Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography
Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography
复制标题
DOI：
10.1109/cvpr52688.2022.01996
复制
发表时间：
2022-02
期刊：
影响因子：
--
通讯作者：
Jiaxiang Ren;K. Park;Yingtian Pan;H. Ling
中科院分区：
文献类型：
--
作者：
Jiaxiang Ren;K. Park;Yingtian Pan;H. Ling
光学相干断层扫描血管造影（OCTA）是一种重要的成像方式，在许多生物工程任务。然而，OCTA的图像质量通常会因体运动伪影（BMA）而降低，体运动伪影（BMA）是由于受试者的微动引起的，通常表现为被模糊区域包围的亮条纹。最先进的方法通常将BMA去除视为基于学习的图像修复问题，但需要大量具有非平凡注释的训练样本。此外，这些方法丢弃了BMA条纹区域中携带的丰富的结构和外观信息。为了解决这些问题，在本文中，我们提出了一个自我监督的内容感知BMA删除模型。首先，从BMA区域中提取基于梯度的结构信息和外观特征，并将其注入模型中以捕获更多的连通性。其次，利用容易收集的缺陷掩模，以自监督的方式训练模型，其中仅使用清晰区域进行训练，而BMA区域用于推理。该模型以含噪图像的结构信息和外观特征为参考，可以去除较大的BMA，并产生更好的可视化效果。此外，只涉及有缺陷的掩模的2D图像，从而提高了我们的方法的效率。对小鼠皮层OCTA的实验表明，我们的模型可以去除大多数BMA的尺寸非常大，强度不一致，而以前的方法失败。
Optical coherence tomography angiography (OCTA) is an important imaging modality in many bioengineering tasks. The image quality of OCTA, however, is often degraded by Bulk Motion Artifacts (BMA), which are due to micromotion of subjects and typically appear as bright stripes surrounded by blurred areas. State-of-the-art methods usually treat BMA removal as a learning-based image inpainting problem, but require numerous training samples with nontrivial annotation. In addition, these methods discard the rich structural and appearance information carried in the BMA stripe region. To address these issues, in this paper we propose a self-supervised content-aware BMA removal model. First, the gradient-based structural information and appearance feature are extracted from the BMA area and injected into the model to capture more connectivity. Second, with easily collected defective masks, the model is trained in a self-supervised manner, in which only the clear areas are used for training while the BMA areas for inference. With the structural information and appearance feature from noisy image as references, our model can remove larger BMA and produce better visualizing result. In addition, only 2D images with defective masks are involved, hence improving the efficiency of our method. Experiments on OCTA of mouse cortex demonstrate that our model can remove most BMA with extremely large sizes and inconsistent intensities while previous methods fail.