Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kelner, Ori, Weinstein, Or, Rivlin, Ehud, Goldenberg, Roman
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917612338806784
author Kelner, Ori
Weinstein, Or
Rivlin, Ehud
Goldenberg, Roman
author_facet Kelner, Ori
Weinstein, Or
Rivlin, Ehud
Goldenberg, Roman
contents Following the successful debut of polyp detection and characterization, more advanced automation tools are being developed for colonoscopy. The new automation tasks, such as quality metrics or report generation, require understanding of the procedure flow that includes activities, events, anatomical landmarks, etc. In this work we present a method for automatic semantic parsing of colonoscopy videos. The method uses a novel DL multi-label temporal segmentation model trained in supervised and unsupervised regimes. We evaluate the accuracy of the method on a test set of over 300 annotated colonoscopy videos, and use ablation to explore the relative importance of various method's components.
format Preprint
id arxiv_https___arxiv_org_abs_2306_06960
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks
Kelner, Ori
Weinstein, Or
Rivlin, Ehud
Goldenberg, Roman
Computer Vision and Pattern Recognition
Following the successful debut of polyp detection and characterization, more advanced automation tools are being developed for colonoscopy. The new automation tasks, such as quality metrics or report generation, require understanding of the procedure flow that includes activities, events, anatomical landmarks, etc. In this work we present a method for automatic semantic parsing of colonoscopy videos. The method uses a novel DL multi-label temporal segmentation model trained in supervised and unsupervised regimes. We evaluate the accuracy of the method on a test set of over 300 annotated colonoscopy videos, and use ablation to explore the relative importance of various method's components.
title Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.06960