Viqar Maryam, Sahin Erdem, Stoykova Elena, Madjarova Violeta
Faculty of Information Technology and Communication Sciences, Tampere University, 33720 Tampere, Finland.
Institute of Optical Materials and Technologies, Bulgarian Academy of Sciences, 1113 Sofia, Bulgaria.
Sensors (Basel). 2024 Dec 27;25(1):93. doi: 10.3390/s25010093.
Conventional Fourier domain Optical Coherence Tomography (FD-OCT) systems depend on resampling into a wavenumber () domain to extract the depth profile. This either necessitates additional hardware resources or amplifies the existing computational complexity. Moreover, the OCT images also suffer from speckle noise, due to systemic reliance on low-coherence interferometry. We propose a streamlined and computationally efficient approach based on Deep Learning (DL) which enables reconstructing speckle-reduced OCT images directly from the wavelength (λ) domain. For reconstruction, two encoder-decoder styled networks, namely Spatial Domain Convolution Neural Network (SD-CNN) and Fourier Domain CNN (FD-CNN), are used sequentially. The SD-CNN exploits the highly degraded images obtained by Fourier transforming the (λ) domain fringes to reconstruct the deteriorated morphological structures along with suppression of unwanted noise. The FD-CNN leverages this output to enhance the image quality further by optimization in the Fourier domain (FD). We quantitatively and visually demonstrate the efficacy of the method in obtaining high-quality OCT images. Furthermore, we illustrate the computational complexity reduction by harnessing the power of DL models. We believe that this work lays the framework for further innovations in the realm of OCT image reconstruction.
传统的傅里叶域光学相干断层扫描（FD-OCT）系统依赖于重采样到波数（）域来提取深度剖面。这要么需要额外的硬件资源，要么会增加现有的计算复杂度。此外，由于系统依赖于低相干干涉测量，OCT图像还会受到散斑噪声的影响。我们提出了一种基于深度学习（DL）的简化且计算高效的方法，该方法能够直接从波长（λ）域重建减少散斑的OCT图像。为了进行重建，依次使用了两个编码器-解码器样式的网络，即空间域卷积神经网络（SD-CNN）和傅里叶域卷积神经网络（FD-CNN）。SD-CNN利用通过对（λ）域条纹进行傅里叶变换获得的高度退化图像，来重建退化的形态结构并抑制不需要的噪声。FD-CNN利用此输出通过在傅里叶域（FD）中进行优化来进一步提高图像质量。我们在定量和视觉上证明了该方法在获取高质量OCT图像方面的有效性。此外，我们通过利用DL模型的能力说明了计算复杂度的降低。我们相信这项工作为OCT图像重建领域的进一步创新奠定了框架。
