EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pixel-Level Segmentation of Retinal Breaks in Ultra-Widefield Fundus Images with a PraNet-Based Machine Learning Model

Takuya Takayama iD, Tsubasa Uto, Taiki Tsuge, Yusuke Kondo, Hironobu Tampo, Mayumi Chiba, Toshikatsu Kaburaki iD, Yasuo Yanagi, Hidenori Takahashi iD

Sensors · 2025

DOI: 10.3390/s25185862 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Takuya Takayama und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, Jichi Medical University, Shimotsuke, Tochigi 329-0498, Japan. Hauptthemen laut MEDLINE: Machine Learning, Fundus Oculi, Retina, Image Processing, Computer-Assisted. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, JSPS KAKENHI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retinal breaks are critical lesions that can cause retinal detachment and vision loss if not detected and treated early. Automated, accurate delineation of retinal breaks in ultra-widefield fundus (UWF) images remains challenging. In this study, we developed and validated a deep learning segmentation model based on the PraNet architecture to localize retinal breaks in break-positive cases. We trained and evaluated the model using a dataset comprising 34,867 UWF images of 8083 cases. Performance was assessed using image-level segmentation metrics, including accuracy, precision, recall, Intersection over Union (IoU), dice score, and centroid distance score. The model achieved an accuracy of 0.996, precision of 0.635, recall of 0.756, IoU of 0.539, dice score of 0.652, and centroid distance score of 0.081. To our knowledge, this is the first study to present pixel-level segmentation of retinal breaks in UWF images using deep learning. The proposed PraNet-based model showed high accuracy and robust segmentation performance, highlighting its potential for clinical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningFundus OculiRetinaImage Processing, Computer-AssistedHumansDeep LearningRetinal DetachmentAlgorithms

Stichwörter der Autor:innen

PraNetmachine learningretinal breaksegmentationultra-widefield fundus images

Autor:innen und Institutionen

  • Department of Ophthalmology, Jichi Medical University, Shimotsuke, Tochigi 329-0498, Japan.
  • DeepEyeVision Inc., Shimotsuke, Tochigi 329-0498, Japan.
  • Department of Ophthalmology, Yokohama City University, Kanagawa 232-0023, Japan.
  • Retina Research Group, Singapore Eye Research Institute, Singapore 168751, Singapore.
  • Center for Cyber Medicine Research, Tsukuba University, Ibaraki 305-8577, Japan.

ORCID-Profile: Takuya Takayama, Toshikatsu Kaburaki, Hidenori Takahashi

Förderung

  • Japan Society for the Promotion of Science
  • JSPS KAKENHI

Zitieren

APA

Takayama, T., Uto, T., Tsuge, T., Kondo, Y., Tampo, H., Chiba, M., Kaburaki, T., Yanagi, Y., & Takahashi, H. (2025). Pixel-Level Segmentation of Retinal Breaks in Ultra-Widefield Fundus Images with a PraNet-Based Machine Learning Model. Sensors. https://doi.org/10.3390/s25185862

Vancouver

Takayama T, Uto T, Tsuge T, Kondo Y, Tampo H, Chiba M, et al. Pixel-Level Segmentation of Retinal Breaks in Ultra-Widefield Fundus Images with a PraNet-Based Machine Learning Model. Sensors. 2025. doi:10.3390/s25185862

BibTeX
@article{Takayama2025,
  author = {Takayama, Takuya and Uto, Tsubasa and Tsuge, Taiki and Kondo, Yusuke and Tampo, Hironobu and Chiba, Mayumi and Kaburaki, Toshikatsu and Yanagi, Yasuo and Takahashi, Hidenori},
  title = {Pixel-Level Segmentation of Retinal Breaks in Ultra-Widefield Fundus Images with a PraNet-Based Machine Learning Model},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25185862}
}
Kostenlos starten →