Control: Theories & Applications (IJOCTA), online erschienen am 02.07.2026. Verfasst von Nora Elrashidy und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Elrashidy, N., Allogmani, E., Elbedwehy, S., Aljabri, J., Albelaihi, R., Hasan, E., & Tarek, Z. (2026). Deep adaptive feature blending system for automated nail disease detection. An International Journal of Optimization and Control: Theories & Applications (IJOCTA), 16(4), 1489. https://doi.org/10.36922/ijocta026090032

Vancouver

Elrashidy N, Allogmani E, Elbedwehy S, Aljabri J, Albelaihi R, Hasan E, et al. Deep adaptive feature blending system for automated nail disease detection. An International Journal of Optimization and Control: Theories & Applications (IJOCTA). 2026;16(4):1489. doi:10.36922/ijocta026090032

BibTeX
@article{Elrashidy2026,
  author = {Elrashidy, Nora and Allogmani, Eman and Elbedwehy, Samar and Aljabri, Jawhara and Albelaihi, Rana and Hasan, Esraa and Tarek, Zahraa},
  title = {Deep adaptive feature blending system for automated nail disease detection},
  journal = {An International Journal of Optimization and Control: Theories & Applications (IJOCTA)},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {1489},
  doi = {10.36922/ijocta026090032}
}
Kostenlos starten →