EUVIMEDEUVIMED entdecken
Crossref

Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G

Wei Xiang Lim, Zhiyuan Chen

Medical & Biological Engineering & Computing · 2024

DOI: 10.1007/s11517-024-03093-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2024. Verfasst von Wei Xiang Lim und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Science and Engineering, School of Computer Science, University of Nottingham Malaysia, Semenyih, Malaysia. Hauptthemen laut MEDLINE: Diabetic Retinopathy, Deep Learning, Fundus Oculi, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic retinopathy disease contains lesions (e.g., exudates, hemorrhages, and microaneurysms) that are minute to the naked eye. Determining the lesions at pixel level poses a challenge as each pixel does not reflect any semantic entities. Furthermore, the computational cost of inspecting each pixel is expensive because the number of pixels is high even at low resolution. In this work, we propose a hybrid image processing method. Simple Linear Iterative Clustering with Gaussian Filter (SLIC-G) for the purpose of overcoming pixel constraints. The SLIC-G image processing method is divided into two stages: (1) simple linear iterative clustering superpixel segmentation and (2) Gaussian smoothing operation. In such a way, a large number of new transformed datasets are generated and then used for model training. Finally, two performance evaluation metrics that are suitable for imbalanced diabetic retinopathy datasets were used to validate the effectiveness of the proposed SLIC-G. The results indicate that, in comparison to prior published works' results, the proposed SLIC-G shows better performance on image classification of class imbalanced diabetic retinopathy datasets. This research reveals the importance of image processing and how it influences the performance of deep learning networks. The proposed SLIC-G enhances pre-trained network performance by eliminating the local redundancy of an image, which preserves local structures, but avoids over-segmented, noisy clips. It closes the research gap by introducing the use of superpixel segmentation and Gaussian smoothing operation as image processing methods in diabetic retinopathy-related tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetic RetinopathyDeep LearningFundus OculiImage Processing, Computer-AssistedHumansAlgorithmsNeural Networks, ComputerPhotographyImage Interpretation, Computer-AssistedNormal Distribution

Stichwörter der Autor:innen

Diabetic retinopathyImage classificationImage processingSLIC superpixel segmentationTransfer learning

Autor:innen und Institutionen

  • Faculty of Science and Engineering, School of Computer Science, University of Nottingham Malaysia, Semenyih, Malaysia.
  • Faculty of Science and Engineering, School of Computer Science, University of Nottingham Malaysia, Semenyih, Malaysia. zhiyuan.chen@nottingham.edu.my.

Zitieren

APA

Lim, W. X., & Chen, Z. (2024). Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-024-03093-0

Vancouver

Lim WX, Chen Z. Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G. Medical & Biological Engineering & Computing. 2024. doi:10.1007/s11517-024-03093-0

BibTeX
@article{Lim2024,
  author = {Lim, Wei Xiang and Chen, Zhiyuan},
  title = {Enhancing deep learning pre-trained networks on diabetic retinopathy fundus photographs with SLIC-G},
  journal = {Medical & Biological Engineering & Computing},
  year = {2024},
  doi = {10.1007/s11517-024-03093-0}
}
Kostenlos starten →