Sponsor
This work is supported in part by the NIH through NEI grant R01-EY032284 (PI: J.L. Prince), NINDS grant R01-NS082347 (PI: P.A. Calabresi), as well as NIA grants RO1-AG021155 (PI: S. C. Johnson) and R01-AG027161 (PI: S. C. Johnson). This material is partially supported by the National Science Foundation grant number 2136228 (PI: J. Gopalakrishnan) and Graduate Research Fellowship grant number DGE-1746891 (S.W. Remedios). The work was made possible in part by a Johns Hopkins University Discovery Grant (PI: A. Carass).
Published In
Medical Image Computing and Computer Assisted Intervention – MICCAI 2025
Document Type
Post-Print
Publication Date
2025
Subjects
Unsupervised learning, Optical coherence tomography, Image interpolation, Deformable registration, Generative model
Abstract
Optical coherence tomography (OCT) images are often acquired as highly anisotropic volumes, where the scanning step is dense along the fast axis but sparse along the slow axis. This affects image analysis, such as image registration for longitudinal alignment. To create more isotropic volumes, bicubic interpolation can be used along the slow axis, but it generally produces blurry features. Registration-based interpolation can reduce blurriness, but often fails to generate realistic OCT images. Deep generative models can sample realistic images, but lack the structural consistency constraints required for interpolation. In this paper, we propose an unsupervised image interpolation method that combines registration-based interpolation with a deep generative model to overcome their individual limitations and improve the structural accuracy and realism of interpolated OCT images. We compare the proposed method with both bicubic and registration-based interpolation on real OCT datasets, and show that it achieves the best interpolation performance.
Rights
Copyright (c) 2025 The Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
Persistent Identifier
https://archives.pdx.edu/ds/psu/44327
Citation Details
Wei, S., Remedios, S. W., Bian, Z., Wang, S., Chen, J., Liu, Y., ... & Carass, A. (2025, September). Unsupervised OCT image interpolation using deformable registration and generative models. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 661-671). Cham: Springer Nature Switzerland.
Description
Miccai Open Access Version/Accepted