Diverse Data Generation for Retinal Layer Segmentation With Potential Structure Modeling
IEEE Transactions on Medical Imaging · 2024
DOI: 10.1109/tmi.2024.3384484 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2024. Verfasst von Kun Huang und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Retina, Algorithms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Major Research Plan of the National Natural Science Foundation of China, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Accurate retinal layer segmentation on optical coherence tomography (OCT) images is hampered by the challenges of collecting OCT images with diverse pathological characterization and balanced distribution. Current generative models can produce high-realistic images and corresponding labels without quantitative limitations by fitting distributions of real collected data. Nevertheless, the diversity of their generated data is still limited due to the inherent imbalance of training data. To address these issues, we propose an image-label pair generation framework that generates diverse and balanced potential data from imbalanced real samples. Specifically, the framework first generates diverse layer masks, and then generates plausible OCT images corresponding to these layer masks using two customized diffusion probabilistic models respectively. To learn from imbalanced data and facilitate balanced generation, we introduce pathological-related conditions to guide the generation processes. To enhance the diversity of the generated image-label pairs, we propose a potential structure modeling technique that transfers the knowledge of diverse sub-structures from lowly- or non-pathological samples to highly pathological samples. We conducted extensive experiments on two public datasets for retinal layer segmentation. Firstly, our method generates OCT images with higher image quality and diversity compared to other generative methods. Furthermore, based on the extensive training with the generated OCT images, downstream retinal layer segmentation tasks demonstrate improved results. The code is publicly available at: https://github.com/nicetomeetu21/GenPSM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- Major Research Plan of the National Natural Science Foundation of China
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Huazhu Fu’s Agency for Science, Technology and Research (A*STAR) Central Research Fund
Zitieren
APA
Huang, K., Ma, X., Zhang, Z., Zhang, Y., Yuan, S., Fu, H., & Chen, Q. (2024). Diverse Data Generation for Retinal Layer Segmentation With Potential Structure Modeling. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2024.3384484
Vancouver
Huang K, Ma X, Zhang Z, Zhang Y, Yuan S, Fu H, et al. Diverse Data Generation for Retinal Layer Segmentation With Potential Structure Modeling. IEEE Transactions on Medical Imaging. 2024. doi:10.1109/tmi.2024.3384484
BibTeX
@article{Huang2024,
author = {Huang, Kun and Ma, Xiao and Zhang, Zetian and Zhang, Yuhan and Yuan, Songtao and Fu, Huazhu and Chen, Qiang},
title = {Diverse Data Generation for Retinal Layer Segmentation With Potential Structure Modeling},
journal = {IEEE Transactions on Medical Imaging},
year = {2024},
doi = {10.1109/tmi.2024.3384484}
}
EUVIMED