Development of an artificial intelligence system using deep learning to indicate anatomical landmarks during laparoscopic cholecystectomy.
Artificial intelligence
Bile duct injury
Deep learning
Landmark
Laparoscopic cholecystectomy
Journal
Surgical endoscopy
ISSN: 1432-2218
Titre abrégé: Surg Endosc
Pays: Germany
ID NLM: 8806653
Informations de publication
Date de publication:
04 2021
04 2021
Historique:
received:
10
07
2019
accepted:
04
04
2020
pubmed:
20
4
2020
medline:
3
7
2021
entrez:
20
4
2020
Statut:
ppublish
Résumé
The occurrence of bile duct injury (BDI) during laparoscopic cholecystectomy (LC) is an important medical issue. Expert surgeons prevent intraoperative BDI by identifying four landmarks. The present study aimed to develop a system that outlines these landmarks on endoscopic images in real time. An intraoperative landmark indication system was constructed using YOLOv3, which is an algorithm for object detection based on deep learning. The training datasets comprised approximately 2000 endoscopic images of the region of Calot's triangle in the gallbladder neck obtained from 76 videos of LC. The YOLOv3 learning model with the training datasets was applied to 23 videos of LC that were not used in training, to evaluate the estimation accuracy of the system to identify four landmarks: the cystic duct, common bile duct, lower edge of the left medial liver segment, and Rouviere's sulcus. Additionally, we constructed a prototype and used it in a verification experiment in an operation for a patient with cholelithiasis. The YOLOv3 learning model was quantitatively and subjectively evaluated in this study. The average precision values for each landmark were as follows: common bile duct: 0.320, cystic duct: 0.074, lower edge of the left medial liver segment: 0.314, and Rouviere's sulcus: 0.101. The two expert surgeons involved in the annotation confirmed consensus regarding valid indications for each landmark in 22 of the 23 LC videos. In the verification experiment, the use of the intraoperative landmark indication system made the surgical team more aware of the landmarks. Intraoperative landmark indication successfully identified four landmarks during LC, which may help to reduce the incidence of BDI, and thus, increase the safety of LC. The novel system proposed in the present study may prevent BDI during LC in clinical practice.
Sections du résumé
BACKGROUND
The occurrence of bile duct injury (BDI) during laparoscopic cholecystectomy (LC) is an important medical issue. Expert surgeons prevent intraoperative BDI by identifying four landmarks. The present study aimed to develop a system that outlines these landmarks on endoscopic images in real time.
METHODS
An intraoperative landmark indication system was constructed using YOLOv3, which is an algorithm for object detection based on deep learning. The training datasets comprised approximately 2000 endoscopic images of the region of Calot's triangle in the gallbladder neck obtained from 76 videos of LC. The YOLOv3 learning model with the training datasets was applied to 23 videos of LC that were not used in training, to evaluate the estimation accuracy of the system to identify four landmarks: the cystic duct, common bile duct, lower edge of the left medial liver segment, and Rouviere's sulcus. Additionally, we constructed a prototype and used it in a verification experiment in an operation for a patient with cholelithiasis.
RESULTS
The YOLOv3 learning model was quantitatively and subjectively evaluated in this study. The average precision values for each landmark were as follows: common bile duct: 0.320, cystic duct: 0.074, lower edge of the left medial liver segment: 0.314, and Rouviere's sulcus: 0.101. The two expert surgeons involved in the annotation confirmed consensus regarding valid indications for each landmark in 22 of the 23 LC videos. In the verification experiment, the use of the intraoperative landmark indication system made the surgical team more aware of the landmarks.
CONCLUSIONS
Intraoperative landmark indication successfully identified four landmarks during LC, which may help to reduce the incidence of BDI, and thus, increase the safety of LC. The novel system proposed in the present study may prevent BDI during LC in clinical practice.
