No abstract

Colorectal cancer (CRC) is the third leading cause of cancer death globally. Early detection and removal of precancerous polyps can significantly reduce the chance of CRC patient death. Currently, the polyp detection rate mainly depends on the skill and expertise of gastroenterologists. Over time, unidentified polyps can develop into cancer. Machine learning has recently emerged as a powerful method in assisting clinical diagnosis. Several classification models have been proposed to identify polyps, but their performance has not been comparable to an expert endoscopist yet. Here, we propose a multiple classifier consultation strategy to create an effective and powerful classifier for polyp identification. This strategy benefits from recent findings that different classification models can better learn and extract various information within the image. Therefore, our Ensemble classifier can derive a more consequential decision than each individual classifier. The extracted combined information inherits the ResNet’s advantage of residual connection, while it also extracts objects when covered by occlusions through depth-wise separable convolution layer of the Xception model. Here, we applied our strategy to still frames extracted from a colonoscopy video. It outperformed other state-of-the-art techniques with a performance measure greater than 95% in each of the algorithm parameters. Our method will help researchers and gastroenterologists develop clinically applicable, computational-guided tools for colonoscopy screening. It may be extended to other clinical diagnoses that rely on image.

No abstract

In this paper, we address a current problem in medical image processing, the detection of colorectal cancer from colonoscopy videos. According to worldwide cancer statistics, colorectal cancer is one of the most common cancers. The process of screening and the removal of pre-cancerous cells from the large intestine is a crucial task to date. The traditional manual process is dependent on the expertise of the medical practitioner. In this paper, a two-stage classification is proposed to detect colorectal cancer. In the first stage, frames of colonoscopy video are extracted and are rated as significant if it contains a polyp, and these results are then aggregated in a second stage to come to an overall decision concerning the final classification of that frame to be neoplastic and non-neoplastic. In doing so, a comparative study is being made by considering the applicability of deep learning to perform this two-stage classification. The CNN models namely VGG16, VGG19, Inception V3, Xception, GoogLeNet, ResNet50, ResNet100, DenseNet, NASNetMobile, MobilenetV2, InceptionResNetV2 and fine-tuned version of each model is evaluated. It is observed that the VGG19 model is the best deep learning method for colonoscopy image diagnosis.

No abstract