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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Seven million people suffer surgical complications each year, but withsufficient surgical training and review, 50\% of these complications could beprevented. To improve surgical performance, existing research uses various deeplearning (DL) technologies including convolutional neural networks (CNN) andrecurrent neural networks (RNN) to automate surgical tool and workflowdetection. However, there is room to improve accuracy; real-time analysis isalso minimal due to the complexity of CNN. In this research, a novel DLarchitecture is proposed to integrate visual simultaneous localization andmapping (vSLAM) into Mask R-CNN. This architecture, vSLAM-CNN (vCNN), for thefirst time, integrates the best of both worlds, inclusive of (1) vSLAM forobject detection, by focusing on geometric information for region proposals,and (2) CNN for object recognition, by focusing on semantic information forimage classification, combining them into one joint end-to-end trainingprocess. This method, using spatio-temporal information in addition to visualfeatures, is evaluated on M2CAI 2016 challenge datasets, achieving thestate-of-the-art results with 96.8 mAP for tool detection and 97.5 mean Jaccardscore for workflow detection, surpassing all previous works, and reaching a 50FPS performance, 10x faster than the region-based CNN. A region proposal module(RPM) replaces the region proposal network (RPN) in Mask R-CNN, accuratelyplacing bounding boxes and lessening the annotation requirement. Furthermore, aMicrosoft HoloLens 2 application is developed to provide an augmented reality(AR)-based solution for surgical training and assistance.

A Novel Deep ML Architecture by Integrating Visual Simultaneous  Localization and Mapping (vSLAM) into Mask R-CNN for Real-time Surgical Video  Analysis