CERVICAL CANCER DETECTION AND CLASSIFICATION USING MRIS

(Received: 29-Dec.-2021, Revised: 5-Mar.-2022 , Accepted: 7-Mar.-2022)

Authors Ichrak Khoulqi, Najlae Idrissi,

Keywords #Cervical cancer #MRI #Segmentation #Features #DCNNs #Transfer learning #Stacking #Classification

Abstract Cervical Cancer (CC) is the second most frequent malignancy in women worldwide, with a 60 % mortality rate; it is the leading cause of death worldwide. The majority of cervical cancer deaths occur in less developed countries where there is a lack of screening programs and sensitization about the disease. CC cannot be detected in its early stages, since it does not reveal any symptoms and has a long latent period. Accurate staging can aid radiologists in providing effective therapy by utilizing diagnostic methods such as MRIs. In this paper, two approaches are proposed. The first consists of introducing an automatic system for early detection of CC using image processing techniques and axial, sagittal T2-weighted MRIs for analysis to determine the pathological stage of tumour and identify the real impact of cancer, that will help the patient to be treated with high efficiency and properly. This detection process goes through three major steps; i.e., pre-processing to make the representation of MRIs significant and easy to be analyzed, then segmentation was performed by region growing and geometric deformable techniques to extract the region of interests (ROIs). In the next step, we extract two categories of features based on statistical and transform methods in order to describe our ROIs. At the final step, five classifiers were trained to classify the MRIs into two classes: benign or malign. The second approach aims to increase the performance of pre-trained Deep Convolutional Neural Networks (DCNNs) based on Transfer Learning (TL) used to classify our Female Pelvis Dataset (FP_Dataset) by adopting the stacking generalized method that provides a more efficient and robust classifier. Data augmentation is a pre-processing method applied to our MRIs and a dropout layer is used to prevent networks from overfitting in our small dataset. The results of experiments show that data augmentation and stacking generalization represent an efficient way to improve accuracy rate of classification.

References

[1] C. Xavier, J. Levêque and D. Riethmuller,"Cancers Gynécologiques Pelviens," ISBN: 978-2-294- 72937-9, Elsevier Masson, 2013.

[2] E. Belglaiaa and C. Mougin, "Le cancer du col de l’utérus: état des lieux et prévention au Maroc," Bulletin du Cancer, vol. 106, no. 11, pp. 1008-1022, 2019.

[3] American Cancer Society, "Cervical Cancer," [Online], Available: https://www.cancer.org/cancer/ cervical-cancer/about/key-statistics.html, February 2017.

[4] J. Bethanney, G. Umashankar, D. Sindu and N. Basilica, "Classification of Cervical Cancer from MRI Images Using Multiclass SVM Classifier," International Journal of Engineering and Technology (UAE), vol. 7, no. 2, DOI: 10.14419/ijet.v7i2.25.12351, 2018.

[5] M. Arya, N. Mittal and G. Singh, "Cervical Cancer Detection Using Segmentation on Pap Smear Images," Proc. of the International Conference on Informatics and Analytics (ICIA-16), pp. 1-5, DOI: 10.1145/2980258.2980311, 2016.

[6] P. Robert and A. Celine Kavida, "Classification of Microscopic Cervical Cancer Images Using Regional Features and HSI Model," International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 8S, pp. 24-28, June 2019.

[7] K. Sneha and C. Arunvinodh, "Cervical Cancer Detection and Classification Using Texture Analysis," Biomedical and Pharmacology Journal, vol. 9, no. 2, pp. 663-671, 2016.

[8] T. A. Sajeena and A. S. Jereesh, "Automated Cervical Cancer Detection through RGVF Segmentation and SVM Classification," Proc. of the IEEE International Conference on Computing and Network Communications (CoCoNet), DOI: 10.1109/CoCoNet.2015.7411260, Trivandrum, India, 2015.

