Cataract surgery is a sight saving surgery that is performed over 10 million
times each year around the world. With such a large demand, the ability to
organize surgical wards and operating rooms efficiently is critical to delivery
this therapy in routine clinical care. In this context, estimating the
remaining surgical duration (RSD) during procedures is one way to help
streamline patient throughput and workflows. To this end, we propose CataNet, a
method for cataract surgeries that predicts in real time the RSD jointly with
two influential elements: the surgeon's experience, and the current phase of
the surgery. We compare CataNet to state-of-the-art RSD estimation methods,
showing that it outperforms them even when phase and experience are not
considered. We investigate this improvement and show that a significant
contributor is the way we integrate the elapsed time into CataNet's feature
extractor.
Description
[2106.11048] CataNet: Predicting remaining cataract surgery duration
%0 Journal Article
%1 marafioti2021catanet
%A Marafioti, Andrés
%A Hayoz, Michel
%A Gallardo, Mathias
%A Neila, Pablo Márquez
%A Wolf, Sebastian
%A Zinkernagel, Martin
%A Sznitman, Raphael
%D 2021
%J MICCAI 2021
%K cataract duration learning machine prediction surgery
%T CataNet: Predicting remaining cataract surgery duration
%U http://arxiv.org/abs/2106.11048
%X Cataract surgery is a sight saving surgery that is performed over 10 million
times each year around the world. With such a large demand, the ability to
organize surgical wards and operating rooms efficiently is critical to delivery
this therapy in routine clinical care. In this context, estimating the
remaining surgical duration (RSD) during procedures is one way to help
streamline patient throughput and workflows. To this end, we propose CataNet, a
method for cataract surgeries that predicts in real time the RSD jointly with
two influential elements: the surgeon's experience, and the current phase of
the surgery. We compare CataNet to state-of-the-art RSD estimation methods,
showing that it outperforms them even when phase and experience are not
considered. We investigate this improvement and show that a significant
contributor is the way we integrate the elapsed time into CataNet's feature
extractor.
@article{marafioti2021catanet,
abstract = {Cataract surgery is a sight saving surgery that is performed over 10 million
times each year around the world. With such a large demand, the ability to
organize surgical wards and operating rooms efficiently is critical to delivery
this therapy in routine clinical care. In this context, estimating the
remaining surgical duration (RSD) during procedures is one way to help
streamline patient throughput and workflows. To this end, we propose CataNet, a
method for cataract surgeries that predicts in real time the RSD jointly with
two influential elements: the surgeon's experience, and the current phase of
the surgery. We compare CataNet to state-of-the-art RSD estimation methods,
showing that it outperforms them even when phase and experience are not
considered. We investigate this improvement and show that a significant
contributor is the way we integrate the elapsed time into CataNet's feature
extractor.},
added-at = {2021-08-08T00:02:03.000+0200},
author = {Marafioti, Andrés and Hayoz, Michel and Gallardo, Mathias and Neila, Pablo Márquez and Wolf, Sebastian and Zinkernagel, Martin and Sznitman, Raphael},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2c8cf5754f9fad233aa578b94d9415acb/felixholm},
description = {[2106.11048] CataNet: Predicting remaining cataract surgery duration},
interhash = {54ef809d5ce310b36f6bfc9ac82caceb},
intrahash = {c8cf5754f9fad233aa578b94d9415acb},
journal = {MICCAI 2021},
keywords = {cataract duration learning machine prediction surgery},
note = {cite arxiv:2106.11048Comment: Accepted at MICCAI 2021},
timestamp = {2021-08-07T22:23:50.000+0200},
title = {CataNet: Predicting remaining cataract surgery duration},
url = {http://arxiv.org/abs/2106.11048},
year = 2021
}