Medical image denoising using convolutional denoising autoencoders

Abstract

Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however limited for requirement of large training sample size and high computational costs. In this paper we show that using small sample size, denoising autoencoders constructed using convolutional layers can be used for efficient denoising of medical images. Heterogeneous images can be combined to boost sample size for increased denoising performance. Simplest of networks can reconstruct images with corruption levels so high that noise and signal are not differentiable to human eye.

To appear: 6 pages, paper to be published at the Fourth Workshop on Data Mining in Biomedical Informatics and Healthcare at ICDM, 2016

References in corpus (3)

• Sequence to Sequence Learning with Neural Networks
• Deep Learning: A Tutorial
• Boltzmann Machines and Denoising Autoencoders for Image Denoising

Cited by in corpus (56)

• Applications of Deep Learning and Reinforcement Learning to Biological Data
• Enhanced CNN for image denoising
• Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model
• Review: Deep Learning in Electron Microscopy
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset
• BIRADS Features-Oriented Semi-supervised Deep Learning for Breast Ultrasound Computer-Aided Diagnosis
• Attenuation of marine seismic interference noise employing a customized U-Net
• hEARt: Motion-resilient Heart Rate Monitoring with In-ear Microphones
• Generative Machine Learning for Robust Free-Space Communication
• Multi-Kernel Prediction Networks for Denoising of Burst Images
• Deep Perceptual Enhancement for Medical Image Analysis
• Geometric Understanding of Deep Learning
• MalPhase: Fine-Grained Malware Detection Using Network Flow Data
• Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing
• Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning -- A Residual Physics Approach
• Multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge 2022 Results
• Revisiting Bayesian Autoencoders with MCMC
• MRI denoising using Deep Learning and Non-local averaging
• Rotor Localization and Phase Mapping of Cardiac Excitation Waves using Deep Neural Networks
• Inverse Mechano-Electrical Reconstruction of Cardiac Excitation Wave Patterns from Mechanical Deformation using Deep Learning
• Two-stage Deep Denoising with Self-guided Noise Attention for Multimodal Medical Images
• 3D Brain and Heart Volume Generative Models: A Survey
• Review: Noise and artifact reduction for MRI using deep learning
• Eformer: Edge Enhancement based Transformer for Medical Image Denoising
• Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation
• Visual Time Series Forecasting: An Image-driven Approach
• Real-Time Zero-Day Intrusion Detection System for Automotive Controller Area Network on FPGAs
• Convex Regularization Behind Neural Reconstruction
• DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices
• Accelerating Neutron Scattering Data Collection and Experiments Using AI Deep Super-Resolution Learning
• Deep Neural Networks to Recover Unknown Physical Parameters from Oscillating Time Series
• MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation
• DANAE: a denoising autoencoder for underwater attitude estimation
• Denoising convolutional autoencoder based B-mode ultrasound tongue image feature extraction
• A deep learning based known plaintext attack method for chaotic cryptosystem
• Learning Personal Representations from fMRIby Predicting Neurofeedback Performance
• Inferring Implicit 3D Representations from Human Figures on Pictorial Maps
• Performance of a convolutional autoencoder designed to remove electronic noise from p-type point contact germanium detector signals
• 3D U-NetR: Low Dose Computed Tomography Reconstruction via Deep Learning and 3 Dimensional Convolutions
• An approach to image denoising using manifold approximation without clean images
• Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanation
• SAR Image Despeckling Based on Convolutional Denoising Autoencoder
• Fantômas: Understanding Face Anonymization Reversibility
• Leveraging Deep Stein's Unbiased Risk Estimator for Unsupervised X-ray Denoising
• MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
• Digging Deeper into CRNN Model in Chinese Text Images Recognition
• Agon: A Scalable Competitive Scheduler for Large Heterogeneous Systems
• Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Tasks
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
• FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram
• Complementary Ensemble Learning
• Partitioned Graph Convolution Using Adversarial and Regression Networks for Road Travel Speed Prediction
• Neuronal Learning Analysis using Cycle-Consistent Adversarial Networks
• LIRA: Lifelong Image Restoration from Unknown Blended Distortions
• JR2net: A Joint Non-Linear Representation and Recovery Network for Compressive Spectral Imaging