Browse > Article
http://dx.doi.org/10.9718/JBER.2021.42.3.80

A Performance Comparison of Histogram Equalization Algorithms for Cervical Cancer Classification Model  

Kim, Youn Ji (Department of Biomedical Engineering, Gachon University)
Park, Ye Rang (Department of Health Sciences and Technology, Gachon Advanced Institute for Health Sciences and Technology (GAIHST), Gachon University)
Kim, Young Jae (Department of Biomedical Engineering, Gachon University)
Ju, Woong (Department of Obstetrics & Gynecology, Ewha Womans University Seoul Hospital)
Nam, Kyehyun (Department of Obstetrics & Gynecology, Soonchunhyang University, Bucheon Hospital)
Kim, Kwang Gi (Department of Biomedical Engineering, Gachon University)
Publication Information
Journal of Biomedical Engineering Research / v.42, no.3, 2021 , pp. 80-85 More about this Journal
Abstract
We developed a model to classify the absence of cervical cancer using deep learning from the cervical image to which the histogram equalization algorithm was applied, and to compare the performance of each model. A total of 4259 images were used for this study, of which 1852 images were normal and 2407 were abnormal. And this paper applied Image Sharpening(IS), Histogram Equalization(HE), and Contrast Limited Adaptive Histogram Equalization(CLAHE) to the original image. Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity index for Measuring image quality(SSIM) were used to assess the quality of images objectively. As a result of assessment, IS showed 81.75dB of PSNR and 0.96 of SSIM, showing the best image quality. CLAHE and HE showed the PSNR of 62.67dB and 62.60dB respectively, while SSIM of CLAHE was shown as 0.86, which is closer to 1 than HE of 0.75. Using ResNet-50 model with transfer learning, digital image-processed images are classified into normal and abnormal each. In conclusion, the classification accuracy of each model is as follows. 90.77% for IS, which shows the highest, 90.26% for CLAHE and 87.60% for HE. As this study shows, applying proper digital image processing which is for cervical images to Computer Aided Diagnosis(CAD) can help both screening and diagnosing.
Keywords
Cervical cancer; Histogram equalization; Classification; ResNet-50;
Citations & Related Records
연도 인용수 순위
  • Reference
1 https://www.cancer.gov/types/cervical/patient/cervical-treatment-pdq. Accessed on 5 Feb 2021.
2 https://www.ksog.org/public/index.php?sub=4. Accessed on 3 Feb 2021.
3 Kudva V, Prasad K, Guruvare S. Transfer Learning for Classification of Uterine Cervix Images for Cervical Cancer Screening. Lecture Notes in Electrical Engineering. 2020; 614:299-312.   DOI
4 Ullah Z, Farooq MU, Lee SH, An D. A hybrid image enhancement based brain MRI images classification technique. Medical Hypotheses. 2020;143:109922.   DOI
5 Singh RP, Dixit M. Histogram Equalization: A Strong Technique for Image Enhancement. International Journal of Signal Processing, Image Processing and Pattern Recognition. 2015;8(8):345-352.   DOI
6 https://docs.opencv.org/3.4/d4/d1b/tutorial_histogram_equalization.html. Accessed on 17 Feb 2021.
7 Kim M. Feature Extraction on a Periocular Region and Person Authentication Using a ResNet Model. Journal of Korea Multimedia Society. 2019;22(1):1347-1355
8 Jeelani H, Martin J, Vasquez F, Salerno M, Weller DS. Image quality affects deep learning reconstruction of MRI. International Symposium on Biomedical Imaging. 2018;357-360.
9 http://opendata.hira.or.kr/op/opc/olap3thDsInfo.do. Accessed on 23 Feb 2021.
10 Korea Central Cancer Registry, National Cancer Center. Annual report of cancer statistics in Korea in 2017. Ministry of Health and Welfare. 2019; 33.
11 Suralkar SR, Rajput, S. Enhancement of Images Using Contrast Image Enhancement Techniques. International Journal of Recent Advances in Engineering & Technology. 2020;8(3):16-20.   DOI
12 Gonzalez RC, Woods RE. Digital Image Processing 3rd Edition (Issue 3). New Jersey, Pearson Education, Inc. 2008;394-460.
