Study on artificial intelligence recognition pre-processing algorithm for cervical cancer

Bo Feng; Chao Xu; Zhengping Li; Jusheng Li; Chuanyi Zhang

doi:10.4108/eetpht.10.7724

Authors

Bo Feng Anhui University
Chao Xu Anhui University
Zhengping Li Anhui University
Jusheng Li Nanjing University of Science and Technology
Chuanyi Zhang People's Hospital of Fanchang

DOI:

https://doi.org/10.4108/eetpht.10.7724

Keywords:

Cervical Intraepithelial Neoplasia, Image Enhancement, Neural Network Pre-Processing, Contrast Limited Adaptive Histogram Equalization, CLAHE

Abstract

INTRODUCTION: Cervical cancer is the most common malignant tumor in the female reproductive system, with the number of deaths due to cervical cancer in developing countries accounting for 80% of the global total. In China, the incidence rate of cervical cancer is increasing year by year. At present, the commonly used methods for cervical cancer screening include TCT, HPV testing, TCT+HPV combined testing, FRD, and VIA/VILI. Among them, although TCT+HPV combined testing has high sensitivity and specificity, it is costly and time-consuming. VIA/VILI screening is cost-effective, easy to operate, and suitable for promotion in economically underdeveloped areas.However, VIA/VILI screening relies on the subjective judgment of doctors, so its accuracy is relatively low in rural areas of China with a large population and a lack of well-trained doctors. To address this issue, computer-aided diagnosis (CAD) technology is needed to improve the accuracy and reliability of VIA/VILI screening.

OBJECTIVES: The implementation of artificial intelligence (AI)-based Visual Inspection with Acetic acid (VIA) screening and computer-aided diagnosis has the potential to significantly reduce the cost of cervical cancer screenings and increase the coverage rate of cervical cancer screenings, thus reducing the incidence rate of the disease. To this end, we have developed an AI preprocessing algorithm aimed at improving the accuracy of AI in detecting cervical cancer.

METHODS: Initially, the algorithm maps images to the YCrCb and Lab color spaces. Unlike traditional enhancement methods that mainly focus on the luminance channel, our method primarily enhances the Cr channel in the YCrCb color space and a channel in the Lab color space. This paper innovatively proposes the LT_CLAHE algorithm to enhance the Cr channel, obtaining an enhanced image with a bias towards blue-green colors, and uses the WLS algorithm to enhance the a channel, obtaining an enhanced image with a bias towards red colors. Subsequently, the enhanced images from both color spaces are fused to eliminate color distortion.

RESULTS: Experimental results show that our method significantly enhances the texture of lesions and outperforms traditional methods across various objective indicators. When the enhanced images from this paper are used as input for neural networks, there is also a significant increase in the accuracy of neural network detection.

Downloads

Download data is not yet available.

References

[1] Sung H, Ferlay J, Siegel R L, Laversanne M, Soerjomataram I, Jemal A and Bray F. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA: A Cancer Journal for Clinicians 2021; 71(3):209-249.

[2] National Health Commission Of The People's Republic Of C.Chinese guidelines for diagnosis and treatment of cervical cancer 2018 (English version). Chinese Journal of Cancer Research Chung-Kuo Yen Cheng Yen Chiu 2019;31(2):295-305.

[3] Denny L, Kuhn L, De Souza M, Pollack A E, Dupree W and Wright T C. Screen-and-treat approaches for cervical cancer prevention in low-resource settings - A randomized controlled trial. Jama-Journal of the American Medical Association 2005;294(17):2173-2181.

[4] Jeronimo J.Secondary Prevention of Cervical Cancer: American Society of Clinical Oncology Resource-Stratified Clinical Practice Guideline Summary (vol 13, pg 129, 2017). Journal of Oncology Practice 2017; 13(7):466-466.

[5] Arbyn M, Sankaranarayanan R, Muwonge R, Keita N, Dolo A, Mbalawa C G, Nouhou H, Sakande B, Wesley R, Somanathan T, Sharma A, Shastri S and Basu P. Pooled analysis of the accuracy of five cervical cancer screening tests assessed in eleven studies in Africa and India. International Journal of Cancer 2008; 123(1):153-160.

