Noise-imitation learning: unpaired speckle noise reduction for optical coherence tomography
- 3 September 2024
- journal article
- research article
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 69 (18) , 185003
Abstract
Objective. Optical coherence tomography (OCT) is widely used in clinical practice for its non-invasive, high-resolution imaging capabilities. However, speckle noise inherent to its low coherence principle can degrade image quality and compromise diagnostic accuracy. While deep learning methods have shown promise in reducing speckle noise, obtaining well-registered image pairs remains challenging, leading to the development of unpaired methods. Despite their potential, existing unpaired methods suffer from redundancy in network structures or interaction mechanisms. Therefore, a more streamlined method for unpaired OCT denoising is essential. Approach. In this work, we propose a novel unpaired method for OCT image denoising, referred to as noise-imitation learning (NIL). NIL comprises three primary modules: the noise extraction module, which extracts noise features by denoising noisy images; the noise imitation module, which synthesizes noisy images and generates fake clean images; and the adversarial learning module, which differentiates between real and fake clean images through adversarial training. The complexity of NIL is significantly lower than that of previous unpaired methods, utilizing only one generator and one discriminator for training. Main results. By efficiently fusing unpaired images and employing adversarial training, NIL can extract more speckle noise information to enhance denoising performance. Building on NIL, we propose an OCT image denoising pipeline, NIL-NAFNet. This pipeline achieved PSNR, SSIM, and RMSE values of 31.27 dB, 0.865, and 7.00, respectively, on the PKU37 dataset. Extensive experiments suggest that our method outperforms state-of-the-art unpaired methods both qualitatively and quantitatively. Significance. These findings indicate that the proposed NIL is a simple yet effective method for unpaired OCT speckle noise reduction. The OCT denoising pipeline based on NIL demonstrates exceptional performance and efficiency. By addressing speckle noise without requiring well-registered image pairs, this method can enhance image quality and diagnostic accuracy in clinical practice.Keywords
Funding Information
- National Natural Science Foundation of China (82371112, 623B2001, 62394311)
- Natural Science Foundation of Beijing Municipality (Z210008)
- High-grade, Precision and Advanced University Discipline Construction Project of Beijing (BMU2024GJJXK004)
This publication has 52 references indexed in Scilit:
- One-Pot Multi-frame DenoisingInternational Journal of Computer Vision, 2023
- Comparative study of deep neural networks with unsupervised Noise2Noise strategy for noise reduction of optical coherence tomography imagesJournal of Biophotonics, 2021
- Noise Reduction for SD-OCT Using a Structure-Preserving Domain Transfer ApproachIEEE Journal of Biomedical and Health Informatics, 2021
- N2NSR‐OCT: Simultaneous denoising and super‐resolution in optical coherence tomography images using semisupervised deep learningJournal of Biophotonics, 2020
- Texture preservation and speckle reduction in poor optical coherence tomography using the convolutional neural networkMedical Image Analysis, 2020
- Quantitative Classification of Eyes with and without Intermediate Age-related Macular Degeneration Using Optical Coherence TomographyOphthalmology, 2014
- Adaptive Speckle Reduction in OCT Volume Data Based on Block-Matching and 3-D FilteringIEEE Photonics Technology Letters, 2012
- Speckle reduction in parallel optical coherence tomography by spatial compoundingOptics & Laser Technology, 2012
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Statistical properties of logarithmically transformed speckleIEEE Transactions on Geoscience and Remote Sensing, 2002