Colonoscopy is an effective tool for early screening of colorectal diseases. However, the application of colonoscopy in distinguishing different intestinal diseases still faces great challenges of efficiency and accuracy. Here we constructed and evaluated a deep convolution neural network (CNN) model based on 117,055 images from 16,004 individuals, which achieved a high accuracy of 0.933 in the validation dataset in identifying patients with polyp, colitis, colorectal cancer (CRC) from normal. The proposed approach was further validated on multi-center real-time colonoscopy videos and images, which achieved accurate diagnostic performance on detecting colorectal diseases with high accuracy and precision to generalize across external validation datasets. The diagnostic performance of the model was further compared to the skilled endoscopists and the novices. In addition, our model has potential in diagnosis of adenomatous polyp and hyperplastic polyp with an area under the receiver operating characteristic curve of 0.975. Our proposed CNN models have potential in assisting clinicians in making clinical decisions with efficiency during application.
Abstract-The progressive anastomotic intimal hyperplasia has been considered as a major failure reason for coronary artery bypass grafting (CABG), which is associated with the abnormality of the hemodynamic conditions. We designed a set of plexiglass models which can serve as in vitro cells or tissue culture bioreactors, also serve as mechanical flow chambers in a physical perfusion system of CABG. The models of distal anastomosis with different angles were made of plexiglass material. The anastomotic angles α in three models are 60°, 30° and 15°, respectively. The numerical simulation models, reproducing from these physical models, were set up using a computer fluid dynamic (CFD) software. First, the numerical results showed that in the model with α=60° there is a high velocity characteristic on the floor of the host artery opposite the graft orifice, where significant intimal thickening is likely to occur. Decreasing α, the peak velocity will move to the outlet of host artery. Second, the stagnant flow region depends directly on the distance D (The distance from the heel of the graft to the center of stenosed site), the larger is the value of D, and the longer is the stagnant region. We also found the residual flow which is harmful to the orifice region and the distal portion of anastomotic gradually became more slender as severity of the stenosis increased. The results suggest that anastomotic angle and stenosed site are very important factors for preoperative investigation. A smaller α can eliminate the stagnation and decrease the risk of intimal thickening at the anastomotic junction, while a shorter D can decrease stagnant region. The results also showed that our perfusion system and the physical models are feasible for CABG studies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.