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: Face detection is a needed component for the automatic analysis andassistance of human activities during surgical procedures. Efficient facedetection algorithms can indeed help to detect and identify the persons presentin the room, and also be used to automatically anonymize the data. However,current algorithms trained on natural images do not generalize well to theoperating room (OR) images. In this work, we provide a comparison ofstate-of-the-art face detectors on OR data and also present an approach totrain a face detector for the OR by exploiting non-annotated OR images.Methods: We propose a comparison of 6 state-of-the-art face detectors onclinical data using Multi-View Operating Room Faces (MVOR-Faces), a dataset ofoperating room images capturing real surgical activities. We then propose touse self-supervision, a domain adaptation method, for the task of facedetection in the OR. The approach makes use of non-annotated images tofine-tune a state-of-the-art detector for the OR without using any humansupervision. Results: The results show that the best model, namely the tinyface detector, yields an average precision of 0.536 at Intersection over Union(IoU) of 0.5. Our self-supervised model using non-annotated clinical dataoutperforms this result by 9.2%. Conclusion: We present the first comparison ofstate-of-the-art face detectors on operating room images and show that resultscan be significantly improved by using self-supervision on non-annotated data.

Face Detection in the Operating Room: Comparison of State-of-the-art Methods and a Self-supervised Approach