2022/09/20 by Arka Saha, Saha, Arka, Sourya Sengupta +1
Computer Science · Engineering · Medicine · #FOS: Electrical engineering #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Optical Coherence Tomography Applications #Retinal Imaging and Analysis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2209.09825
openalex publication_date 2022/09/20 · openalex created_date 2022/09/23 · openalex updated_date 2026/07/28
Optical Coherence Tomography (OCT) image denoising is a fundamental problem as OCT images suffer from multiplicative speckle noise, resulting in poor visibility of retinal layers. The traditional denoising methods consider specific statistical properties of the noise, which are not always known. Furthermore, recent deep learning-based denoising methods require paired noisy and clean images, which are often difficult to obtain, especially medical images. Noise2Noise family architectures are generally proposed to overcome this issue by learning without noisy-clean image pairs. However, for that, multiple noisy observations from a single image are typically needed. Also, sometimes the experiments are demonstrated by simulating noises on clean synthetic images, which is not a realistic scenario. This work shows how a single real-world noisy observation of each image can be used to train a denoising network. Along with a theoretical understanding, our algorithm is experimentally validated using a publicly available OCT image dataset. Our approach incorporates Anscombe transform to convert the multiplicative noise model to additive Gaussian noise to make it suitable for OCT images. The quantitative results show that this method can outperform several other methods where a single noisy observation of an image is needed for denoising. The code and implementation of this paper will be available publicly upon acceptance of this paper.