.png){kind=icon}
Return
Physics-guided self-supervised method for OCT refocusing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.optlastec.2026.114704.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Addressing the trade-off between lateral resolution and depth of focus in OCT imaging is crucial for advancing biomedical imaging. Computational methods can achieve effective refocusing results while requiring high phase stability during scanning, which presents challenges in in vivo imaging. Existing deep learning methods are typically supervised and require large amounts of paired data, which are difficult to obtain in practice. Here we propose an OCT digital refocusing algorithm that integrates a physical diffraction model with a neural network. The approach uses deep learning to learn physical diffraction prior knowledge and applies it to OCT intensity images, enabling self-supervised refocusing without relying on the high phase stability of OCT system, offering broad potential applications.
Journal
O
IF:
0
Papers:
880
Citations:
0
Organization
Cited Papers
ShareSaveShareSaveNon-iterative numerical method for laterally superresolving Fourier domain optical coherence tomography.png)
OPTICS EXPRESS
OAAI
OPTICS EXPRESSIF3.3
OAAIShareSaveStability in computed optical interferometric tomography (Part II): in vivo stability assessmentOPTICS EXPRESS
OAAI
OPTICS EXPRESSIF3.3
OAAIShareSaveRetinal fundus image superresolution generated by optical coherence tomography based on a realistic mixed attention GANMEDICAL PHYSICS
MEDICAL PHYSICSIF3.2
PREAI
ShareSave
View more