The Effect of Noisy and Blurry Data on Deep Learning: Application in Brain Image Classification

Muhammad Fajar Azka Fadillah, Dewinda Julianensi Rumala, Mauridhi Hery Purnomo, I. Ketut Eddy Purnama*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Convolutional Neural Networks (CNN) is one of the best Deep Learning algorithms commonly used for computer vision tasks, including medical image analysis. CNN can learn the representational features from images starting from the lower to complex features. However, noisy data can affect the generalization of the networks, which we can often find in medical images, such as Magnetic Resonance Imaging (MRI). In this paper, we intend to find the correlation between noisy data and the performance of CNN models. We build automatic CNN-based classifiers for normal brain MR images based on axial view by setting up three different data scenarios to train the classifiers: 1) original data, 2) blurred data, and 3) noisy data. We also evaluate the relationship between the prediction accuracy and kernel size of the convolutional layers. Based on our investigation, deeper layers and smaller kernels in the CNN models give better generalization.

Original languageEnglish
Title of host publicationProceedings of 2022 IEEE Region 10 International Conference, TENCON 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665450959
DOIs
Publication statusPublished - 2022
Event2022 IEEE Region 10 International Conference, TENCON 2022 - Virtual, Online, Hong Kong
Duration: 1 Nov 20224 Nov 2022

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume2022-November
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2022 IEEE Region 10 International Conference, TENCON 2022
Country/TerritoryHong Kong
CityVirtual, Online
Period1/11/224/11/22

Keywords

  • Blurry Data
  • Convolutional Neural Networks
  • Deep Learning
  • Magnetic Resonance Imaging Brain
  • Noisy Data
  • image classification

Fingerprint

Dive into the research topics of 'The Effect of Noisy and Blurry Data on Deep Learning: Application in Brain Image Classification'. Together they form a unique fingerprint.

Cite this