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: Automatic segmentation and classification of surgical activity iscrucial for providing advanced support in computer-assisted interventions andautonomous functionalities in robot-assisted surgeries. Prior works havefocused on recognizing either coarse activities, such as phases, orfine-grained activities, such as gestures. This work aims at jointlyrecognizing two complementary levels of granularity directly from videos,namely phases and steps. Method: We introduce two correlated surgicalactivities, phases and steps, for the laparoscopic gastric bypass procedure. Wepropose a Multi-task Multi-Stage Temporal Convolutional Network (MTMS-TCN)along with a multi-task Convolutional Neural Network (CNN) training setup tojointly predict the phases and steps and benefit from their complementarity tobetter evaluate the execution of the procedure. We evaluate the proposed methodon a large video dataset consisting of 40 surgical procedures (Bypass40).Results: We present experimental results from several baseline models for bothphase and step recognition on the Bypass40 dataset. The proposed MTMS-TCNmethod outperforms in both phase and step recognition by 1-2% in accuracy,precision and recall, compared to single-task methods. Furthermore, for steprecognition, MTMS-TCN achieves a superior performance of 3-6% compared to LSTMbased models in accuracy, precision, and recall. Conclusion: In this work, wepresent a multi-task multi-stage temporal convolutional network for surgicalactivity recognition, which shows improved results compared to single-taskmodels on the Bypass40 gastric bypass dataset with multi-level annotations. Theproposed method shows that the joint modeling of phases and steps is beneficialto improve the overall recognition of each type of activity.

Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures