EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MidFusionEfficientV2: Improving Ophthalmic Diagnosis with Mid-Level RGB–LBP Fusion and SE Attention

Julide Kurt Keles, Soner Kiziloluk iD, Eser Sert iD, Furkan Talo iD, Muhammed Yildirim iD

Journal of Clinical Medicine · 19.03.2026 · 15 (6) · 2352

DOI: 10.3390/jcm15062352 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 19.03.2026. Verfasst von Julide Kurt Keles und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Eye Clinic, Elazig Fethi Sekin City Hospital, Elazig 23300, Türkiye. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Early diagnosis of eye diseases is critically important for enhancing individuals’ quality of life and reducing the risk of vision loss. In this study, a deep learning-based hybrid model called MidFusionEfficientV2 has been proposed to classify eye diseases, including uveitis, conjunctivitis, cataract, eyelid drooping, and normal conditions.

Methods

The model presents a dual-branch architecture that combines an RGB image branch with an EfficientNetV2-S architecture and a specialized texture branch based on Local Binary Pattern (LBP) transformation at an intermediate level. Thanks to the Squeeze-and-Excitation (SE) blocks integrated into the LBP branch, channel-based attention mechanisms have been activated, enhancing the prominence of textural features. The features obtained from the RGB and LBP branches were combined at an intermediate level and transferred to the classification stage.

Results

Experimental studies on the five-class eye disease dataset from the Mendeley Data platform have shown that the proposed model outperformed six strong models (ResNetV2, ConvNeXt, DenseNet-121, EfficientNet-B1, MobileNetV3 Large, and EfficientNetV2-S) with an accuracy of 98%. Especially in the difficult-to-diagnose uveitis class, recall and F1 scores of 97% and 94%, respectively, were achieved.

Conclusions

The results show that a moderate combination of color and texture features significantly improves classification performance, and that MidFusionEfficientV2 offers a reliable and effective solution for the automatic diagnosis of eye diseases.

Schlagwörter

Stichwörter der Autor:innen

EfficientNetV2-SLocal Binary Pattern (LBP)Squeeze-and-Excitationdeep learningeye diseases

Autor:innen und Institutionen

  • Department of Eye Clinic, Elazig Fethi Sekin City Hospital, Elazig 23300, Türkiye.
  • Department of Computer Engineering, Malatya Turgut Ozal University, Malatya 44200, Türkiye.
  • Department of Computer Engineering, Firat University, Elazig 23119, Türkiye.
  • Department of Artificial Intelligence and Data Engineering, Firat University, Elazig 23119, Türkiye.

ORCID-Profile: Soner Kiziloluk, Eser Sert, Furkan Talo, Muhammed Yildirim

Zitieren

APA

Keles, J. K., Kiziloluk, S., Sert, E., Talo, F., & Yildirim, M. (2026). MidFusionEfficientV2: Improving Ophthalmic Diagnosis with Mid-Level RGB–LBP Fusion and SE Attention. Journal of Clinical Medicine, 15(6), 2352. https://doi.org/10.3390/jcm15062352

Vancouver

Keles JK, Kiziloluk S, Sert E, Talo F, Yildirim M. MidFusionEfficientV2: Improving Ophthalmic Diagnosis with Mid-Level RGB–LBP Fusion and SE Attention. Journal of Clinical Medicine. 2026;15(6):2352. doi:10.3390/jcm15062352

BibTeX
@article{Keles2026,
  author = {Keles, Julide Kurt and Kiziloluk, Soner and Sert, Eser and Talo, Furkan and Yildirim, Muhammed},
  title = {MidFusionEfficientV2: Improving Ophthalmic Diagnosis with Mid-Level RGB–LBP Fusion and SE Attention},
  journal = {Journal of Clinical Medicine},
  year = {2026},
  volume = {15},
  number = {6},
  pages = {2352},
  doi = {10.3390/jcm15062352}
}
Kostenlos starten →