[9] S. R. Salian and S. D. Sawarkar, "Melanoma Skin Lesion Classification Using Improved Efficientnetb3," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 8, no. 1, pp. 45-56, DOI: 10.5455/jjcit.71-1636005929, March 2022.

[10] T. G. Debelee, A. Gebreselasie, F. Schwenker, M. Amirian and D. Yohannes, "Classification of Mammograms Using Texture and CNN Based Extracted Features", Journal of Biomimetics, Biomaterials and Biomedical Engineering, vol. 42, pp. 79-97, 2019.

[11] M.Sandler, A.Howard, M.Zhu, A.Zhmoginov, and L.Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks", In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4510-4520), 2018.

[12] H. A. Almubarak, R. J. Stanley, R. Long et al., "Convolutional Neural Network Based Localized Classification of Uterine Cervical Cancer Digital Histology Images," Procedia Computer Science, vol. 114, pp. 281–287, 2017.

[13] G. Sun, S. Li, Y. Cao and F. Lang, "Cervical Cancer Diagnosis Based on Random Forest," International Journal of Performability Engineering, vol. 13, pp. 446–457, 2017.

[14] A. Makris, I. Kontopoulos and K. Tserpes, "COVID-19 Detection from Chest X-Ray Images Using Deep Learning and Convolutional Neural Networks," Proc. of the 11th Hellenic Conference on Artificial Intelligence, DOI: 10.1101/2020.05.22.20110817, 2020.

[15] C. Yuan, Y. Yao, B. Cheng et al., "The Application of Deep Learning Based Diagnostic System to Cervical Squamous Intraepithelial Lesions Recognition in Colposcopy Images," Scientific Reports, vol. 10, article ID: 11639, DOI: 10.1038/s41598-020-68252-3, 2020.

[16] S. Ho, E. Bullitt and G. Gerig, "Level-set Evolution with Region Competition: Automatic 3-D Segmentation of Brain Tumors," International Conference on Pattern Recognition, vol. I, pp. 532-535, Chapel Hill, NC 27599, USA.

[17] K. Karantzalos and D. Argialas, "A Region-based Level Set Segmentation for Automatic Detection of Man-made Objects from Aerial and Satellite Images," Photogrammetric Engineering & Remote Sensing, vol. 75, no. 6, pp. 667–677, June 2009.

[18] J. Fan, D. K. Y. Yau, A. K. Elmagarmid and W. G. Aref, "Automatic Image Segmentation by Integrating Color-edge Extraction and Seeded Region Growing," IEEE Transactions on Image Processing, vol. 10, no. 10, pp. 1454-1466, DOI: 10.1109/83.951532, Oct. 2001.

[19] M. Kocher and R. Leonardi, "Adaptive Region Growing Technique Using Polynomial Functions For Image Approximation," Signal Processing, vol. 11, no. 1, pp. 47-60, 1986.

[20] S. Saladi and N. Amutha Prabha, "Analysis of Denoising Filters on MRI Brain Images," International Journal of Imaging Systems and Technology, vol. 27, no. 3, pp. 201-208, 2017.

[21] C. Tomasi and R. Manduchi, "Bilateral Filtering for Gray and Color Images," Proc. of the IEEE 6th Int. Conf. on Computer Vision (IEEE Cat. No.98CH36271), pp. 839-846, Bombay, India. 1998.

[22] S. Paris and F. Durand, "Fast Approximation of the Bilateral Filter Using a Signal Processing Approach," Proc. of European Conference on Computer Vision (ECCV 2006), Part of the Lecture Notes in Computer Science Book Series, vol. 3954, pp. 568-580, 2006.

[23] B. K. J. Veronica, "An Effective Neural Network Model for Lung Nodule Detection in CT Images with Optimal Fuzzy Model," Multimedia Tools and Applications, vol. 79, pp. 14291–14311, 2020.

