A Study on Improving the Accuracy of Medical Images Classification Using Data Augmentation (데이터 증강을 이용한 의료 이미지 분류 정확도 개선에 관한 연구)

Cheon-Ho Park (박천호); Min-Guan Kim (김민관); Seung-Zoon Lee (이승준); Jeong-Il Choi (최정일)

doi:10.9708/jksci.2023.28.12.167

A Study on Improving the Accuracy of Medical Images Classification Using Data Augmentation

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2023, 28(12), pp.167-174
DOI : 10.9708/jksci.2023.28.12.167
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : November 13, 2023
Accepted : December 4, 2023
Published : December 29, 2023

Cheon-Ho Park ¹, Min-Guan Kim ¹, Seung-Zoon Lee ¹, Jeong-Il Choi ¹

¹숭실대학교

Accredited

ABSTRACT

This paper attempted to improve the accuracy of the colorectal cancer diagnosis model using image data augmentation in convolutional neural network. Image data augmentation was performed by flipping, rotation, translation, shearing and zooming with basic image manipulation method. This study split 4000 training data and 1000 test data for 5000 image data held, the model is learned by adding 4000 and 8000 images by image data augmentation technique to 4000 training data. The evaluation results showed that the clasification accuracy for 4000, 8000, and 12,000 training data were 85.1%, 87.0%, and 90.2%, respectively, and the improvement effect depending on the increase of image data was confirmed.

KEYWORDS

Convolutional Neural Network, Colorectal Cancer, Image Data Augmentation, Accuracy, Basic Image Manipulation

Citation status

* References for papers published after 2023 are currently being built.

[web] Korea National Statistical Office / Causes of Death Statistics in 2022 / https://kostat.go.kr/board.es?mid=a10301010000&bid=218&act=view&list_no=427216

[web] J. Malik / 2019 / Colorectal cancer diagnosis from histology images: A compatative study / arXiv / arXiv:1903.11210

[journal] Young‐Jin Cha / 2017 / Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks / Computer-Aided Civil and Infrastructure Engineering / Wiley 32(5) : 361~378

[journal] Shuang Liang / 2021 / A deep convolutional neural network to simultaneously localize and recognize waste types in images / Waste Management / Elsevier BV 126 : 247~257

[confproc] H. Wang / 2020 / Garbage recognition and classification system based on convolutional neural network vgg16 / Proceedings of the 20203rd International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) : 252~255

[journal] Yoonsoo Shin / 2021 / An Image-Based Steel Rebar Size Estimation and Counting Method Using a Convolutional Neural Network Combined with Homography / Buildings / MDPI AG 11(10) : 463~

[confproc] Y. LeCun / 1998 / Gradient-based learning applied to document recognition / Proceedings of the IEEE 86(11) : 2278~2324

[journal] 이의철 / 2016 / Recognition of characters on car number plate and best recognition ratio among their layers using Multi-layer Perceptron / 한국전자통신학회 논문지 / 한국전자통신학회 11(1) : 73~80

[other] A. Krizhevsky / 2012 / Imagenet classification with deep convolutional neural networks / Advances in neural information processing systems : 1097~1105

[journal] 방상완 / 2017 / Implementation of Image based Fire Detection System Using Convolution Neural Network / 한국전자통신학회 논문지 / 한국전자통신학회 12(2) : 331~336

[journal] Connor Shorten / 2019 / A survey on Image Data Augmentation for Deep Learning / Journal of Big Data / Springer Science and Business Media LLC 6(1) : 1~48

[journal] 최수환 / 2023 / Improvement of Detection Performance for Tanks in Aerial Image Using Data Augmentation / 한국산학기술학회논문지 / 한국산학기술학회 24(5) : 229~236

[journal] 이찬우 / 2022 / A Study on the Classification of Military Airplanes in Neighboring Countries Using Deep Learning and Various Data Augmentation Techniques / 한국군사과학기술학회지 / 한국군사과학기술학회 25(6) : 572~579

[confproc] N. Sengar / 2016 / Grading of colorectal cancer using histology images / 201639th International Conference on Telecommunications and Signal Processing : 529~532

[journal] Jakob Nikolas Kather / 2016 / Multi-class texture analysis in colorectal cancer histology / Scientific Reports / Springer Science and Business Media LLC 6(1) : 1~11

[journal] Devvi Sarwinda / 2021 / Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer / Procedia Computer Science / Elsevier BV 179 : 423~431

[journal] Venubabu Rachapudi / 2020 / Improved convolutional neural network based histopathological image classification / Evolutionary Intelligence / Springer Science and Business Media LLC 14(3) : 1337~1343

[journal] Nour Eldeen Khalifa / 2022 / A comprehensive survey of recent trends in deep learning for digital images augmentation / Artificial Intelligence Review / Springer Science and Business Media LLC 55(3) : 2351~2377

[journal] Jakub Nalepa / 2019 / Data Augmentation for Brain-Tumor Segmentation: A Review / Frontiers in Computational Neuroscience / Frontiers Media SA 13 : 1~18

[confproc] L. Sifre / 2013 / Rotation, scaling and deformation invariant scattering for texture discrimination / Proceedings of the IEEE conference on computer vision and pattern recognition : 1233~1240

[journal] Evgin Goceri / 2023 / Medical image data augmentation: techniques, comparisons and interpretations / Artificial Intelligence Review / Springer Science and Business Media LLC 56(11) : 12561~12605

[book] A. Vyas / 2018 / Multiscale Transforms with Application to Image Processing : 3~11

[journal] 김민정 / 2021 / Proposal of a Convolutional Neural Network Model for the Classification of Cardiomegaly in Chest X-ray Images / 한국방사선학회논문지 / 한국방사선학회 15(5) : 613~620

[journal] Olga Russakovsky / 2015 / ImageNet Large Scale Visual Recognition Challenge / International Journal of Computer Vision / Springer Science and Business Media LLC 115(3) : 211~252

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

A Study on Improving the Accuracy of Medical Images Classification Using Data Augmentation

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

A Study on Improving the Accuracy of Medical Images Classification Using Data Augmentation

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (24) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.