A residual U-Net network with image prior for 3D image denoising
| Autor: | Nicolas Ducros, Françoise Peyrin, Christine Chappard, Philippe Douek, Juan F P J Abascal, S. Bussod, Salim Si-Mohamed |
|---|---|
| Přispěvatelé: | Imagerie Tomographique et Radiothérapie, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Hospices Civils de Lyon (HCL)-Université Jean Monnet [Saint-Étienne] (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Novae, Centre de Recherche et d'Application en Traitement de l'Image et du Signal (CREATIS), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-École Supérieure Chimie Physique Électronique de Lyon-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Bioingénierie et Bioimagerie Ostéo-articulaires, Biomécanique et Biomatériaux Ostéo-Articulaires (B2OA (UMR_7052)), Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS)-École nationale vétérinaire d'Alfort (ENVA), European Synchrotron Radiation Facility (ESRF) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Noise measurement
Image quality business.industry Computer science Noise reduction Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION deep learning 020206 networking & telecommunications Pattern recognition 02 engineering and technology Sparse approximation Residual U-Net Index Terms-Image denoising [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV] 0202 electrical engineering electronic engineering information engineering [INFO.INFO-IM]Computer Science [cs]/Medical Imaging 020201 artificial intelligence & image processing Noise (video) Artificial intelligence business Image restoration |
| Zdroj: | 28th European Signal Processing Conference (EUSIPCO) 28th European Signal Processing Conference (EUSIPCO), Jan 2021, Amsterdam, Netherlands. ⟨10.23919/Eusipco47968.2020.9287607⟩ EUSIPCO |
| Popis: | International audience; Denoising algorithms via sparse representation are among the state-of-the art for image restoration. On previous work, we proposed SPADE-a sparse-and prior-based method for 3D-image denoising. In this work, we extend this idea to learning approaches and propose a novel residual-U-Net prior-based (ResPrU-Net) method that exploits a prior image. The proposed ResPrU-Net architecture has two inputs, the noisy image and the prior image, and a residual connection that connects the prior image to the output of the network. We compare ResPrU-Net to U-Net and SPADE on human knee data acquired on a spectral computerized tomography scanner. The prior image is built from the noisy image by combining information from neighbor slices and it is the same for both SPADE and ResPrU-Net. For deep learning approaches, we use four knee samples and data augmentation for training, one knee for validation and two for test. Results show that for high noise, U-Net leads to worst results, with images that are excessively blurred. Prior-based methods, SPADE and ResPrU-Net, outperformed U-Net, leading to restored images that present similar image quality than the target. ResPrU-Net provides slightly better results than SPADE. For low noise, methods present similar results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|