EUVIMEDEUVIMED entdecken
Open Access

Multi-dimensional dense attention network for pixel-wise segmentation of optic disc in colour fundus images

Sreema Ma, Jayachandran A, Sudarson Rama Perumal T

Technology and Health Care · 2024

DOI: 10.3233/thc-230310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology and Health Care, 2024. Verfasst von Sreema Ma und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Communication Engineering, Arunachala College of Engineering for Women, Manavilai, India. Hauptthemen laut MEDLINE: Optic Disk, Deep Learning. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Segmentation of retinal fragments like blood vessels, Optic Disc (OD), and Optic Cup (OC) enables the early detection of different retinal pathologies like Diabetic Retinopathy (DR), Glaucoma, etc. OBJECTIVE: Accurate segmentation of OD remains challenging due to blurred boundaries, vessel occlusion, and other distractions and limitations. These days, deep learning is rapidly progressing in the segmentation of image pixels, and a number of network models have been proposed for end-to-end image segmentation. However, there are still certain limitations, such as limited ability to represent context, inadequate feature processing, limited receptive field, etc., which lead to the loss of local details and blurred boundaries. METHODS: A multi-dimensional dense attention network, or MDDA-Net, is proposed for pixel-wise segmentation of OD in retinal images in order to address the aforementioned issues and produce more thorough and accurate segmentation results. In order to acquire powerful contexts when faced with limited context representation capabilities, a dense attention block is recommended. A triple-attention (TA) block is introduced in order to better extract the relationship between pixels and obtain more comprehensive information, with the goal of addressing the insufficient feature processing. In the meantime, a multi-scale context fusion (MCF) is suggested for acquiring the multi-scale contexts through context improvement. RESULTS: Specifically, we provide a thorough assessment of the suggested approach on three difficult datasets. In the MESSIDOR and ORIGA data sets, the suggested MDDA-NET approach obtains accuracy levels of 99.28% and 98.95%, respectively. CONCLUSION: The experimental results show that the MDDA-Net can obtain better performance than state-of-the-art deep learning models under the same environmental conditions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Optic DiskDeep LearningHumansFundus OculiDiabetic RetinopathyGlaucomaNeural Networks, ComputerImage Processing, Computer-AssistedImage Interpretation, Computer-Assisted

Stichwörter der Autor:innen

Deep learningdense prediction networksfundus imagessegmentation

Autor:innen und Institutionen

  • Department of Electronics and Communication Engineering, Arunachala College of Engineering for Women, Manavilai, India.
  • Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli, India.
  • Department of Computer Science and Engineering, Rohini College of Engineering and Technology, Nagercoil, India.

Zitieren

APA

Ma, S., A, J., & Perumal T, S. R. (2024). Multi-dimensional dense attention network for pixel-wise segmentation of optic disc in colour fundus images. Technology and Health Care. https://doi.org/10.3233/thc-230310

Vancouver

Ma S, A J, Perumal T SR. Multi-dimensional dense attention network for pixel-wise segmentation of optic disc in colour fundus images. Technology and Health Care. 2024. doi:10.3233/thc-230310

BibTeX
@article{Ma2024,
  author = {Ma, Sreema and A, Jayachandran and Perumal T, Sudarson Rama},
  title = {Multi-dimensional dense attention network for pixel-wise segmentation of optic disc in colour fundus images},
  journal = {Technology and Health Care},
  year = {2024},
  doi = {10.3233/thc-230310}
}
Kostenlos starten →