![]() ![]() Nevertheless, observation bias may lead to an erroneous diagnosis. Since polyps belonging to different categories have only minimal difference in texture, manual categorization is not recommended. Otherwise, biopsy sample is collected from that region for further examination such as pathological assays. If the polyp is normal, it can be simply removed through surgical procedures. When the endoscopists find a polyp, they comprehensively study the characteristics of the polyp and assess the level of its abnormality. For the colonoscopy examination, an endoscope scans the whole colon in real time. The current process of colonoscopy examination and abnormality detection is based on subjective analysis of the level of abnormality present in a polyp. The World Health Organization has recommended a thorough colonoscopy examination every three years for patients having colonic polyps 4. ‘Polyp’ generally describes a mass of tissue over-grown into the lumen of the gastrointestinal tract 3. Colonic polyps occur frequently and are more lethal than other types. One such technique is colonoscopy, which has become increasingly popular for early detection and prevention of colorectal carcinoma. Numerous techniques have been developed and routinely used for early detection and disease screening, helping our society to reducing the vulnerability of disease at a large extent 1, 2. Based on the comparison with four deep learning models, we demonstrate that the proposed approach out-performs the existing feature-based methods of colonic polyp identification.Įarly detection of disease especially cancer can save millions of lives and substantially reduce the healthcare and economic burden. Evaluation of our analytical approach using two datasets suggested that the feature descriptors could efficiently designate a colonic polyp, which subsequently can help the early detection of colorectal carcinoma. Finally, classification is performed using Least Square Support Vector Machine and Multi-layer Perceptron with five-fold cross-validation to avoid overfitting. Final descriptors selected after ANOVA are optimized using the fuzzy entropy-based feature ranking algorithm. Analysis of variance (ANOVA) is applied to measure statistical significance of the contribution of different descriptors between two colonic polyps: non-neoplastic and neoplastic. The nonsubsampled contourlet transform is used as texture and color feature descriptor, with different combinations of filters. Shape features are extracted using generic Fourier descriptor. A comprehensive analysis of these features is presented in this paper. Shape, texture, and color are critical features for assessing the degree of dysplasia in colonic polyps. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |