EUVIMEDEUVIMED entdecken
Crossref

Dual-Spatial Domain Generalization for Fundus Lesion Segmentation in Unseen Manufacturer's OCT Images

Shichen Liao, Tao Peng, Haoyu Chen, Tian Lin, Weifang Zhu, Fei Shi, Xinjian Chen, Dehui Xiang

IEEE Transactions on Biomedical Engineering · 2024

DOI: 10.1109/tbme.2024.3393453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2024. Verfasst von Shichen Liao und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Image Interpretation, Computer-Assisted, Algorithms. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: Optical Coherence Tomography (OCT) images can provide non-invasive visualization of fundus lesions; however, scanners from different OCT manufacturers largely vary from each other, which often leads to model deterioration to unseen OCT scanners due to domain shift. METHODS: To produce the T-styles of the potential target domain, an Orthogonal Style Space Reparameterization (OSSR) method is proposed to apply orthogonal constraints in the latent orthogonal style space to the sampled marginal styles. To leverage the high-level features of multi-source domains and potential T-styles in the graph semantic space, a Graph Adversarial Network (GAN) is constructed to align the generated samples with the source domain samples. To align features with the same label based on the semantic feature in the graph semantic space, Graph Semantic Alignment (GSA) is performed to focus on the shape and the morphological differences between the lesions and their surrounding regions. RESULTS: Comprehensive experiments have been performed on two OCT image datasets. Compared to state-of-the-art methods, the proposed method can achieve better segmentation. CONCLUSION: The proposed fundus lesion segmentation method can be trained with labeled OCT images from multiple manufacturers' scanners and be tested on an unseen manufacturer's scanner with better domain generalization. SIGNIFICANCE: The proposed method can be used in routine clinical occasions when an unseen manufacturer's OCT image is available for a patient.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Tomography, Optical CoherenceImage Interpretation, Computer-AssistedAlgorithmsHumansFundus OculiDatabases, FactualRetinal Diseases

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China

Zitieren

APA

Liao, S., Peng, T., Chen, H., Lin, T., Zhu, W., Shi, F., Chen, X., & Xiang, D. (2024). Dual-Spatial Domain Generalization for Fundus Lesion Segmentation in Unseen Manufacturer's OCT Images. IEEE Transactions on Biomedical Engineering. https://doi.org/10.1109/tbme.2024.3393453

Vancouver

Liao S, Peng T, Chen H, Lin T, Zhu W, Shi F, et al. Dual-Spatial Domain Generalization for Fundus Lesion Segmentation in Unseen Manufacturer's OCT Images. IEEE Transactions on Biomedical Engineering. 2024. doi:10.1109/tbme.2024.3393453

BibTeX
@article{Liao2024,
  author = {Liao, Shichen and Peng, Tao and Chen, Haoyu and Lin, Tian and Zhu, Weifang and Shi, Fei and Chen, Xinjian and Xiang, Dehui},
  title = {Dual-Spatial Domain Generalization for Fundus Lesion Segmentation in Unseen Manufacturer's OCT Images},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2024},
  doi = {10.1109/tbme.2024.3393453}
}
Kostenlos starten →