TY - GEN
T1 - Unsupervised OCT Image Interpolation Using Deformable Registration and generative models
AU - Wei, Shuwen
AU - Remedios, Samuel W.
AU - Bian, Zhangxing
AU - Wang, Shimeng
AU - Chen, Junyu
AU - Liu, Yihao
AU - Jedynak, Bruno
AU - Liu, Tin Y.A.
AU - Saidha, Shiv
AU - Calabresi, Peter A.
AU - Prince, Jerry L.
AU - Carass, Aaron
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - 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.
AB - 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.
KW - Deformable registration
KW - Generative model
KW - Image interpolation
KW - Optical coherence tomography
KW - Unsupervised learning
UR - https://www.scopus.com/pages/publications/105017852236
UR - https://www.scopus.com/pages/publications/105017852236#tab=citedBy
U2 - 10.1007/978-3-032-04965-0_62
DO - 10.1007/978-3-032-04965-0_62
M3 - Conference contribution
AN - SCOPUS:105017852236
SN - 9783032049643
T3 - Lecture Notes in Computer Science
SP - 661
EP - 671
BT - Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, Proceedings
A2 - Gee, James C.
A2 - Hong, Jaesung
A2 - Sudre, Carole H.
A2 - Golland, Polina
A2 - Alexander, Daniel C.
A2 - Iglesias, Juan Eugenio
A2 - Venkataraman, Archana
A2 - Kim, Jong Hyo
PB - Springer Science and Business Media Deutschland GmbH
T2 - 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Y2 - 23 September 2025 through 27 September 2025
ER -