English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Conventional Endoscopy (CE) and Wireless Capsule Endoscopy (WCE) are knowntools for diagnosing gastrointestinal (GI) tract disorders. Detecting theanatomical location of GI tract can help clinicians to determine a moreappropriate treatment plan, can reduce repetitive endoscopy and is important indrug-delivery. There are few research that address detecting anatomicallocation of WCE and CE images using classification, mainly because ofdifficulty in collecting data and anotating them. In this study, we present afew-shot learning method based on distance metric learning which combinestransfer-learning and manifold mixup scheme for localizing endoscopy frames andcan be trained on few samples. The manifold mixup process improves few-shotlearning by increasing the number of training epochs while reducingoverfitting, as well as providing more accurate decision boundaries. A datasetis collected from 10 different anatomical positions of human GI tract. Twomodels were trained using only 78 CE and 27 WCE annotated frames to predict thelocation of 25700 and 1825 video frames from CE and WCE, respectively. Inaddition, we performed subjective evaluation using nine gastroenterologists toshow the necessaity of having an AI system for localization. Various ablationstudies and interpretations are performed to show the importance of each step,such effect of transfer-learning approach, and impact of manifold mixup onperformance. The proposed method is also compared with various methods trainedon categorical cross-entropy loss and produced better results which show thatproposed method has potential to be used for endoscopy image classification.

Distance Metric-Based Learning with Interpolated Latent Features for Location Classification in Endoscopy Image and Video