[6] Bhatla N, Gulati A, Mathur S R, Rani S, Anand K, Muwonge R and Sankaranarayanan R. Evaluation of cervical screening in rural North India. International Journal of Gynecology & Obstetrics 2009; 105(2):145-149.

[7] Ferreccio C, Bratti M C, Sherman M E, Herrero R, Wacholder S, Hildesheim A, Burk R D, Hutchinson M, Alfaro M, Greenberg M D, Morales J, Rodriguez A C, Schussler J, Eklund C, Marshall G and Schiffman M.A comparison of single and combined visual, cytologic, and virologic tests as screening strategies in a region at high risk of cervical cancer. Cancer Epidemiology Biomarkers & Prevention 2003; 12(9):815-823.

[8] Qureshi S, Das V and Zahra F. Evaluation of visual inspection with acetic acid and Lugol's iodine as cervical cancer screening tools in a low-resource setting. Tropical Doctor 2010; 40(1):9-12.

[9] Sankaranarayanan R, Basu P, Wesley R S, Mahe C, Keita N, Mbalawa C C G, Sharma R, Dolo A, Shastri S S, Nacoulma M, Nayama M, Somanathan T, Lucas H, Muwonge R, Frappart L, Parkin D M and Cervic I M S G. Accuracy of visual screening for cervical neoplasia: Results from an IARC multicentre study in India and Africa. International Journal of Cancer 2004; 110(6):907-913.

[10] Poli U R, Bidinger P D and Gowrishankar S.Visual Inspection with Acetic Acid (VIA) Screening Program:7 Years Experience in Early Detection of Cervical Cancer and Pre-Cancers in Rural South India.Indian Journal of Community Medicine 2015; 40(3):203-207.

[11] Adsul P, Manjunath N, Srinivas V, Arun A and Madhivanan P. Implementing community-based cervical cancer screening programs using visual inspection with acetic acid in India:A systematic review. Cancer Epidemiology 2017; 49:161-174.

[12] Underwood M, Arbyn M, Parry-Smith W, De Bellis-Ayres S,Todd R, Redman C W E and Moss E. Accuracy of colposcopy-directed punch biopsies: a systematic review and meta-analysis.Bjog-an International Journal of Obstetrics and Gynaecology 2012; 119(11):1293-1301.

[13] Hu L M, Bell D, Antani S K, Xue Z Y, Yu K, Horning M P, Gachuhi N, Wilson B K, Jaiswal M S, Befano B, Long L R, Herrero R, Einstein M H, Burk R D, Demarco M, Gage J C, Rodriguez A C, Wentzensen N and Schiffman M. An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening. Jnci-Journal of the National Cancer Institute 2019; 111(9):923-932.

[14] Li Y X, Chen J W, Xue P, Tang C, Chang J, Chu C Y, Ma K, Li Q, Zheng Y F and Qiao Y L.Computer-Aided Cervical Cancer Diagnosis Using Time-Lapsed Colposcopic Images. IEEE Transactions on Medical Imaging 2020; 39(11):3403-3415.

[15] Zhang S, Wang T, Dong J Y and Yu H. Underwater image enhancement via extended multi-scale Retinex. Neurocomputing 2017; 245:1-9.

[16] Palanisamy G, Ponnusamy P and Gopi V P. An improved luminosity and contrast enhancement framework for feature preservation in color fundus images. Signal Image and Video Processing 2019; 13(4):719-726.

[17] Zhou M, Jin K, Wang S Z, Ye J and Qian D H. Color Retinal Image Enhancement Based on Luminosity and Contrast Adjustment. IEEE Transactions on Biomedical Engineering 2018; 65(3):521-527.

[18] He K M, Sun J and Tang X O. Single Image Haze Removal Using Dark Channel Prior. Ieee Transactions on Pattern Analysis and Machine Intelligence 2011;33(12):2341-2353.

[19] Jeong C B, Kim K G, Kim T S and Kim S K. Comparison of image enhancement methods for the effective diagnosis in successive whole-body bone scans. Journal of Digital Imaging 2011; 24(3):424-436.

[20] Ibrahim H, Kong N S P. Brightness preserving dynamic histogram equalization for image contrast enhancement. Ieee Transactions on Consumer Electronics 2007;53(4):1752-1758.

[21] Wang Y, Chen Q and Zhang B M.Image enhancement based on equal area dualistic sub-image histogram equalization method. Ieee Transactions on Consumer Electronics 1999; 45(1):68-75.

