Komninos Charalampos, Pissas Theodoros, Flores Blanca, Bloch Edward, Vercauteren Tom, Ourselin Sébastien, Da Cruz Lyndon, Bergeles Christos
School of Biomedical Engineering & Imaging Sciences, King's College London, SE1 7EU, London, UK.
Moorfields Eye Hospital, EC1V 2PD, London, UK.
Ophthalmic Med Image Anal (2022). 2022;13576:105-114. doi: 10.1007/978-3-031-16525-2_11. Epub 2022 Sep 15.
Regenerative therapies have recently shown potential in restoring sight lost due to degenerative diseases. Their efficacy requires precise intra-retinal delivery, which can be achieved by robotic systems accompanied by high quality visualization of retinal layers. Intra-operative Optical Coherence Tomography (iOCT) captures cross-sectional retinal images in real-time but with image quality that is inadequate for intra-retinal therapy delivery. This paper proposes a two-stage super-resolution methodology that enhances the image quality of the low resolution (LR) iOCT images leveraging information from pre-operatively acquired high-resolution (HR) OCT (preOCT) images. First, we learn the degradation process from HR to LR domain through CycleGAN and use it to generate pseudo iOCT (LR) images from the HR preOCT ones. Then, we train a Pix2Pix model on the pairs of pseudo iOCT and preOCT to learn the super-resolution mapping. Quantitative analysis using both full-reference and no-reference image quality metrics demonstrates that our approach clearly outperforms the learning-based state-of-the art techniques with statistical significance. Achieving iOCT image quality comparable to pre-OCT quality can help this medical imaging modality be established in vitreoretinal surgery, without requiring expensive hardware-related system updates.
再生疗法最近在恢复因退行性疾病而丧失的视力方面显示出潜力。其疗效需要精确的视网膜内给药，这可以通过机器人系统实现，并伴有视网膜层的高质量可视化。术中光学相干断层扫描（iOCT）可实时捕获视网膜横截面图像，但图像质量不足以用于视网膜内治疗给药。本文提出了一种两阶段超分辨率方法，利用术前获取的高分辨率（HR）光学相干断层扫描（preOCT）图像中的信息来提高低分辨率（LR）iOCT图像的质量。首先，我们通过CycleGAN学习从HR到LR域的退化过程，并使用它从HR preOCT图像生成伪iOCT（LR）图像。然后，我们在伪iOCT和preOCT图像对上训练Pix2Pix模型，以学习超分辨率映射。使用全参考和无参考图像质量指标进行的定量分析表明，我们的方法明显优于基于学习的现有技术，具有统计学意义。实现与pre - OCT质量相当的iOCT图像质量有助于在玻璃体视网膜手术中建立这种医学成像模式，而无需进行与昂贵硬件相关的系统更新。
