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) has many documented advantages, but thesurgeon's limited visual contact with the scene can be problematic. Hence,systems that can help surgeons navigate, such as a method that can produce a 3Dsemantic map, can compensate for the limitation above. In theory, we can borrow3D semantic mapping techniques developed for robotics, but this requiresfinding solutions to the following challenges in MIS: 1) semantic segmentation,2) depth estimation, and 3) pose estimation. In this paper, we propose thefirst 3D semantic mapping system from knee arthroscopy that solves the threechallenges above. Using out-of-distribution non-human datasets, where posecould be labeled, we jointly train depth+pose estimators using selfsupervisedand supervised losses. Using an in-distribution human knee dataset, we train afully-supervised semantic segmentation system to label arthroscopic imagepixels into femur, ACL, and meniscus. Taking testing images from human knees,we combine the results from these two systems to automatically create 3Dsemantic maps of the human knee. The result of this work opens the pathway tothe generation of intraoperative 3D semantic mapping, registration withpre-operative data, and robotic-assisted arthroscopy

3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training