Identifiants
pubmed: 32306111
doi: 10.1007/s00464-020-07548-x
pii: 10.1007/s00464-020-07548-x
pmc: PMC7940266
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1651-1658Références
Walker R (2001) The first laparoscopic cholecystectomy. JSLS 5:89–94
Soper NJ, Stockmann PT, Dunnegan DL, Ashley SW (1992) Laparoscopic cholecystectomy the new 'gold standard'? Arch Surg 127:917–923
doi: 10.1001/archsurg.1992.01420080051008
Pucher PH, Brunt LM, Fanelli RD, Asbun HJ, Aggarwal R (2015) SAGES expert Delphi consensus: critical factors for safe surgical practice in laparoscopic cholecystectomy. Surg Endosc 29:3074–3085
doi: 10.1007/s00464-015-4079-z
Davidoff AM, Pappas TN, Murray EA, Hilleren DJ, Johnson RD, Baker ME, Newman GE, Cotton PB, Meyers WC (1992) Mechanisms of major biliary injury during laparoscopic cholecystectomy. Ann Surg 215:196–202
doi: 10.1097/00000658-199203000-00002
Giger UF, Michel JM, Opitz I, Inderbitzin DT, Thomas K, Lukas K (2006) Risk factors for perioperative complications in patients undergoing laparoscopic cholecystectomy: analysis of 22,953 consecutive cases from the Swiss Association of Laparoscopic and Thoracoscopic Surgery database. J Am Coll Surg 203:723–728
doi: 10.1016/j.jamcollsurg.2006.07.018
Harboe KM, Bardram L (2011) The quality of cholecystectomy in Denmark: outcome and risk factors for 20,307 patients from the national database. Surg Endosc 25:1630–1641
doi: 10.1007/s00464-010-1453-8
Navez B, Ungureanu F, Michiels M, Claeys D, Muysoms F, Hubert C, Vanderveken M, Detry O, Detroz B, Closset J, Devos B, Kint M, Navez J, Zech F, Gigot JF (2012) Surgical management of acute cholecystitis: results of a 2-year prospective multicenter survey in Belgium. Surg Endosc 26:2436–2445
doi: 10.1007/s00464-012-2206-7
Steven MS (2002) Avoidance of biliary injury during laparoscopic cholecystectomy. J Hepatobiliary Pancreat Surg 9:543–547
doi: 10.1007/s005340200071
Hugh TB (2002) New strategies to prevent laparoscopic bile duct injury–surgeons can learn from pilots. Surgery 132:826–835
doi: 10.1067/msy.2002.127681
Iwashita Y, Hibi T, Ohyama T, Umezawa A, Takada T, Strasberg SM, Asbun HJ, Pit HA, Han HS, Hwang T, Suzuki K, Yoon Y, Choi I, Yoon DS, Huang WS, Yoshida M, Wakabayashi G, Miura F, Okamoto K, Endo I, Santibañes E, Giménez ME, Windsor JA, Garden OJ, Gouma DJ, Cherqui D, Belli G, Dervenis C, Deziel DJ, Jonas E, Jagannath P, Supe AN, Singh H, Liau K, Chen X, Chan ACW, Lau WY, Fan ST, Chen M, Kim M, Honda G, Sugioka A, Asai K, Wada K, Mori Y, Higuchi R, Misawa T, Watanabe M, Matsumura N, Rikiyama T, Sata N, Kano N, Tokumura H, Kimura T, Kitano S, Inomata M, Hirata K, Sumiyama Y, Inui K, Yamamoto M (2017) Delphi consensus on bile duct injuries during laparoscopic cholecystectomy: an evolutionary cul-de-sac or the birth pangs of a new technical framework? J Hepatobiliary Pancreat Sci 24:591–602
doi: 10.1002/jhbp.503
Ferzli G, Timoney M, Nazir S, Swedler D, Fingerhut A (2015) Importance of the node of Calot in gallbladder neck dissection: an important landmark in the standardized approach to the laparoscopic cholecystectomy. J Laparoendosc Adv Surg Tech A 25:28–32
doi: 10.1089/lap.2014.0195
Rajkomar K, Bowman M, Rodgers M, Koea JB (2016) Quadrate lobe: a reliable landmark for bile duct anatomy during laparoscopic cholecystectomy. ANZ J Surg 86:560–562
doi: 10.1111/ans.13509
Strasberg SM, Brunt LM (2017) The critical view of safety: why it is not the only method of ductal identification within the standard of care in laparoscopic cholecystectomy. Ann Surg 265:464–465
doi: 10.1097/SLA.0000000000002054
Onoe S, Maeda A, Takayama Y, Fukami Y, Kaneoka Y (2017) A preoperative predictive scoring system to predict the ability to achieve the critical view of safety during laparoscopic cholecystectomy for acute cholecystitis. HPB (Oxford) 19:406–410
doi: 10.1016/j.hpb.2016.12.013
