Survey of Image Denoising Methods for Medical Image Classification

被引:7
作者
Michael, Peter F. [1 ]
Yoon, Hong-Jun [2 ]
机构
[1] Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA
[2] Oak Ridge Natl Lab, Hlth Data Sci Inst, Engn & Comp Grp, Biomed Sci, Oak Ridge, TN 37830 USA
来源
MEDICAL IMAGING 2020: COMPUTER-AIDED DIAGNOSIS | 2020年 / 11314卷
关键词
image denoising; image classification; X-ray image denoising; machine learning; deep learning;
D O I
10.1117/12.2549695
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
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.
引用
收藏
页数:8
相关论文
共 19 条
  • [1] Chintala S., 2017, 31 C NEURAL INFORM P
  • [2] Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
  • [3] Diamond Steven, 2017, Dirty pixels: Optimizing image classification architectures for raw sensor data
  • [4] Ding Q., 2018, arXiv
  • [5] Dodge S. F., 2017, ABS170308119 CORR
  • [6] Dodge S.L. Karam., 2016, Understanding how image quality affects deep neural networks
  • [7] Optimal bilateral filter and Convolutional Neural Network based denoising method of medical image measurements
    Elhoseny, Mohamed
    Shankar, K.
    [J]. MEASUREMENT, 2019, 143 : 125 - 135
  • [8] Huang G., 2017, P IEEE C COMP VIS PA, P4700, DOI [DOI 10.1109/CVPR.2017.243, 10.1109/CVPR.2017.243]
  • [9] Image recognition with deep neural networks in presence of noise - Dealing with and taking advantage of distortions
    Koziarski, Michal
    Cyganek, Boguslaw
    [J]. INTEGRATED COMPUTER-AIDED ENGINEERING, 2017, 24 (04) : 337 - 349
  • [10] Lehtinen J, 2018, PR MACH LEARN RES, V80