Cargando…

Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models

Video-recorded robotic-assisted surgeries allow the use of automated computer vision and artificial intelligence/deep learning methods for quality assessment and workflow analysis in surgical phase recognition. We considered a dataset of 209 videos of robotic-assisted laparoscopic inguinal hernia re...

Descripción completa

Detalles Bibliográficos
Autores principales: Zang, Chengbo, Turkcan, Mehmet Kerem, Narasimhan, Sanjeev, Cao, Yuqing, Yarali, Kaan, Xiang, Zixuan, Szot, Skyler, Ahmad, Feroz, Choksi, Sarah, Bitner, Daniel P., Filicori, Filippo, Kostic, Zoran
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10295003/
https://www.ncbi.nlm.nih.gov/pubmed/37370585
http://dx.doi.org/10.3390/bioengineering10060654
_version_ 1785063317048393728
author Zang, Chengbo
Turkcan, Mehmet Kerem
Narasimhan, Sanjeev
Cao, Yuqing
Yarali, Kaan
Xiang, Zixuan
Szot, Skyler
Ahmad, Feroz
Choksi, Sarah
Bitner, Daniel P.
Filicori, Filippo
Kostic, Zoran
author_facet Zang, Chengbo
Turkcan, Mehmet Kerem
Narasimhan, Sanjeev
Cao, Yuqing
Yarali, Kaan
Xiang, Zixuan
Szot, Skyler
Ahmad, Feroz
Choksi, Sarah
Bitner, Daniel P.
Filicori, Filippo
Kostic, Zoran
author_sort Zang, Chengbo
collection PubMed
description Video-recorded robotic-assisted surgeries allow the use of automated computer vision and artificial intelligence/deep learning methods for quality assessment and workflow analysis in surgical phase recognition. We considered a dataset of 209 videos of robotic-assisted laparoscopic inguinal hernia repair (RALIHR) collected from 8 surgeons, defined rigorous ground-truth annotation rules, then pre-processed and annotated the videos. We deployed seven deep learning models to establish the baseline accuracy for surgical phase recognition and explored four advanced architectures. For rapid execution of the studies, we initially engaged three dozen MS-level engineering students in a competitive classroom setting, followed by focused research. We unified the data processing pipeline in a confirmatory study, and explored a number of scenarios which differ in how the DL networks were trained and evaluated. For the scenario with 21 validation videos of all surgeons, the Video Swin Transformer model achieved ~0.85 validation accuracy, and the Perceiver IO model achieved ~0.84. Our studies affirm the necessity of close collaborative research between medical experts and engineers for developing automated surgical phase recognition models deployable in clinical settings.
format Online
Article
Text
id pubmed-10295003
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102950032023-06-28 Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models Zang, Chengbo Turkcan, Mehmet Kerem Narasimhan, Sanjeev Cao, Yuqing Yarali, Kaan Xiang, Zixuan Szot, Skyler Ahmad, Feroz Choksi, Sarah Bitner, Daniel P. Filicori, Filippo Kostic, Zoran Bioengineering (Basel) Article Video-recorded robotic-assisted surgeries allow the use of automated computer vision and artificial intelligence/deep learning methods for quality assessment and workflow analysis in surgical phase recognition. We considered a dataset of 209 videos of robotic-assisted laparoscopic inguinal hernia repair (RALIHR) collected from 8 surgeons, defined rigorous ground-truth annotation rules, then pre-processed and annotated the videos. We deployed seven deep learning models to establish the baseline accuracy for surgical phase recognition and explored four advanced architectures. For rapid execution of the studies, we initially engaged three dozen MS-level engineering students in a competitive classroom setting, followed by focused research. We unified the data processing pipeline in a confirmatory study, and explored a number of scenarios which differ in how the DL networks were trained and evaluated. For the scenario with 21 validation videos of all surgeons, the Video Swin Transformer model achieved ~0.85 validation accuracy, and the Perceiver IO model achieved ~0.84. Our studies affirm the necessity of close collaborative research between medical experts and engineers for developing automated surgical phase recognition models deployable in clinical settings. MDPI 2023-05-27 /pmc/articles/PMC10295003/ /pubmed/37370585 http://dx.doi.org/10.3390/bioengineering10060654 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zang, Chengbo
Turkcan, Mehmet Kerem
Narasimhan, Sanjeev
Cao, Yuqing
Yarali, Kaan
Xiang, Zixuan
Szot, Skyler
Ahmad, Feroz
Choksi, Sarah
Bitner, Daniel P.
Filicori, Filippo
Kostic, Zoran
Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
title Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
title_full Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
title_fullStr Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
title_full_unstemmed Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
title_short Surgical Phase Recognition in Inguinal Hernia Repair—AI-Based Confirmatory Baseline and Exploration of Competitive Models
title_sort surgical phase recognition in inguinal hernia repair—ai-based confirmatory baseline and exploration of competitive models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10295003/
https://www.ncbi.nlm.nih.gov/pubmed/37370585
http://dx.doi.org/10.3390/bioengineering10060654
work_keys_str_mv AT zangchengbo surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT turkcanmehmetkerem surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT narasimhansanjeev surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT caoyuqing surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT yaralikaan surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT xiangzixuan surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT szotskyler surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT ahmadferoz surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT choksisarah surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT bitnerdanielp surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT filicorifilippo surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels
AT kosticzoran surgicalphaserecognitionininguinalherniarepairaibasedconfirmatorybaselineandexplorationofcompetitivemodels