Computer-Aided Polyp Removal Detection in Endoscopic Images

One of the most common gastrointestinal (GI) diseases is polyps. It is capable of causing the most lethal colon and rectal cancers. As a result, it must be removed during the primitive stage. In this paper, we investigated seven different classifiers with seven distinct features and proposed a simple polyp removal detection approach. It has also compared the performance of all classifiers for the features. The researchers noted that the Support Vector Machine (SVM) classifier provided the highest result for all features except Auto Color Correlogram. Besides, Bag of Features has achieved the highest result accuracy of 70.35%, the precision of 69.93%, F1-score 70.66%, and recall 71.40% for SVM classifier among all the features. It is optimistic that the research will open a path for future research in Polyp removal classification.