ClipAssistNet: Bringing Real-time Safety Feedback to Operating Rooms

Overview

Journal Int J Comput Assist Radiol Surg

Publisher Springer

Specialties General Surgery
Radiology

Date 2021 Jul 23

PMID 34297269

Citations 7

Authors

Florian Aspart

Jon L Bolmgren

Joel L Lavanchy

Guido Beldi

Michael S Woods

Nicolas Padoy

Enes Hosgor

Affiliations

Soon will be listed here.

Abstract

Purpose: Cholecystectomy is one of the most common laparoscopic procedures. A critical phase of laparoscopic cholecystectomy consists in clipping the cystic duct and artery before cutting them. Surgeons can improve the clipping safety by ensuring full visibility of the clipper, while enclosing the artery or the duct with the clip applier jaws. This can prevent unintentional interaction with neighboring tissues or clip misplacement. In this article, we present a novel real-time feedback to ensure safe visibility of the instrument during this critical phase. This feedback incites surgeons to keep the tip of their clip applier visible while operating.

Methods: We present a new dataset of 300 laparoscopic cholecystectomy videos with frame-wise annotation of clipper tip visibility. We further present ClipAssistNet, a neural network-based image classifier which detects the clipper tip visibility in single frames. ClipAssistNet ensembles predictions from 5 neural networks trained on different subsets of the dataset.

Results: Our model learns to classify the clipper tip visibility by detecting its presence in the image. Measured on a separate test set, ClipAssistNet classifies the clipper tip visibility with an AUROC of 0.9107, and 66.15% specificity at 95% sensitivity. Additionally, it can perform real-time inference (16 FPS) on an embedded computing board; this enables its deployment in operating room settings.

Conclusion: This work presents a new application of computer-assisted surgery for laparoscopic cholecystectomy, namely real-time feedback on adequate visibility of the clip applier. We believe this feedback can increase surgeons' attentiveness when departing from safe visibility during the critical clipping of the cystic duct and artery.

Citing Articles

Machine learning perioperative applications in visceral surgery: a narrative review.

Hossain I, Madani A, Laplante S Front Surg. 2024; 11:1493779.

PMID: 39539511 PMC: 11557547. DOI: 10.3389/fsurg.2024.1493779.

Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study.

Cao J, Yip H, Chen Y, Scheppach M, Luo X, Yang H Nat Commun. 2023; 14(1):6676.

PMID: 37865629 PMC: 10590425. DOI: 10.1038/s41467-023-42451-8.

Evolution of a surgical system using deep learning in minimally invasive surgery (Review).

Sone K, Tanimoto S, Toyohara Y, Taguchi A, Miyamoto Y, Mori M Biomed Rep. 2023; 19(1):45.

PMID: 37324165 PMC: 10265572. DOI: 10.3892/br.2023.1628.

Preserving privacy in surgical video analysis using a deep learning classifier to identify out-of-body scenes in endoscopic videos.

Lavanchy J, Vardazaryan A, Mascagni P, Mutter D, Padoy N Sci Rep. 2023; 13(1):9235.

PMID: 37286660 PMC: 10247775. DOI: 10.1038/s41598-023-36453-1.

A vision transformer for decoding surgeon activity from surgical videos.

Kiyasseh D, Ma R, Haque T, Miles B, Wagner C, Donoho D Nat Biomed Eng. 2023; 7(6):780-796.

PMID: 36997732 PMC: 10307635. DOI: 10.1038/s41551-023-01010-8.

References

Stulberg J, Huang R, Kreutzer L, Ban K, Champagne B, Steele S . Association Between Surgeon Technical Skills and Patient Outcomes. JAMA Surg. 2020; 155(10):960-968. PMC: 7439214. DOI: 10.1001/jamasurg.2020.3007. View

Lavanchy J, Zindel J, Kirtac K, Twick I, Hosgor E, Candinas D . Automation of surgical skill assessment using a three-stage machine learning algorithm. Sci Rep. 2021; 11(1):5197. PMC: 7933408. DOI: 10.1038/s41598-021-84295-6. View

Birkmeyer J, Finks J, OReilly A, Oerline M, Carlin A, Nunn A . Surgical skill and complication rates after bariatric surgery. N Engl J Med. 2013; 369(15):1434-42. DOI: 10.1056/NEJMsa1300625. View

Twinanda A, Yengera G, Mutter D, Marescaux J, Padoy N . RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations. IEEE Trans Med Imaging. 2018; 38(4):1069-1078. DOI: 10.1109/TMI.2018.2878055. View

