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

Flexible endoscopes for colonoscopy present several limitations due to theirinherent complexity, resulting in patient discomfort and lack of intuitivenessfor clinicians. Robotic devices together with autonomous control represent aviable solution to reduce the workload of endoscopists and the training timewhile improving the overall procedure outcome. Prior works on autonomousendoscope control use heuristic policies that limit their generalisation to theunstructured and highly deformable colon environment and require frequent humanintervention. This work proposes an image-based control of the endoscope usingDeep Reinforcement Learning, called Deep Visuomotor Control (DVC), to exhibitadaptive behaviour in convoluted sections of the colon tract. DVC learns amapping between the endoscopic images and the control signal of the endoscope.A first user study of 20 expert gastrointestinal endoscopists was carried outto compare their navigation performance with DVC policies using a realisticvirtual simulator. The results indicate that DVC shows equivalent performanceon several assessment parameters, being more safer. Moreover, a second userstudy with 20 novice participants was performed to demonstrate easier humansupervision compared to a state-of-the-art heuristic control policy. Seamlesssupervision of colonoscopy procedures would enable interventionists to focus onthe medical decision rather than on the control problem of the endoscope.

Colonoscopy Navigation using End-to-End Deep Visuomotor Control: A User Study