Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
  • Optical Coherence Imaging Techniques and Imaging in Scattering Media III
  • SPIE Proceedings (Optica Publishing Group, 2019),
  • paper 11078_43
  • https://doi.org/10.1117/12.2526936

Semantic denoising autoencoders for retinal optical coherence tomography

Not Accessible

Your library or personal account may give you access

Abstract

Noise in speckle-prone optical coherence tomography tends to obfuscate important details necessary for medical diagnosis. In this paper, a denoising approach that preserves disease characteristics on retinal optical coherence tomography images in ophthalmology is presented. We propose semantic denoising autoencoders, which combine a convolutional denoising autoencoder with a priorly trained ResNet image classifier as regularizer during training. This promotes the perceptibility of delicate details in the denoised images that are important for diagnosis and filters out only informationless background noise. With our approach, higher peak signal-to-noise ratios with PSNR = 31.0 dB and higher classification performance of F1 = 0.92 can be achieved for denoised images compared to state-of-the-art denoising. It is shown that semantically regularized autoencoders are capable of denoising retinal OCT images without blurring details of diseases.

© 2019 SPIE/OSA

PDF Article
More Like This
High quality optical coherence tomography imaging of mock cataract surgery with deep-learning-based denoising

Jonas Nienhaus, Anja Britten, Philipp Matten, Thomas Schlegl, Katharina Dettelbacher, Andreas Pollreisz, Wolfgang Drexler, Rainer A. Leitgeb, and Tilman Schmoll
126321Q European Conference on Biomedical Optics (ECBO) 2023

Adaptive Wavelet Thresholding for Optical Coherence Tomography Image Denoising

Farzana Zaki, Yahui Wang, Xin Yuan, and Xuan Liu
CTh4B.4 Computational Optical Sensing and Imaging (COSI) 2017

Optimizing Deep Learning Based Retinal Diseases Classification On Optical Coherence Tomography Scans

Aditya Chandra Mandal and Abhijeet Phatak
1263220 European Conference on Biomedical Optics (ECBO) 2023

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved