Division of Electronics, Ruđer Bošković Institute, Zagreb, Croatia.
School of Electronics and Information Engineering, Soochow University, Suzhou, People's Republic of China.
Phys Med Biol. 2023 Jun 8;68(12). doi: 10.1088/1361-6560/acd6d1.
. Many methods for compression and/or de-speckling of 3D optical coherence tomography (OCT) images operate on a slice-by-slice basis and, consequently, ignore spatial relations between the B-scans. Thus, we develop compression ratio (CR)-constrained low tensor train (TT)-and low multilinear (ML) rank approximations of 3D tensors for compression and de-speckling of 3D OCT images. Due to inherent denoising mechanism of low-rank approximation, compressed image is often even of better quality than the raw image it is based on.. We formulate CR-constrained low rank approximations of 3D tensor as parallel non-convex non-smooth optimization problems implemented by alternating direction method of multipliers of unfolded tensors. In contrast to patch- and sparsity-based OCT image compression methods, proposed approach does not require clean images for dictionary learning, enables CR as high as 60:1, and it is fast. In contrast to deep networks based OCT image compression, proposed approach is training free and does not require any supervised data pre-processing.. Proposed methodology is evaluated on twenty four images of a retina acquired on Topcon 3D OCT-1000 scanner, and twenty images of a retina acquired on Big Vision BV1000 3D OCT scanner. For the first dataset, statistical significance analysis shows that for CR ≤ 35, all low ML rank approximations and Schatten-0 () norm constrained low TT rank approximation can be useful for machine learning-based diagnostics by using segmented retina layers. Also for CR ≤ 35,-constrained ML rank approximation and-constrained low TT rank approximation can be useful for visual inspection-based diagnostics. For the second dataset, statistical significance analysis shows that for CR ≤ 60 all low ML rank approximations as well asandlow TT ranks approximations can be useful for machine learning-based diagnostics by using segmented retina layers. Also, for CR ≤ 60, low ML rank approximations constrained with,∊ {0, 1/2, 2/3} and one surrogate ofcan be useful for visual inspection-based diagnostics. That is also true for low TT rank approximations constrained with,∊ {0, 1/2, 2/3} for CR ≤ 20.. Studies conducted on datasets acquired by two different types of scanners confirmed capabilities of proposed framework that, for a wide range of CRs, yields de-speckled 3D OCT images suitable for clinical data archiving and remote consultation, for visual inspection-based diagnosis and for machine learning-based diagnosis by using segmented retina layers.
. 许多用于压缩和/或去噪三维光学相干断层扫描（OCT）图像的方法都是基于切片的，因此忽略了 B 扫描之间的空间关系。因此，我们开发了用于压缩和去噪三维 OCT 图像的压缩比（CR）约束的低张量树（TT）和低多线性（ML）秩逼近三维张量。由于低秩逼近的固有去噪机制，压缩后的图像质量通常甚至优于其基于的原始图像。. 我们将 CR 约束的低秩逼近三维张量表述为通过展开张量的交替方向乘子法实现的并行非凸非光滑优化问题。与基于块和稀疏的 OCT 图像压缩方法相比，所提出的方法不需要干净的图像进行字典学习，能够实现高达 60:1 的 CR，并且速度很快。与基于深度网络的 OCT 图像压缩方法相比，所提出的方法是无训练的，不需要任何有监督的数据预处理。. 在所提出的方法中，我们在 Topcon 3D OCT-1000 扫描仪上采集的 24 张视网膜图像和在 Big Vision BV1000 3D OCT 扫描仪上采集的 20 张视网膜图像上进行了评估。对于第一个数据集，统计显著性分析表明，对于 CR≤35，所有低 ML 秩逼近和 Schatten-0()范数约束的低 TT 秩逼近都可以用于基于机器学习的诊断，使用分割的视网膜层。对于 CR≤35，-约束的 ML 秩逼近和-约束的低 TT 秩逼近也可以用于基于视觉检查的诊断。对于第二个数据集，统计显著性分析表明，对于 CR≤60，所有低 ML 秩逼近以及和低 TT 秩逼近都可以用于基于机器学习的诊断，使用分割的视网膜层。此外，对于 CR≤60，约束在，∊{0,1/2,2/3}内的低 ML 秩逼近和一个可以用于基于视觉检查的诊断的替代物。对于 CR≤20，约束在，∊{0,1/2,2/3}内的低 TT 秩逼近也是如此。. 在由两种不同类型的扫描仪采集的数据集上进行的研究证实了所提出的框架的能力，该框架在广泛的 CR 范围内生成适合临床数据存档和远程咨询、基于视觉检查的诊断以及使用分割的视网膜层的基于机器学习的诊断的去噪三维 OCT 图像。
