%0 Journal Article
%@ 18761100
%A Liew, W.S.
%A Tang, T.B.
%A Lu, C.-K.
%D 2022
%F scholars:17385
%I Springer Science and Business Media Deutschland GmbH
%J Lecture Notes in Electrical Engineering
%K Computer aided diagnosis; Computer aided instruction; Convolution; Convolutional neural networks; Deep neural networks; Diseases; Principal component analysis; Transfer learning, Colonic polyps; Colorectal cancer; Computer aided diagnostics; Convolutional neural network; Deep convolutional neural network; Diagnostics tools; Polyp; Pre-processing; Support vectors machine; Transfer learning, Support vector machines
%P 735-743
%R 10.1007/978-981-16-2183-3₇₁
%T Computer-Aided Diagnostic Tool for Classification of Colonic Polyp Assessment
%U https://khub.utp.edu.my/scholars/17385/
%V 758
%X Colorectal cancer is the third most common malignancy and the fourth leading cause of cancer-related deaths worldwide. This paper presents a combination of techniques (e.g., pre-processing, transfer learning, principal component analysis, and support vector machine) to detect the polyp during colonoscopy. In particular, we carefully choose the pre-trained deep convolutional neural networks (i.e., AlexNet, GoogLeNet, ResNet-50, and VGG-19) according to their performance extracting features. A publicly available database, Kvasir, is used to train and test the detection model. The result indicates that to use ResNet-50 as a pre-trained network provides the best results among the rest. Our proposed model achieves an accuracy of 99.39, and its sensitivity and specificity are 99.39, 99.41, and 99.38, respectively. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
%Z cited By 1; Conference of 1st International Conference on Artificial Intelligence for Smart Community, AISC 2020 ; Conference Date: 17 December 2020 Through 18 December 2020; Conference Code:286319