EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ChoroidSeg-ViT: A Transformer Model for Choroid Layer Segmentation Based on a Mixed Attention Feature Enhancement Mechanism

Zhaolin Lu, Tao Liu, Yewen Ni, Haiyang Liu, Lina Guan

Translational Vision Science & Technology · 2024

DOI: 10.1167/tvst.13.9.7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Translational Vision Science & Technology, 2024. Verfasst von Zhaolin Lu und 4 weiteren Autor:innen. Beteiligte Einrichtung: The Affiliated Xuzhou Municipal Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China. Hauptthemen laut MEDLINE: Choroid, Tomography, Optical Coherence. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop a Vision Transformer (ViT) model based on the mixed attention feature enhancement mechanism, ChoroidSeg-ViT, for choroid layer segmentation in optical coherence tomography (OCT) images.

Methods

This study included a dataset of 100 OCT B-scans images. Ground truths were carefully labeled by experienced ophthalmologists. An end-to-end local-enhanced Transformer model, ChoroidSeg-ViT, was designed to segment the choroid layer by integrating the local enhanced feature extraction and semantic feature fusion paths. Standard segmentation metrics were selected to evaluate ChoroidSeg-ViT.

Results

Experimental results demonstrate that ChoroidSeg-ViT exhibited superior segmentation performance (mDice: 98.31, mIoU: 96.62, mAcc: 98.29) compared to other deep learning approaches, thus indicating the effectiveness and superiority of this proposed model for the choroid layer segmentation task. Furthermore, ablation and generalization experiments validated the reasonableness of the module design.

Conclusions

We developed a novel Transformer model to precisely and automatically segment the choroid layer and achieved the state-of-the-art performance. Translational Relevance: ChoroidSeg-ViT could segment precise and smooth choroid layers and form the basis of an automatic choroid analysis system that would facilitate future choroidal research in ophthalmology.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ChoroidTomography, Optical CoherenceHumansDeep LearningAlgorithmsImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • The Affiliated Xuzhou Municipal Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
  • School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, China.
  • Xuzhou Medical University, Xuzhou, Jiangsu, China.

Zitieren

APA

Lu, Z., Liu, T., Ni, Y., Liu, H., & Guan, L. (2024). ChoroidSeg-ViT: A Transformer Model for Choroid Layer Segmentation Based on a Mixed Attention Feature Enhancement Mechanism. Translational Vision Science & Technology. https://doi.org/10.1167/tvst.13.9.7

Vancouver

Lu Z, Liu T, Ni Y, Liu H, Guan L. ChoroidSeg-ViT: A Transformer Model for Choroid Layer Segmentation Based on a Mixed Attention Feature Enhancement Mechanism. Translational Vision Science & Technology. 2024. doi:10.1167/tvst.13.9.7

BibTeX
@article{Lu2024,
  author = {Lu, Zhaolin and Liu, Tao and Ni, Yewen and Liu, Haiyang and Guan, Lina},
  title = {ChoroidSeg-ViT: A Transformer Model for Choroid Layer Segmentation Based on a Mixed Attention Feature Enhancement Mechanism},
  journal = {Translational Vision Science & Technology},
  year = {2024},
  doi = {10.1167/tvst.13.9.7}
}
Kostenlos starten →