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/

Zendy Plus

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

Zendy Tools

Zendy Open

Minimally Invasive Surgery (MIS) techniques have gained rapid popularityamong surgeons since they offer significant clinical benefits including reducedrecovery time and diminished post-operative adverse effects. However,conventional endoscopic systems output monocular video which compromises depthperception, spatial orientation and field of view. Suturing is one of the mostcomplex tasks performed under these circumstances. Key components of this tasksare the interplay between needle holder and the surgical needle. Reliable 3Dlocalization of needle and instruments in real time could be used to augmentthe scene with additional parameters that describe their quantitative geometricrelation, e.g. the relation between the estimated needle plane and its rotationcenter and the instrument. This could contribute towards standardization andtraining of basic skills and operative techniques, enhance overall surgicalperformance, and reduce the risk of complications. The paper proposes anAugmented Reality environment with quantitative and qualitative visualrepresentations to enhance laparoscopic training outcomes performed on asilicone pad. This is enabled by a multi-task supervised deep neural networkwhich performs multi-class segmentation and depth map prediction. Scarcity oflabels has been conquered by creating a virtual environment which resembles thesurgical training scenario to generate dense depth maps and segmentation maps.The proposed convolutional neural network was tested on real surgical trainingscenarios and showed to be robust to occlusion of the needle. The networkachieves a dice score of 0.67 for surgical needle segmentation, 0.81 for needleholder instrument segmentation and a mean absolute error of 6.5 mm for depthestimation.

Towards Augmented Reality-based Suturing in Monocular Laparoscopic Training