EUVIMEDEUVIMED entdecken
Crossref

Graph Attention U-Net for Retinal Layer Surface Detection and Choroid Neovascularization Segmentation in OCT Images

Yuhe Shen, Jiang Li, Weifang Zhu, Kai Yu, Meng Wang, Yuanyuan Peng, Yi Zhou, Liling Guan, Xinjian Chen

IEEE Transactions on Medical Imaging · 2023-11 · 42 (11) · 3140-3154

DOI: 10.1109/tmi.2023.3240757 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2023-11. Verfasst von Yuhe Shen und 8 weiteren Autor:innen. Hauptthemen laut MEDLINE: Choroidal Neovascularization, Macular Degeneration. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Choroidal neovascularization (CNV) is a typical symptom of age-related macular degeneration (AMD) and is one of the leading causes for blindness. Accurate segmentation of CNV and detection of retinal layers are critical for eye disease diagnosis and monitoring. In this paper, we propose a novel graph attention U-Net (GA-UNet) for retinal layer surface detection and CNV segmentation in optical coherence tomography (OCT) images. Due to retinal layer deformation caused by CNV, it is challenging for existing models to segment CNV and detect retinal layer surfaces with the correct topological order. We propose two novel modules to address the challenge. The first module is a graph attention encoder (GAE) in a U-Net model that automatically integrates topological and pathological knowledge of retinal layers into the U-Net structure to achieve effective feature embedding. The second module is a graph decorrelation module (GDM) that takes reconstructed features by the decoder of the U-Net as inputs, it then decorrelates and removes information unrelated to retinal layer for improved retinal layer surface detection. In addition, we propose a new loss function to maintain the correct topological order of retinal layers and the continuity of their boundaries. The proposed model learns graph attention maps automatically during training and performs retinal layer surface detection and CNV segmentation simultaneously with the attention maps during inference. We evaluated the proposed model on our private AMD dataset and another public dataset. Experiment results show that the proposed model outperformed the competing methods for retinal layer surface detection and CNV segmentation and achieved new state of the arts on the datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Choroidal NeovascularizationMacular DegenerationHumansTomography, Optical CoherenceRetinaDiagnostic Techniques, Ophthalmological

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Shen, Y., Li, J., Zhu, W., Yu, K., Wang, M., Peng, Y., Zhou, Y., Guan, L., & Chen, X. (2023). Graph Attention U-Net for Retinal Layer Surface Detection and Choroid Neovascularization Segmentation in OCT Images. IEEE Transactions on Medical Imaging, 42(11), 3140-3154. https://doi.org/10.1109/tmi.2023.3240757

Vancouver

Shen Y, Li J, Zhu W, Yu K, Wang M, Peng Y, et al. Graph Attention U-Net for Retinal Layer Surface Detection and Choroid Neovascularization Segmentation in OCT Images. IEEE Transactions on Medical Imaging. 2023;42(11):3140-3154. doi:10.1109/tmi.2023.3240757

BibTeX
@article{Shen2023,
  author = {Shen, Yuhe and Li, Jiang and Zhu, Weifang and Yu, Kai and Wang, Meng and Peng, Yuanyuan and Zhou, Yi and Guan, Liling and Chen, Xinjian},
  title = {Graph Attention U-Net for Retinal Layer Surface Detection and Choroid Neovascularization Segmentation in OCT Images},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2023},
  volume = {42},
  number = {11},
  pages = {3140--3154},
  doi = {10.1109/tmi.2023.3240757}
}
Kostenlos starten →