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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Detection of surgical instruments plays a key role in ensuring patient safetyin minimally invasive surgery. In this paper, we present a novel method for 2Dvision-based recognition and pose estimation of surgical instruments thatgeneralizes to different surgical applications. At its core, we propose a novelscene model in order to simultaneously recognize multiple instruments as wellas their parts. We use a Convolutional Neural Network architecture to embodyour model and show that the cross-entropy loss is well suited to optimize itsparameters which can be trained in an end-to-end fashion. An additionaladvantage of our approach is that instrument detection at test time is achievedwhile avoiding the need for scale-dependent sliding window evaluation. Thisallows our approach to be relatively parameter free at test time and shows goodperformance for both instrument detection and tracking. We show that ourapproach surpasses state-of-the-art results on in-vivo retinal microsurgeryimage data, as well as ex-vivo laparoscopic sequences.

Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery