Enhanced Denoising of Optical Coherence Tomography Images Using Residual U-Net
This work addresses noise reduction in OCT imaging for ophthalmic diagnosis, offering incremental improvements in denoising techniques.
The study tackled the problem of speckle noise and artifacts in Optical Coherence Tomography (OCT) images, which hinder diagnosis, by proposing a Residual U-Net denoising model that improved image quality metrics, such as achieving a PSNR of 34.343 ± 1.113 for PSOCT images and 23.525 ± 0.872 dB for ASOCT images.
Optical Coherence Tomography (OCT) imaging is pivotal in diagnosing ophthalmic conditions by providing detailed cross-sectional images of the anterior and posterior segments of the eye. Nonetheless, speckle noise and other imaging artifacts inherent to OCT impede the accuracy of diagnosis significantly. In this study, we proposed an enhanced denoising model using a Residual U-Net architecture that effectively diminishes noise and improves image clarity across both Anterior Segment OCT (ASOCT) and polarization-sensitive OCT (PSOCT) images. Our approach demonstrated substantial improvements in image quality metrics: the Peak Signal Noise Ratio (PSNR) was 34.343 $\pm$ 1.113 for PSOCT images, and Structural Similarity Index Measure (SSIM) values were 0.885 $\pm$ 0.030, indicating enhanced preservation of tissue integrity and textural details. For ASOCT images, we observed the PSNR to be 23.525 $\pm$ 0.872 dB and SSIM 0.407 $\pm$ 0.044, reflecting significant enhancements in visual quality and structural accuracy. These metrics substantiate the models efficacy in not only reducing noise but also in maintaining crucial anatomical features, thereby enabling more precise and efficient clinical evaluations. The dual functionality across both ASOCT and PSOCT modalities underscores the versatility and potential for broad application in clinical settings, optimizing diagnostic processes and reducing the necessity for prolonged imaging sessions.