Nonuniform rotational distortion (NURD) correction is vital for endoscopic optical coherence tomography (OCT) imaging and its functional extensions, such as angiography and elastography. Current NURD correction methods require time-consuming feature tracking or cross-correlation calculations and thus sacrifice temporal resolution. Here we propose a cross-attention learning method for the NURD correction in OCT. Our method is inspired by the recent success of the self-attention mechanism in natural language processing and computer vision. By leveraging its ability to model long-range dependencies, we can directly obtain the correlation between OCT A-lines at any distance, thus accelerating the NURD correction. We develop an end-to-end stacked cross-attention network and design three types of optimization constraints. We compare our method with two traditional feature-based methods and a CNN-based method, on two publicly-available endoscopic OCT datasets and a private dataset collected on our home-built endoscopic OCT system. Our method achieved a ∼3× speedup to real time (26±3 fps), and superior correction performance.
@article{arxiv.2306.04512,
title = {Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT},
author = {Haoran Zhang and Jianlong Yang and Jingqian Zhang and Shiqing Zhao and Aili Zhang},
journal= {arXiv preprint arXiv:2306.04512},
year = {2024}
}