[24] B. Nugroho, E. Y. Puspaningrum and A. Yuniarti, "Performance of Face Recognition with Pre-process- ing Techniques on Robust Regression Method," International Journal of GEOMATE, vol. 15, no. 50, pp. 101-106, 2018.

[25] I. Khoulqi and N. Idrissi, "Segmentation and Classification of Cervical Cancer," Proc. of the IEEE 6th Int. Conf. on Optimization and Applications (ICOA), pp. 1-7, Beni Mellal, Morocco, 2020.

[26] A. Herbulot, Nonparametric Statistical Measurements for Image and Video Segmentation and Active Contour Minimization, Ph.D. Thesis, University of Nice-Sophia Antipolis, Nice, France, Oct. 2007.

[27] Jiang Xin, R. Zhang and S. Nie, "Image Segmentation Based on Level Set Method," Physics Procedia, vol. 33, pp. 840-845, DOI: 10.1016/j.phpro.2012.05.143, 2012.

[28] F. Chen, "Medical Image Segmentation Using Level Sets," Technical Report, University of Waterloo, Canada, pp. 1-8, 2008.

[29] C. Li, C. Xu, C. Gui and M. D. Fox, "Distance Regularized Level Set Evolution and Its Application to Image Segmentation," IEEE Transactions on Image Processing, vol. 19, no. 12, pp. 3243-3254, December 2010.

[30] A. Khadidos, V. Sanchez and C.-T. Li, "Weighted Level Set Evolution Based on Local Edge Features for Medical Image Segmentation," IEEE Transactions on Image Processing, vol. 26, no. 4, pp. 1979- 1991, 2017.

[31] J. Bethanney and E. Roslin, "Classification and Detection of Skin Cancer using Hybrid Texture Features," Biomedicine, vol. 37, no. 2, pp.214-22, 2017.

[32] Soumya M., Sneha K. and Arunvinodh C., "Cervical Cancer Detection and Classification Using Texture Analysis, "Biomedical and Pharmacology Journal, vol. 9, no. 2, 2016.

[33] I. Khoulqi and N. Idrissi, "Breast Cancer Image Segmentation and Classification," Proc. of the 4th International Conference on Smart City Applications, pp. 1-9, DOI:10.1145/3368756.3369039, 2019.

[34] S. Paris, "Le Multimédia et la Compression," Lavoisier, Hermes Science Publisher, 1, p. 208, Informatique, Jean-Charles Pomerol, 978-2-7462-2203-8.hal-00841603, 2009.

[35] W. Lin, Z. Wu, L. Lin, A. Wen and J. Li, "An Ensemble Random Forest Algorithm for Insurance Big Data Analysis," IEEE Access, vol. 5, pp. 16568-16575, DOI: 10.1109/ACCESS.2017.2738069, 2017.

[36] I. M. Nasser and S. S. Abu-Naser, "Predicting Tumor Category Using Artificial Neural Networks," International Journal of Academic Health and Medical Research (IJAHMR), vol. 3, no. 2, pp. 1-7, 2019.

[37] R. V. K. Reddy et al., "Prediction of Heart Disease Using Decision Tree Approach," International Journal of Advanced Research in Computer Science and Software Engineering, vol. 6, no. 3, 2016.

[38] L. E. Peterson, "K-nearest Neighbor," Scholarpedia, vol. 4, no. 2, Article ID: 1883, 2009.

[39] C. Krauss, X. A. Do and N. Huck, "Deep Neural Networks, Gradient-boosted Trees, Random Forests: Statistical Arbitrage on the S&P 500, " European Journal of Operational Research, vol. 259, no. 2, pp. 689-702, 2017.

[40] D. Theckedath and R. R. Sedamkar, "Detecting Affect States Using VGG16, ResNet50 and SE- ResNet50 Networks, "SN Computer Science, vol. 1, Article no. 79, pp. 1-7, 2020.

