School of Electronics and Information Engineering, Soochow University, Suzhou, Jiangsu, China.
Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, Virginia, USA.
Med Phys. 2022 Sep;49(9):5914-5928. doi: 10.1002/mp.15712. Epub 2022 Jun 1.
Optical coherence tomography (OCT) imaging uses the principle of Michelson interferometry to obtain high-resolution images by coherent superposing of multiple forward and backward scattered light waves with random phases. This process inevitably produces speckle noise that severely compromises visual quality of OCT images and degrades performances of subsequent image analysis tasks. In addition, datasets obtained by different OCT scanners have distribution shifts, making a speckle noise suppression model difficult to be generalized across multiple datasets. In order to solve the above issues, we propose a novel end-to-end denoising framework for OCT images collected by different scanners.
The proposed model utilizes the high-resolution network (HRNet) as backbone for image restoration, which reconstructs high-fidelity images by maintaining high-resolution representations throughout the entire learning process. To compensate distribution shifts among datasets collected by different scanners, we develop a hierarchical adversarial learning strategy for domain adaption. The proposed model is trained using datasets with clean ground truth produced by two commercial OCT scanners, and then applied to suppress speckle noise in OCT images collected by our recently developed OCT scanner, BV-1000 (China Bigvision Corporation). We name the proposed model as DHNet (Double-H-Net, High-resolution and Hierarchical Network).
We compare DHNet with state-of-the-art methods and experiment results show that DHNet improves signal-to-noise ratio by a large margin of 18.137 dB as compared to the best of our previous method. In addition, DHNet achieves a testing time of 25 ms, which satisfies the real-time processing requirement for the BV-1000 scanner. We also conduct retinal layer segmentation experiment on OCT images before and after denoising and show that DHNet can also improve segmentation.
The proposed DHNet can compensate domain shifts between different data sets while significantly improve speckle noise suppression. The HRNet backbone is utilized to carry low- and high-resolution information to recover fidelity images. Domain adaptation is achieved by a hierarchical module through adversarial learning. In addition, DHNet achieved a testing time of 25 ms, which satisfied the real-time processing requirement.
光学相干断层扫描（OCT）成像利用迈克尔逊干涉原理，通过相干叠加具有随机相位的多个前向和后向散射光来获得高分辨率图像。这个过程不可避免地会产生散斑噪声，严重影响 OCT 图像的视觉质量，并降低后续图像分析任务的性能。此外，不同 OCT 扫描仪获得的数据集存在分布偏移，使得难以在多个数据集之间推广散斑噪声抑制模型。为了解决上述问题，我们提出了一种新的用于不同扫描仪采集的 OCT 图像的端到端去噪框架。
所提出的模型利用高分辨率网络（HRNet）作为图像恢复的骨干，通过在整个学习过程中保持高分辨率表示来重建高保真图像。为了补偿不同扫描仪采集的数据集之间的分布偏移，我们开发了一种用于域自适应的分层对抗学习策略。所提出的模型使用由两个商业 OCT 扫描仪生成的具有干净真实值的数据集进行训练，然后应用于抑制我们最近开发的 OCT 扫描仪 BV-1000（中国大视野公司）采集的 OCT 图像中的散斑噪声。我们将所提出的模型命名为 DHNet（Double-H-Net，高分辨率和分层网络）。
我们将 DHNet 与最先进的方法进行了比较，实验结果表明，DHNet 比我们之前的最佳方法大幅提高了 18.137dB 的信噪比。此外，DHNet 的测试时间为 25ms，满足了 BV-1000 扫描仪的实时处理要求。我们还在去噪前后的 OCT 图像上进行了视网膜层分割实验，表明 DHNet 还可以提高分割性能。
所提出的 DHNet 可以补偿不同数据集之间的域偏移，同时显著提高散斑噪声抑制效果。HRNet 骨干网用于携带低分辨率和高分辨率信息以恢复保真度图像。通过分层模块通过对抗学习实现域自适应。此外，DHNet 的测试时间为 25ms，满足了实时处理要求。
