TY - JOUR
T1 - Multicentric validation of EndoDigest
T2 - a computer vision platform for video documentation of the critical view of safety in laparoscopic cholecystectomy
AU - Mascagni, Pietro
AU - Alapatt, Deepak
AU - Laracca, Giovanni Guglielmo
AU - Guerriero, Ludovica
AU - Spota, Andrea
AU - Fiorillo, Claudio
AU - Vardazaryan, Armine
AU - Quero, Giuseppe
AU - Alfieri, Sergio
AU - Baldari, Ludovica
AU - Cassinotti, Elisa
AU - Boni, Luigi
AU - Cuccurullo, Diego
AU - Costamagna, Guido
AU - Dallemagne, Bernard
AU - Padoy, Nicolas
N1 - Funding Information:
This study was partially supported by an EAES Research Grant 2017, by BPI France through Project CONDOR, and by French State Funds managed by the Agence Nationale de la Recherche (ANR) through the Investissements d’Avenir Program under Grant ANR-10- IAHU-02 (IHU-Strasbourg) and through the National AI Chair program under Grant ANR-20-CHIA-0029-01 (Chair AI4ORSafety).
Funding Information:
Pietro Mascagni, Deepak Alapatt, Giovanni Guglielmo Laracca, Ludovica Guerriero, Andrea Spota, Claudio Fiorillo, Armine Vardazaryan, Giuseppe Quero, Sergio Alfieri, Ludovica Baldari, Elisa Cassinotti, Luigi Boni, Diego Cuccurullo and Bernard Dallemagne have no conflicts of interest or financial ties to disclose. Guido Costamagna is an advisory committee/review panel member for Olympus and Cook Endoscopy and his institute receives grant funding from Boston Scientific. Nicolas Padoy is a scientific advisor to Caresyntax.
Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022
Y1 - 2022
N2 - Background: A computer vision (CV) platform named EndoDigest was recently developed to facilitate the use of surgical videos. Specifically, EndoDigest automatically provides short video clips to effectively document the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). The aim of the present study is to validate EndoDigest on a multicentric dataset of LC videos. Methods: LC videos from 4 centers were manually annotated with the time of the cystic duct division and an assessment of CVS criteria. Incomplete recordings, bailout procedures and procedures with an intraoperative cholangiogram were excluded. EndoDigest leveraged predictions of deep learning models for workflow analysis in a rule-based inference system designed to estimate the time of the cystic duct division. Performance was assessed by computing the error in estimating the manually annotated time of the cystic duct division. To provide concise video documentation of CVS, EndoDigest extracted video clips showing the 2 min preceding and the 30 s following the predicted cystic duct division. The relevance of the documentation was evaluated by assessing CVS in automatically extracted 2.5-min-long video clips. Results: 144 of the 174 LC videos from 4 centers were analyzed. EndoDigest located the time of the cystic duct division with a mean error of 124.0 ± 270.6 s despite the use of fluorescent cholangiography in 27 procedures and great variations in surgical workflows across centers. The surgical evaluation found that 108 (75.0%) of the automatically extracted short video clips documented CVS effectively. Conclusions: EndoDigest was robust enough to reliably locate the time of the cystic duct division and efficiently video document CVS despite the highly variable workflows. Training specifically on data from each center could improve results; however, this multicentric validation shows the potential for clinical translation of this surgical data science tool to efficiently document surgical safety.
AB - Background: A computer vision (CV) platform named EndoDigest was recently developed to facilitate the use of surgical videos. Specifically, EndoDigest automatically provides short video clips to effectively document the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). The aim of the present study is to validate EndoDigest on a multicentric dataset of LC videos. Methods: LC videos from 4 centers were manually annotated with the time of the cystic duct division and an assessment of CVS criteria. Incomplete recordings, bailout procedures and procedures with an intraoperative cholangiogram were excluded. EndoDigest leveraged predictions of deep learning models for workflow analysis in a rule-based inference system designed to estimate the time of the cystic duct division. Performance was assessed by computing the error in estimating the manually annotated time of the cystic duct division. To provide concise video documentation of CVS, EndoDigest extracted video clips showing the 2 min preceding and the 30 s following the predicted cystic duct division. The relevance of the documentation was evaluated by assessing CVS in automatically extracted 2.5-min-long video clips. Results: 144 of the 174 LC videos from 4 centers were analyzed. EndoDigest located the time of the cystic duct division with a mean error of 124.0 ± 270.6 s despite the use of fluorescent cholangiography in 27 procedures and great variations in surgical workflows across centers. The surgical evaluation found that 108 (75.0%) of the automatically extracted short video clips documented CVS effectively. Conclusions: EndoDigest was robust enough to reliably locate the time of the cystic duct division and efficiently video document CVS despite the highly variable workflows. Training specifically on data from each center could improve results; however, this multicentric validation shows the potential for clinical translation of this surgical data science tool to efficiently document surgical safety.
KW - Computer vision
KW - Critical view of safety
KW - Laparoscopic cholecystectomy
KW - Multicentric validation
KW - Surgical data science
KW - Video-based assessment
UR - http://www.scopus.com/inward/record.url?scp=85124835364&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124835364&partnerID=8YFLogxK
U2 - 10.1007/s00464-022-09112-1
DO - 10.1007/s00464-022-09112-1
M3 - Article
C2 - 35171336
AN - SCOPUS:85124835364
SN - 0930-2794
JO - Surgical Endoscopy
JF - Surgical Endoscopy
ER -