An Enhancement of Computer Aided Approach for Colon Cancer Detection in WCE Images Using ROI Based Color Histogram and SVM2
- 80 Downloads
The colon cancer is formed by uncontrollable growth of abnormal cells in large intestine or colon that can affect both men and women and it is third cancer disease in the world. At present, Wireless Capsule Endoscopy (WCE) screening method is utilized to identify colon cancer tumor at early stage to save the patient life who affected by the colon cancer. In this CTC method, the radiologist needs to analyze the colon polyps in digital image using computer aided approach with accurate automatic tumor classification to detect the cancer tumor at early stage. This kind of computer aided approach can operate as an intermediate between input digital image and radiologist. Therefore, in this paper, a novel computer aided approach is presented with ROI based color histogram and SVM2 to find the cancer tumor in WCE image. In this method, the digital WCE image can be preprocessed using filtering and ROI based color histogram depending on the salient region in colon. In common, the salient region can be distinctive because of low redundancy. Hence, the saliency is estimated by ROI based color histogram on the basis of color and structure contrast in given colon image for the further process of clustering and tumor classification in WCE image. The K-means clustering can be employed to cluster the preprocessed digital image to discover the tumor of colon. Subsequently, the features are extracted from the image in terms of contrast, correlation, energy and homogeneity by applying SGLDM method. The SVM2 classifier as input to classify the tumor is normal or malignancy using selected feature vectors. Here, the extracted features can also being combined to enhance the hybrid feature vector for the accurate tumor classification. Experimental results of proposed method can show that this presented technique can executes can tumor detection in colon image accurately reaching almost 95% in evaluation with existing algorithms.
KeywordsColon cancer Computer aided approach ROI extraction Image clustering Feature extraction SVM2 classifier
Compliance with Ethical Standards
Conflict of Interest
The author’s has no conflict of interest in submitting the manuscript to this journal.
This article does not contain any studies with human participants performed by any of the authors.
- 3.Park, C. H., Kim, J. O., Choi, M.-G., Kim, K. J., Kim, Y.-H., Kim, Y. S., Kim, T., Do, J. H., Ryu, J. K., Moon, J. S., Park, S.-H., Shim, K.-N., Lee, K. M., Lee, I. S., and Chun, H. J., Utility of capsule endoscopy for the classification of Crohn's disease: A multicenter study in Korea. Dig. Dis. Sci. 52(6):1405–1140, 2007.CrossRefGoogle Scholar
- 8.Vijayakumar, V., Priyan, M. K., Ushadevi, G., Varatharajan, R., Manogaran, G., and Tarare, P. V., E-health cloud security using timing enabled proxy re-encryption. Mobile Networks and Applications:1–12, 2018.Google Scholar
- 10.Mathan, K., Kumar, P. M., Panchatcharam, P., Manogaran, G., and Varadharajan, R., A novel Gini index decision tree data mining method with neural network classifiers for prediction of heart disease. Des. Autom. Embed. Syst.:1–18, 2018.Google Scholar
- 11.Priya, S., Varatharajan, R., Manogaran, G., Sundarasekar, R., and Kumar, P. M., Paillier homomorphic cryptosystem with poker shuffling transformation based water marking method for the secured transmission of digital medical images. Pers. Ubiquit. Comput.:1–11, 2018.Google Scholar
- 12.Varatharajan, R., Preethi, A. P., Manogaran, G., Kumar, P. M., and Sundarasekar, R., Stealthy attack detection in multi-channel multi-radio wireless networks. Multimed. Tools Appl.:1–24, 2018.Google Scholar
- 13.Manogaran, G., Shakeel, P. M., Hassanein, A. S., Priyan, M. K., and Gokulnath, C., Machine-learning approach based gamma distribution for Brian abnormalities detection and data sample imbalance analysis. IEEE Access, 2018.Google Scholar
- 14.Parthasarathy, P., Synthesis and UV detection characteristics of TiO2 thin film prepared through sol gel route. In IOP Conference Series: Materials Science and Engineering (Vol. 360, No. 1). IOP Publishing, 012056, 2018.Google Scholar
- 16.Varadharajan, R., Priyan, M. K., Panchatcharam, P., Vivekanandan, S., and Gunasekaran, M., A new approach for prediction of lung carcinoma using back propogation neural network with decision tree classifiers. J. Ambient. Intell. Humaniz. Comput.:1–12, 2018.Google Scholar
- 18.Sareena, Ajay Mittal and Manvjeet Kaur, “Computer-aided-diagnosis in colorectal cancer: A survey of state of the art techniques”, International Conference on Inventive Computation Technologies (ICICT), vol. 1, pp. 1–6, 2016.Google Scholar
- 20.Lokesh, S., Kumar, P. M., Devi, M. R., Parthasarathy, P., and Gokulnath, C., An automatic tamil speech recognition system by using bidirectional recurrent neural network with self-organizing map. Neural Comput. & Applic.:1–11, 2018.Google Scholar
- 21.Yanan, F., Zhang, W., Mandal, M., and Meng, M. Q.-H., Computer-aided bleeding detection in WCE video. IEEE Journal of Biomedical and Health Informatics 18(12):636–642, 2014.Google Scholar
- 25.Barbosa, D. J. C., Ramos J., and Lima, C. S., Detection of small bowel cancers in capsule endoscopy frames using texture analysis based on the discrete wavelet transform. 30th Annual International IEEE EMBS Conference Vancouver, British Columbia, Canada, August 20–24, 2008.Google Scholar
- 26.Parthasarathy, P., and Vivekanandan, S., A typical IoT architecture-based regular monitoring of arthritis disease using time wrapping algorithm. Int. J. Comput. Appl.:1–11, 2018.Google Scholar
- 27.Karargyris, A., and Bourbakis, N., Identification of ulcers in wireless capsule endoscopy videos. In: IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009, 554–557.Google Scholar