Automatic detection of ovarian cancer based on improved DWT transformation

  • Authors

    • Sabreena Rashid Yazd University
    • Rajdeep Kaur Yazd University
    2018-07-08
    https://doi.org/10.14419/ijet.v7i3.12572
  • Cancer Detection, Wavelet Transformation and Machine Learning, Support Vector Machine.

  • Ovarian cancer sub-kinds are distinct pathologic individual with dissimilar prognostic and therapeutic suggestions. Histo-typing by pathologists has good reproducibility; therefore, occasional cases are challenging and require immune histo chemistry and sub-specialty discussion. Motivated by the need for more accurate and reproducible diagnosis and to facilitate pathologist’s work-flow, implement an automated system for ovarian cancer classification and identification. The main problem discussed for detecting procedure fields: (i) the cancer detection on ultra sound image is not easy to classify on the basis of clustering or segmentation. It can involve the False Acceptance Rate and False Rejection Rate higher at the interval of time recognition from the knowledge base.(ii)The working accuracy rate is 90 to 95 of Normal SVM existing systems. Our technique is implemented by detection of the cancer stage accordingly workflow. We implement images of cancer at two enlargement and extract features like a, color, text and shape data using digital image processing techniques. We analyze the machine-learning algorithm and spatial domain algorithm used to extract the features in four phases: LL, HL, LH and HH. Extract the features used to dimension reduction and a SVM classification to divide the 5 ovarian cancer stages. The research paper represents, the details of our implementation and its validate on (Govt. hospital) clinically derived database of high-resolution diagnosis images. The new system attained a linear classification accuracy 98% when classifying un-seen tissues. The method has been implemented using simulation tool using MATLAB 2016a. The Ovarian Stages were then tested for the accuracy using transformation software. Testing consequences defined an accuracy of 94%, Specificity 0.99 and Sensitivity value is 0.9978 for MRI Medical Images respectively.

     

     

     

     

  • References

    1. [1] Li, Yan-E., Juan Zhang, Bin Han, and Lihua Li. "Identifying Ovarian Cancer Chemotherapy Response Relevant Gene Cliques." In Bioinformatics and Biomedicine (BIBM), 2011 IEEE International Conference on, pp. 294-298. IEEE, 2011.

      [2] Koshiyama, Masafumi, Noriomi Matsumura, and IkuoKonishi. "Clinical efficacy of ovarian cancer screening." Journal of Cancer 7, no. 10 (2016): 1311.https://doi.org/10.7150/jca.14615.

      [3] Khazendar, S., H. Al-Assam, H. Du, S. Jassim, A. Sayasneh, T. Bourne, J. Kaijser, and D. Timmerman. "Automated classification of static ultrasound images of ovarian tumours based on decision level fusion." In Computer Science and Electronic Engineering Conference (CEEC), 2014 6th, pp. 148-153. IEEE, 2014.

      [4] Renz, Christian, Jagath C. Rajapakse, Khalil Razvi, and Stephen KohChee Liang. "Ovarian cancer classification with missing data." In Neural Information Processing, 2002. ICONIP'02. Proceedings of the ninth International Conference on, vol. 2, pp. 809-813. IEEE, 2002.https://doi.org/10.1109/ICONIP.2002.1198171.

      [5] Cherkassky, Vladimir, and Yunqian Ma. "Practical selection of SVM parameters and noise estimation for SVM regression." Neural networks 17, no. 1 (2004): 113-126.https://doi.org/10.1016/S0893-6080(03)00169-2.

      [6] Gupta, Dipalee, and Siddhartha Choubey. "Discrete wavelet transform for image processing." International Journal of Emerging Technology and Advanced Engineering 4, no. 3 (2015): 598-602.

      [7] WENQING, LIU JIANZHUANG LI. "The Automatic thresholding of gray-level pictures via two-dimensional otsu method [J]." ActaAutomaticaSinica 1 (1993): 015.

      [8] Liu, Jianfei, Shijun Wang, Marius George Linguraru, Jianhua Yao, and Ronald M. Summers. "Augmenting tumor sensitive matching flow to improve detection and segmentation of ovarian cancer metastases within a PDE framework." In Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on, pp. 652-655. IEEE, 2013.

      [9] Kaur, Ada Rajneet. "Feature extraction and principal component analysis for lung cancer detection in CT scan images." International Journal of Advanced Research in Computer Science and Software Engineering 3, no. 3 (2013).

