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

Purpose: Mitral valve repair is a complex minimally invasive surgery of theheart valve. In this context, suture detection from endoscopic images is ahighly relevant task that provides quantitative information to analyse suturingpatterns, assess prosthetic configurations and produce augmented realityvisualisations. Facial or anatomical landmark detection tasks typically containa fixed number of landmarks, and use regression or fixed heatmap-basedapproaches to localize the landmarks. However in endoscopy, there are a varyingnumber of sutures in every image, and the sutures may occur at any location inthe annulus, as they are not semantically unique. Method: In this work, weformulate the suture detection task as a multi-instance deep heatmap regressionproblem, to identify entry and exit points of sutures. We extend our previouswork, and introduce the novel use of a 2D Gaussian layer followed by adifferentiable 2D spatial Soft-Argmax layer to function as a local non-maximumsuppression. Results: We present extensive experiments with multiple heatmapdistribution functions and two variants of the proposed model. In theintra-operative domain, Variant 1 showed a mean F1 of +0.0422 over thebaseline. Similarly, in the simulator domain, Variant 1 showed a mean F1 of+0.0865 over the baseline. Conclusion: The proposed model shows an improvementover the baseline in the intra-operative and the simulator domains. The data ismade publicly available within the scope of the MICCAI AdaptOR2021 Challengehttps://adaptor2021.github.io/, and the code athttps://github.com/Cardio-AI/suture-detection-pytorch/.DOI:10.1007/s11548-021-02523-w. The link to the open access article can befound here: https://link.springer.com/article/10.1007%2Fs11548-021-02523-w

Point detection through multi-instance deep heatmap regression for sutures in endoscopy