Bodenstedt S, Rivoir D, Jenke A, Wagner M, Breucha M, Muller-Stich B . Active learning using deep Bayesian networks for surgical workflow analysis. Int J Comput Assist Radiol Surg. 2019; 14(6):1079-1087. DOI: 10.1007/s11548-019-01963-9. View

Yeung S, Downing N, Fei-Fei L, Milstein A . Bedside Computer Vision - Moving Artificial Intelligence from Driver Assistance to Patient Safety. N Engl J Med. 2018; 378(14):1271-1273. DOI: 10.1056/NEJMp1716891. View

Ross T, Zimmerer D, Vemuri A, Isensee F, Wiesenfarth M, Bodenstedt S . Exploiting the potential of unlabeled endoscopic video data with self-supervised learning. Int J Comput Assist Radiol Surg. 2018; 13(6):925-933. DOI: 10.1007/s11548-018-1772-0. View

Cho S, Kim Y, Jeong J, Kim I, Lee H, Kim N . Automatic tip detection of surgical instruments in biportal endoscopic spine surgery. Comput Biol Med. 2021; 133:104384. DOI: 10.1016/j.compbiomed.2021.104384. View

Woods M, Traverso L, Kozarek R, Donohue J, Fletcher D, Hunter J . Biliary tract complications of laparoscopic cholecystectomy are detected more frequently with routine intraoperative cholangiography. Surg Endosc. 1995; 9(10):1076-80. DOI: 10.1007/BF00188990. View

10.

Nwoye C, Mutter D, Marescaux J, Padoy N . Weakly supervised convolutional LSTM approach for tool tracking in laparoscopic videos. Int J Comput Assist Radiol Surg. 2019; 14(6):1059-1067. DOI: 10.1007/s11548-019-01958-6. View

11.

Twinanda A, Shehata S, Mutter D, Marescaux J, De Mathelin M, Padoy N . EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos. IEEE Trans Med Imaging. 2016; 36(1):86-97. DOI: 10.1109/TMI.2016.2593957. View

12.

Eisenstein S, Greenstein A, Kim U, Divino C . Cystic duct stump leaks: after the learning curve. Arch Surg. 2008; 143(12):1178-83. DOI: 10.1001/archsurg.143.12.1178. View

13.

Yamashita Y, Takada T, Kawarada Y, Nimura Y, Hirota M, Miura F . Surgical treatment of patients with acute cholecystitis: Tokyo Guidelines. J Hepatobiliary Pancreat Surg. 2007; 14(1):91-7. PMC: 2784499. DOI: 10.1007/s00534-006-1161-x. View

14.

Tzovaras G, Peyser P, Kow L, Wilson T, Padbury R, Toouli J . Minimally invasive management of bile leak after laparoscopic cholecystectomy. HPB (Oxford). 2008; 3(2):165-8. PMC: 2020798. DOI: 10.1080/136518201317077189. View

15.

Bouget D, Allan M, Stoyanov D, Jannin P . Vision-based and marker-less surgical tool detection and tracking: a review of the literature. Med Image Anal. 2016; 35:633-654. DOI: 10.1016/j.media.2016.09.003. View

16.

Richardson M, Bell G, Fullarton G . Incidence and nature of bile duct injuries following laparoscopic cholecystectomy: an audit of 5913 cases. West of Scotland Laparoscopic Cholecystectomy Audit Group. Br J Surg. 1996; 83(10):1356-60. DOI: 10.1002/bjs.1800831009. View

17.

Bonrath E, Gordon L, Grantcharov T . Characterising 'near miss' events in complex laparoscopic surgery through video analysis. BMJ Qual Saf. 2015; 24(8):516-21. DOI: 10.1136/bmjqs-2014-003816. View

18.

Jin Y, Li H, Dou Q, Chen H, Qin J, Fu C . Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med Image Anal. 2019; 59:101572. DOI: 10.1016/j.media.2019.101572. View

19.

van Dijk A, van Roessel S, de Reuver P, Boerma D, Boermeester M, Donkervoort S . Systematic review of cystic duct closure techniques in relation to prevention of bile duct leakage after laparoscopic cholecystectomy. World J Gastrointest Surg. 2018; 10(6):57-69. PMC: 6162244. DOI: 10.4240/wjgs.v10.i6.57. View

20.

Talebpour M, Alijani A, Hanna G, Moosa Z, Tang B, Cuschieri A . Proficiency-gain curve for an advanced laparoscopic procedure defined by observation clinical human reliability assessment (OCHRA). Surg Endosc. 2008; 23(4):869-75. DOI: 10.1007/s00464-008-0088-5. View