      [10] Acharya, U. Rajendra, S. VinithaSree, Luca Saba, Filippo Molinari, Stefano Guerriero, and Jasjit S. Suri. "Ovarian tumor characterization and classification using ultrasound—a new online paradigm." Journal of digital imaging 26, no. 3 (2013): 544-553.https://doi.org/10.1007/s10278-012-9553-8.

      [11] RajendraAcharya, U., Luca Saba, Filippo Molinari, Stefano Guerriero, and Jasjit S. Suri. "Ovarian tumor characterization and classification using ultrasound: A new online paradigm." (2013): 413-423.

      [12] Ullah, Irfan, Iftikhar Ahmad, HasanNisar, Saranjam Khan, RahatUllah, Rashad Rashid, and Hassan Mahmood. "Computer assisted optical screening of human ovarian cancer using Raman spectroscopy." Photodiagnosis and photodynamic therapy 15 (2016): 94-99.https://doi.org/10.1016/j.pdpdt.2016.05.011.

      [13] Bhattacharjee, Sharmistha, YumnamJayanta Singh, and Dipankar Ray. "Comparative performance analysis of machine learning classifiers on ovarian cancer dataset." In Research in Computational Intelligence and Communication Networks (ICRCICN), 2017 Third International Conference on, pp. 213-218. IEEE, 2017.

      [14] Kaur, Beant, Kulvinder Singh Mann, and ManpreetKaurGrewal. "Ovarian cancer stage based detection on convolutional neural network." In Communication and Electronics Systems (ICCES), 2017 2nd International Conference on, pp. 855-859. IEEE, 2017.

      [15] Lu, Yen-Chiao, Chi-Jie Lu, Chi-Chang Chang, and Yu-Wen Lin. "A hybrid of data mining and ensemble learning forecasting for recurrent ovarian cancer." In Intelligent Informatics and Biomedical Sciences (ICIIBMS), 2017 International Conference on, pp. 216-216. IEEE, 2017.

      [16] Yasodha, P., and N. R. Ananthanarayanan. "Detecting the ovarian cancer using big data analysis with effective model." Biomedical Research 29 (2018).

      [17] Wu, Miao, Chuanbo Yan, Huiqiang Liu, and Qian Liu. "Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks." Bioscience reports 38, no. 3 (2018): BSR20180289.https://doi.org/10.1042/BSR20180289.

      [18] Tsai, Meng-Hsiun, Ching-Hao Lai, Shin-Jr Lu, and Shun-Feng Su. "Performance comparisons between unsupervised clustering techniques for microarray data analysis on ovarian cancer." In Systems, Man and Cybernetics, 2006. SMC'06. IEEE International Conference on, vol. 5, pp. 3685-3690. IEEE, 2006.

      [19] Akutekwe, Arinze, and HuseyinSeker. "Two-stage computational bio-network discovery approach for metabolites: Ovarian cancer as a case study." In Biomedical and Health Informatics (BHI), 2014 IEEE-EMBS International Conference on, pp. 97-100. IEEE, 2014.

      [20] Babahosseini, Hesam, Paul C. Roberts, Eva M. Schmelz, and MasoudAgah. "Roles of bioactive sphingolipid metabolites in ovarian cancer cell biomechanics." In Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, pp. 2436-2439. IEEE, 2012.https://doi.org/10.1109/EMBC.2012.6346456.

      [21] Sameen, Sheema, Zoya Khalid, and ShaukatIqbal Malik. "In Silico Mining of MicroRNA Signatures in Human Ovarian Cancer." In Bioinformatics and Biomedical Engineering,(iCBBE) 2011 5th International Conference on, pp. 1-4. IEEE, 2011.https://doi.org/10.1109/icbbe.2011.5780100.

      [22] Janowczyk, Andrew, SharatChandran, Rajendra Singh, DimitraSasaroli, George Coukos, Michael D. Feldman, and AnantMadabhushi. "High-throughput biomarker segmentation on ovarian cancer tissue microarrays via hierarchical normalized cuts." IEEE Transactions on Biomedical Engineering 59, no. 5 (2012): 1240-1252.https://doi.org/10.1109/TBME.2011.2179546.

  • Downloads

  • How to Cite

    Rashid, S., & Kaur, R. (2018). Automatic detection of ovarian cancer based on improved DWT transformation. International Journal of Engineering & Technology, 7(3), 77-81. https://doi.org/10.14419/ijet.v7i3.12572