[41] G. Sun, S. Li, Y. Cao and F. Lang, "Cervical Cancer Diagnosis Based on Random Forest," International Journal of Performability Engineering, vol. 13, no. 4, pp. 446–457, 2017.

[42] D. M. Rouse and S. S. Hemami, "The Role of Edge Information to Estimate the Perceived Utility of Natural Images," Visual Communications Lab., School of Electrical and Computer Engineering, Cornell University, Ithaca, NY 14853, 2009.

[43] J. W. Prescott, M. Pennell, T. M. Best et al., "An Automated Method to Segment the Femur for Osteoarthritis Research," Proc. of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6364–6367, DOI: 10.1109/IEMBS.2009.5333257, 2009.

[44] P. K. Malli and S. Nandyal, "Machine Learning Technique for Detection of Cervical Cancer Using K- NN and Artificial Neural Network," International Journal of Emerging Trends & Technology in Computer Science (IJETTCS), vol. 6, no. 4, pp. 145-149, 2017.

[45] K. P. Chandran and U. V. Ratna Kumari, "Improving Cervical Cancer Classification on MR Images Using Texture Analysis and Probabilistic Neural Network," Int. J. of Engineering Sciences & Research Technology, vol. 4, pp. 3141-3145, 2015.

[46] A. I. Naimi and L. B. Balzer, "Stacked Generalization: An Introduction to Super Learning," European Journal of Epidemiology, vol. 33, no. 5, pp. 459-464, 2018.

[47] F. Chollet et al., "Xception: Deep Learning with Depthwise Separable Convolutions," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2017.195, Honolulu, HI, USA, 2017.

[48] T. Majeed et al., "Problems of Deploying CNN Transfer Learning to Detect Covid-19 from Chest X- rays," MedRxiv, DOI: 10.1101/2020.05.12.20098954, 2020.

[49] J. Dekhtiar et al., "Deep Learning for Big Data Applications in CAD and PLM–Research Review, Opportunities and Case Study," Computers in Industry, vol. 100, pp. 227-243, 2018.

[50] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, Las Vegas, NV, USA, 2016.

[51] Q. M. Ilyas and M. Ahmad, "An Enhanced Ensemble Diagnosis of Cervical Cancer: A Pursuit of Machine Intelligence towards Sustainable Health," IEEE Access, vol. 9, pp. 12374-12388, 2021.

[52] Akter, Laboni, Md Islam, Mabrook S. Al-Rakhami and Md Haque, "Prediction of Cervical Cancer from Behavior Risk Using Machine Learning Techniques," SN Computer Science, vol. 2, Article no. 177 pp. 1-10, 2021.

[53] B. Chitra and S. S. Kumar, "An Optimized Deep Learning Model Using Mutation-based Atom Search Optimization Algorithm for Cervical Cancer Detection," Soft Computing, vol. 25, no. 24, pp. 15363- 15376, 2021.

Abstract: Cervical Cancer (CC) is the second most frequent malignancy in women worldwide, with a 60 % mortality rate; it is the leading cause of death worldwide. The majority of cervical cancer deaths occur in less developed countries where there is a lack of screening programs and sensitization about the disease. CC cannot be detected in its early stages, since it does not reveal any symptoms and has a long latent period. Accurate staging can aid radiologists in providing effective therapy by utilizing diagnostic methods such as MRIs. In this paper, two approaches are proposed. The first consists of introducing an automatic system for early detection of CC using image processing techniques and axial, sagittal T2-weighted MRIs for analysis to determine the pathological stage of tumour and identify the real impact of cancer, that will help the patient to be treated with high efficiency and properly. This detection process goes through three major steps; i.e., pre-processing to make the representation of MRIs significant and easy to be analyzed, then segmentation was performed by region growing and geometric deformable techniques to extract the region of interests (ROIs). In the next step, we extract two categories of features based on statistical and transform methods in order to describe our ROIs. At the final step, five classifiers were trained to classify the MRIs into two classes: benign or malign. The second approach aims to increase the performance of pre-trained Deep Convolutional Neural Networks (DCNNs) based on Transfer Learning (TL) used to classify our Female Pelvis Dataset (FP_Dataset) by adopting the stacking generalized method that provides a more efficient and robust classifier. Data augmentation is a pre-processing method applied to our MRIs and a dropout layer is used to prevent networks from overfitting in our small dataset. The results of experiments show that data augmentation and stacking generalization represent an efficient way to improve accuracy rate of classification.
URL: https://jjcit.org/paper/160

