Deep transfer learning from ordinary to capsule esophagogastroduodenoscopy for image quality controlling

Abstract

Quality controlling for capsule endoscopic images can be completed with the assistance of artificial intelligence, but the labeling process is time‐consuming. Domain adaption is a robust tool for cross‐domain learning to reach a consistent target. Current research aims to study the feasibility and effectiveness of domain adaption from ordinary endoscopic images to capsule endoscopic images in quality controlling. Dynamic adversarial adaptation network (DAAN) was trained to identify low‐quality images using ordinary endoscopic images with corresponding labels (source domain with supervision) and capsule endoscopic images without corresponding labels (target domain without supervision) so that image quality controlling can be transferred from ordinary to capsule endoscopic images. 62,850 images from capsule endoscopy and 17,434 images from ordinary endoscopy were included in developing deep learning models. In internal cross‐validation, DAAN achieved an average area under receiver operating characteristic curve (AUROC) of 0.8638 (95% confidence interval [CI] 0.6753–1.0000) in filtering low‐quality images for capsule endoscopic images, compared with CNN B/16 and L/32, which were also trained with ordinary endoscopic images with corresponding labels. 18,636 images from 355 patients who received capsule endoscopy were prospectively collected. The AUROC of DAAN reached 0.9471 (95% CI 0.9428–0.9511), which surpassed CNN (0.8570 and 95% CI [0.8529–0.8608]) and ViT (L/32: 0.8183 and 95% CI [0.8143–0.8220] and B/16: 0.7779 and 95% CI [0.7960–0.8036]). Domain adaption can complete image quality controlling task in capsule endoscopic images with the supervision of ordinary endoscopic images, whose quantity is smaller so that the annotation workload can be alleviated.

Deep learning system for screening AIDS-related cytomegalovirus retinitis with ultra-wide-field fundus images

“…We established these three models for the better application in various clinical situations. We adopted subject independently [ [38] , [39] ] five-fold cross validation [ [40] , [41] , [42] ] to fairly test the performance of the models and selected the optimal one, at the same time, convolutional neural network (CNN) architectures were fine-tuned with the pre-trained models constructed with ImageNet dataset [ 43 ]. Furthermore, cross-validation is carried out in a subject-independent manner, namely, the images from one patient will not be split into training and validation datasets.…”