Honda G, Iwanaga T, Kurata M, Watanabe F, Satoh H, Iwasaki K (2009) The critical view of safety in laparoscopic cholecystectomy is optimized by exposing the inner layer of the subserosal layer. J Hepatobiliary Pancreat Surg 16:445–449
doi: 10.1007/s00534-009-0060-3
Vettoretto N, Saronni C, Harbi A, Balestra L, Taglietti L, Giovanetti M (2011) Critical view of safety during laparoscopic cholecystectomy. JSLS 15:322–325
doi: 10.4293/108680811X13071180407474
SAGES. THE SAGES SAFE CHOLECYSTECTOMY PROGRAM. Available at: https://www.sages.org/safe-cholecystectomy-program/ . September 2014; Accessed 10 December 2019
Schendel J, Ball C, Dixon E, Sutherland F, (2019) Prevalence of anatomic landmarks for orientation during elective laparoscopic cholecystectomies. Surg Endosc 2019: https://doi.org/10.1007/s00464-019-07131-z
Lockhart S, Singh-Ranger G (2018) Rouviere's sulcus-aspects of incorporating this valuable sign for laparoscopic cholecystectomy. Asian J Surg 41:1–3
doi: 10.1016/j.asjsur.2016.07.012
Girshick R (2015) Fast R-CNN. In: IEEE International Conference on Computer Vision, pp 1440–1448
Liu W, Anguelov D, Erhan D, Szedegy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multiBox detector. European Conference on Computer Vision. Springer, Cham, pp 21–37
Redman J, Farhadi A (2018) YOLOv3: An incremental improvement. Available at: https://pjreddie.com/darknet/yoloMay 2016; Accessed 21 June 2018.
Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. arXiv:1712.04621 [Cited 2018 12/6]. https://arxiv.org/pdf/1712.04621.pdf
Keras Image Preprocessing. Available at: March 2015; Accessed 3 August 2018.
Sah NP, Sahl SP, Khaniya S, Awale L, Shah RP, Agarwall CS, Adhikary S (2018) Extrahepatic biliary anatomy variation encountered during laparoscopic cholecystectomy. Int J Pharm 35:7–11
Way LW, Stewart L, Gantert W, Liu K, Lee CM, Whang K, Hunter JG (2003) Causes and prevention of laparoscopic bile duct injuries: analysis of 252 cases from a human factors and cognitive psychology perspective. Ann Surg 237:460–469
pubmed: 12677139
pmcid: 1514483
Strasberg SM (2002) Avoidance of biliary injury during laparoscopic cholecystectomy. J Hepatobiliary Pancreat Surg 9:543–547
doi: 10.1007/s005340200071
Massarweh NN, Devlin A, Symons RG, Broeckel Elrod JA, Flum DR (2009) Risk tolerance and bile duct injury: surgeon characteristics, risk-taking preference, and common bile duct injuries. J Am Coll Surg 209:17–24
doi: 10.1016/j.jamcollsurg.2009.02.063
Kim MG, Kwon SJ (2014) Comparison of the outcomes for laparoscopic gastrectomy performed by the same surgeon between a low-volume hospital and a high-volume center. Surg Endosc 28:1563–1570
doi: 10.1007/s00464-013-3352-2
Singla A, Simons JP, Carroll JE, Li Y, Ng SC, Tseng JF, Shah SA (2010) Hospital volume as a surrogate for laparoscopically assisted colectomy. Surg Endosc 24:662–669
doi: 10.1007/s00464-009-0665-2
Setio A, Ciompi F, Litjens G, Gerke P, Jacobs C, van Riel S, Wille M, Naqibullah M, Snchez C, van Ginneken B (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35:1160–1169
doi: 10.1109/TMI.2016.2536809
Siemens Healthineers. Angiography. Available at: https://www.siemens-healthineers.com/ . January 2019; Accessed 2 June 2019.
Misawa M, Kudo S, Mori Y, Cho T, Kataoka S, Yamauchi A, Ogawa Y, Maeda Y, Takeda K, Ichimasa K, Nakamura H, Yagawa Y, Toyoshima N, Ogata N, Kudo T, Hisayuki T, Hayashi T, Wakamura K, Baba T, Ishida F, Ito H, Holger R, Mori K (2018) Artificial intelligence-assisted polyp detection for colonoscopy: initial experience. Gastroenterology 154:2027–2029
doi: 10.1053/j.gastro.2018.04.003
Hirasawa T, Aoyama K, Tanimoto T, Ishihara S, Shichijo S, Ozawa T, Ohnishi T, Fujishiro M, Matsuo K, Fujisaki J, Tada T (2018) Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 21:653–660
doi: 10.1007/s10120-018-0793-2