,abstract={Cervical Cancer (CC) is the second most frequent malignancy in women worldwide, with a 60 % mortality rate; it is the leading cause of death worldwide. The majority of cervical cancer deaths occur in less developed countries where there is a lack of screening programs and sensitization about the disease. CC cannot be detected in its early stages, since it does not reveal any symptoms and has a long latent period. Accurate staging can aid radiologists in providing effective therapy by utilizing diagnostic methods such as MRIs. In this paper, two approaches are proposed. The first consists of introducing an automatic system for early detection of CC using image processing techniques and axial, sagittal T2-weighted MRIs for analysis to determine the pathological stage of tumour and identify the real impact of cancer, that will help the patient to be treated with high efficiency and properly. This detection process goes through three major steps; i.e., pre-processing to make the representation of MRIs significant and easy to be analyzed, then segmentation was performed by region growing and geometric deformable techniques to extract the region of interests (ROIs). In the next step, we extract two categories of features based on statistical and transform methods in order to describe our ROIs. At the final step, five classifiers were trained to classify the MRIs into two classes: benign or malign. The second approach aims to increase the performance of pre-trained Deep Convolutional Neural Networks (DCNNs) based on Transfer Learning (TL) used to classify our Female Pelvis Dataset (FP_Dataset) by adopting the stacking generalized method that provides a more efficient and robust classifier. Data augmentation is a pre-processing method applied to our MRIs and a dropout layer is used to prevent networks from overfitting in our small dataset. The results of experiments show that data augmentation and stacking generalization represent an efficient way to improve accuracy rate of classification.},
keywords={Cervical cancer,MRI,Segmentation,Features,DCNNs,Transfer learning,Stacking,Classification},
ISSN={2413-9351},
month={June}}

AB - Cervical Cancer (CC) is the second most frequent malignancy in women worldwide, with a 60 % mortality rate; it is the leading cause of death worldwide. The majority of cervical cancer deaths occur in less developed countries where there is a lack of screening programs and sensitization about the disease. CC cannot be detected in its early stages, since it does not reveal any symptoms and has a long latent period. Accurate staging can aid radiologists in providing effective therapy by utilizing diagnostic methods such as MRIs. In this paper, two approaches are proposed. The first consists of introducing an automatic system for early detection of CC using image processing techniques and axial, sagittal T2-weighted MRIs for analysis to determine the pathological stage of tumour and identify the real impact of cancer, that will help the patient to be treated with high efficiency and properly. This detection process goes through three major steps; i.e., pre-processing to make the representation of MRIs significant and easy to be analyzed, then segmentation was performed by region growing and geometric deformable techniques to extract the region of interests (ROIs). In the next step, we extract two categories of features based on statistical and transform methods in order to describe our ROIs. At the final step, five classifiers were trained to classify the MRIs into two classes: benign or malign. The second approach aims to increase the performance of pre-trained Deep Convolutional Neural Networks (DCNNs) based on Transfer Learning (TL) used to classify our Female Pelvis Dataset (FP_Dataset) by adopting the stacking generalized method that provides a more efficient and robust classifier. Data augmentation is a pre-processing method applied to our MRIs and a dropout layer is used to prevent networks from overfitting in our small dataset. The results of experiments show that data augmentation and stacking generalization represent an efficient way to improve accuracy rate of classification.

Download Full Text