Survey of image denoising methods for medical image classification

Medical imaging devices, such as X-ray machines, inherently produce images that suffer from visual noise. Our objectives were to (i.) determine the effect of image denoising on a medical image classification task, and (ii.) determine if there exists a correlation between image denoising performance and medical image classification performance. We performed the medical image classification task on chest X-rays using the DenseNet-121 convolutional neural network (CNN) and used the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics as the image denoising performance measures. We first found that different denoising methods can make a statistically significant difference in classification performance for select labels. We also found that denoising methods affect fine-tuned models more than randomly-initialized models and that fine-tuned models have significantly higher and more uniform performance than randomly-initialized models. Lastly, we found that there is no significant correlation between PSNR and SSIM values and classification performance for our task.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[3]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Stephen P. Boyd,et al.  Dirty Pixels: Optimizing Image Classification Architectures for Raw Sensor Data , 2017, ArXiv.

[5]  Kyung-Ah Sohn,et al.  Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets , 2017, 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[6]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[7]  Lina J. Karam,et al.  Understanding how image quality affects deep neural networks , 2016, 2016 Eighth International Conference on Quality of Multimedia Experience (QoMEX).

[8]  Lina J. Karam,et al.  Quality Resilient Deep Neural Networks , 2017, ArXiv.

[9]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.

[10]  Jaakko Lehtinen,et al.  Noise2Noise: Learning Image Restoration without Clean Data , 2018, ICML.

[11]  Gabriel B. Paranhos da Costa,et al.  Deep Convolutional Neural Networks and Noisy Images , 2017, CIARP.

[12]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[13]  Jeffrey A. Fessler,et al.  Statistical Image Reconstruction Using Mixed Poisson-Gaussian Noise Model for X-Ray CT , 2018, 1801.09533.

[14]  Boguslaw Cyganek,et al.  Image recognition with deep neural networks in presence of noise - Dealing with and taking advantage of distortions , 2017, Integr. Comput. Aided Eng..

[15]  B. F. Logan,et al.  The Fourier reconstruction of a head section , 1974 .

[16]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[17]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series , 1964 .

[18]  Mohamed Elhoseny,et al.  Optimal bilateral filter and Convolutional Neural Network based denoising method of medical image measurements , 2019, Measurement.

[19]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.