13 Yun JW. Deep Residual Learning for Image Recognition arXiv:1512.03385v1. Enzyme and Microbial Technology. 1996;19(2):107-117.   DOI
14 Alyafeai Z, Ghouti L. A fully-automated deep learning pipeline for cervical cancer classification. Expert Systems with Applications. 2020;141.
15 Kurt B, Nabiyev VV, Turhan K. Medical images enhancement by using anisotropic filter and CLAHE. INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications. 2012;1-4.
16 Zarchi MK, Binesh F, Kazemi Z, Teimoori S, Soltani HR, Chiti Z. Value of colposcopy in the early diagnosis of cervical cancer in patients with abnormal pap smears at Shahid Sadoughi Hospital, Yazd. Asian Pacific Journal of Cancer Prevention. 2011;12(12):3439-3441.
17 Wu M, Yan C, Liu H, Liu Q, Yin Y. Automatic classification of cervical cancer from cytological images by using convolutional neural network. Bioscience Reports. 2018;38(6):1-9.
18 Russo F. Piecewise Linear Model-Based Image Enhancement. EURASIP J. Adv. Signal Process. 2004;983173.
19 Weiss K, Khoshgoftaar TM, Wang DD. A survey of transfer learning. In Journal of Big Data. Springer International Publishing. 2016;3(1).
20 Hore A, Ziou D. Image quality metrics: PSNR vs. SSIM. International Conference on Pattern Recognition. 2010;2366-2369.
21 https://www.hira.or.kr/bbsDummy.do;INTERSESSIONID=g4BoNr8ikGPGbzbX8V4OWHwPnvCxfaVCw8Ef9JZb9LzudJguEp37!1206362664!375626493?pgmid=HIRAA020041000100&brdScnBltNo=4&brdBltNo=9774. Accessed on 15 Feb 2021.
22 Ulku EE, Camurcu AY. Computer aided brain tumor detection with histogram equalization and morphological image processing techniques. ICECCO 2013. 2013;48-51.
23 Wang Z, Bovik AC, Sheikh HR, Simoncelli E.P. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing. 2004;13(4):600-612   DOI
24 Coppleson, LW. Barry Brown. Estimation of the screening error rate from the observed detection rates in repeated cervical cytology. American Journal of Obstetrics and Gynecology. 1974;119(7):953-958.   DOI
25 Lange H. Automatic detection of multi-level acetowhite regions in RGB color images of the uterine cervix. Medical Imaging 2005: Image Processing. 2005;5747:1004.   DOI
26 Lee Y, Kim HJ, Kim GB, Kim N. Deep Learning-based Feature Extraction for Medical Image Analysis. 2014;1-12.
27 Guo P, Singh S, Xue Z, Long R, Antani S. Deep learning for assessing image focus for automated cervical cancer screening. 2019 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2019. 2019;2019-2022.
28 Ziaei A, Yeganeh H, Faez K, Sargolzaei S. A novel approach for contrast enhancement in biomedical images based on histogram equalization. BMEI 2008. 2008;1:855-858.
29 Kugelman J, Alonso-Caneiro D, Read SA, Vincent SJ, Chen FK, Collins MJ. Effect of Altered OCT Image Quality on Deep Learning Boundary Segmentation. IEEE Access. 2020; 8:43537-43553.   DOI
30 Nevriyanto A, Equalization AH. Enhancement, and Standard Median Filter (Noise Removal) with Pixel-Based and Human Visual System-Based Measurements. International Conference on Electrical Engineering and Computer Science. 2017;1(1): 114-119.
31 Kaur H, Rani J. MRI brain image enhancement using Histogram Equalization techniques. Proceedings of the 2016 IEEE International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2016. 2016;1: 770-773.
32 Srinivasan Y, Hernes D, Tulpule B, Yang S, Guo J, Mitra S, Yagneswaran S, Nutter B, Jeronimo J, Phillips B, Long R, Ferris D. A probabilistic approach to segmentation and classification of neoplasia in uterine cervix images using color and geometric features. Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 2005;5747(2):995-1003.
33 Kang K, Lee J. PSNR Appraisal of MRI image. 2009;3(4): 13-20.