[22] Reza A M.Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for real-time image enhancement. Journal of Vlsi Signal Processing Systems for Signal Image and Video Technology 2004; 38(1):35-44.

[23] DuLe V N, Wang Q Z, Gould T, Ramella-Roman J C and Pfefer T J. Vascular contrast in narrow-band and white light imaging. Applied Optics 2014; 53(18):4061-4071.

[24] Pandey A K, Sharma P D, Dheer P, Parida G K, Goyal H, Patel C, Bal C and Kumar R. Investigating the Role of Global Histogram Equalization Technique for (99m)Technetium-Methylene diphosphonate Bone Scan Image Enhancement. Indian Journal of Nuclear Medicine 2017; 32(4):283-288.

[25] Castellanos M R, Szerszen A, Gundry S, Pirog E C, Maiman M, Rajupet S, Gomez J P, Davidov A, Debata P R, Banerjee P and Fata J E. Diagnostic imaging of cervical intraepithelial neoplasia based on hematoxylin and eosin fluorescence. Diagnostic Pathology 2015;10:119(1)-119(14).

[26] Jobson D J, Rahman Z U and Woodell G A.A multiscale retinex for bridging the gap between color images and the human observation of scenes. Ieee Transactions on Image Processing 1997; 6(7):965-976.

[27] Wang S Q, Ma K D, Yeganeh H, Wang Z and Lin W S. A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images. Ieee Signal Processing Letters 2015; 22(12):2387-2390.

[28] Rezazadeh S and Coulombe S. A novel discrete wavelet transform framework for full reference image quality assessment. Signal Image and Video Processing 2013; 7(3):559-573.

[29] Shin J and Park R H. Histogram-Based Locality-Preserving Contrast Enhancement. Ieee Signal Processing Letters 2015; 22(9):1293-1296.

[30] Xiong L, Li H Q and Xu L. An enhancement method for color retinal images based on image formation model. Computer Methods and Programs in Biomedicine 2017; 143:137-150.

[31] Wang S, Ma K, Yeganeh H, Wang Z, Lin W J. A patch-structure representation method for quality assessment of contrast changed images. IEEE Signal Process 2015;22:2387-2390.

[32] Rezazadeh S, Coulombe S. A novel discrete wavelet transform framework for full reference image quality assessment. Signal Image Video Process 2013; 7:559-573.

[33] Shin J,Park R-H J. Histogram-based locality-preserving contrast enhancement. IEEE Signal Process 2015;22:1293-1296.

[34] Xiong L, Li H, Xu L J. An enhancement method for color retinal images based on image formation model. Comput. Methods Programs Biomed 2017; 143:137-150.

[35] Ghimire D, Lee J. Nonlinear transfer function-based local approach for color image enhancement. IEEE Transactions on Consumer Electronics 2011;57(2): 858-865.

[36] Zhaohong Zhang, Wei Huang, Xiaoling Xue, Lanni Wang, Xiaoli Sun. Clinical Significance of the Special Stain for Epithelial Tissue in the Examination of Cervical Lesions by the Special Stain for the Uterine Cervix. Chinese Journal of the Frontiers of Medical Science (Electronic Version) 2014, 9: 4.

[37] Pretorius R G, Belinson J L. Re: An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening. Journal of the National Cancer Institute 2019; 112(10).

[38] Yasunari, Miyagi, Kazuhiro. Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images. Molecular and clinical oncology 2019; 11(6):583-589.

[39] Zhang T,Luo Y M ,Li P. Cervical precancerous lesions classification using pre-trained densely connected convolutional networks with colposcopy images. Biomedical signal processing and control 2020; 55(Jan.):101566.1-101566.11.

[40] Ying Z, Li G, Ren Y, Wang R, Wang W. A new image contrast enhancement algorithm using exposure fusion framework. In Proceedings of the International Conference on Computer Analysis of Images and Patterns, Ystad, Sweden, 22–24 August 2017; pp. 36–46.

[41] [Online].Available:https://github.com/microsoft/cervical-cancer-image-dataset

[42] [Online]. Available:https://github.com/google/cervical-cancer-segmentation

[43] [Online].Available:https://www.kaggle.com/datasets/kmader/cervical-cancer-image-classi