EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Perbandingan Teknik Prapemrosesan Citra terhadap Akurasi CNN dalam Deteksi Diabetic Retinopathy

Nurul Maulidiyah, I Gde Eka Dirgayussa, Rafli Filano, Yusuf Maulana

Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi · 04.05.2026 · 6 (2) · 749-762

DOI: 10.67142/edutik.v6i2.341 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi, online erschienen am 04.05.2026. Verfasst von Nurul Maulidiyah und 3 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic Retinopathy (DR) is a diabetes complication and the leading cause of blindness in the working-age population, affecting more than 93 million people worldwide. The quality of retinal fundus images is significantly affected by lighting conditions and contrast, making image preprocessing a critical factor that influences the accuracy of deep learning-based detection models. This study aims to compare the effect of four preprocessing techniques—original images, color Histogram Equalization (HE), grayscale HE, and Color Constancy—on the performance of a Convolutional Neural Network (CNN) based on the AlexNet architecture for DR detection. The APTOS 2019 Kaggle dataset was used, comprising 3,722 color retinal fundus images: 1,830 non-DR and 1,892 DR images. Model validation was performed using 10-Fold Cross Validation, and performance was evaluated using confusion matrix, ROC curve, accuracy, sensitivity, and specificity. Results show that original images yielded the best overall performance with accuracy of 96.10%, sensitivity of 97.98%, specificity of 94.29%, and AUC of 0.994. Grayscale HE produced the highest AUC (0.996), while Color Constancy had the lowest AUC (0.989). These findings indicate that color information in fundus images contains important discriminative features, and preprocessing does not always improve overall accuracy. The AlexNet model shows potential for implementation as a DR screening system based on Computer-Aided Diagnosis (CAD) with relatively low computational complexity

Zitieren

APA

Maulidiyah, N., Dirgayussa, I. G. E., Filano, R., & Maulana, Y. (2026). Perbandingan Teknik Prapemrosesan Citra terhadap Akurasi CNN dalam Deteksi Diabetic Retinopathy. Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi, 6(2), 749-762. https://doi.org/10.67142/edutik.v6i2.341

Vancouver

Maulidiyah N, Dirgayussa IGE, Filano R, Maulana Y. Perbandingan Teknik Prapemrosesan Citra terhadap Akurasi CNN dalam Deteksi Diabetic Retinopathy. Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi. 2026;6(2):749-762. doi:10.67142/edutik.v6i2.341

BibTeX
@article{Maulidiyah2026,
  author = {Maulidiyah, Nurul and Dirgayussa, I Gde Eka and Filano, Rafli and Maulana, Yusuf},
  title = {Perbandingan Teknik Prapemrosesan Citra terhadap Akurasi CNN dalam Deteksi Diabetic Retinopathy},
  journal = {Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {749--762},
  doi = {10.67142/edutik.v6i2.341}
}
Kostenlos starten →