Two-step artificial intelligence algorithm for liver segmentation automates anatomic virtual hepatectomy.
anatomic virtual hepatectomy
artificial intelligence
automatic liver segmentation
automatic liver vessel extraction
deep learning
Journal
Journal of hepato-biliary-pancreatic sciences
ISSN: 1868-6982
Titre abrégé: J Hepatobiliary Pancreat Sci
Pays: Japan
ID NLM: 101528587
Informations de publication
Date de publication:
Nov 2023
Nov 2023
Historique:
pubmed:
25
9
2023
medline:
25
9
2023
entrez:
25
9
2023
Statut:
ppublish
Résumé
Anatomic virtual hepatectomy with precise liver segmentation for hemilivers, sectors, or Couinaud's segments using conventional three-dimensional simulation is not automated and artificial intelligence (AI)-based algorithms have not yet been applied. Computed tomography data of 174 living-donor candidates for liver transplantation (training data) were used for developing a new two-step AI algorithm to automate liver segmentation that was validated in another 51 donors (validation data). The Pure-AI (no human intervention) and ground truth (GT, full human intervention) data groups were compared. In the Pure-AI group, the median Dice coefficients of the right and left hemilivers were highly similar, 0.95 and 0.92, respectively; sectors, posterior to lateral: 0.86-0.92, and Couinaud's segments 1-8: 0.71-0.89. Labeling of the first-order branch as hemiliver, right or left portal vein perfectly matched; 92.8% of the second-order (sectors); 91.6% of third-order (segments) matched between the Pure-AI and GT data. The two-step AI algorithm for liver segmentation automates anatomic virtual hepatectomy. The AI-based algorithm correctly divided all hemilivers, and more than 90% of the sectors and segments.
Sections du résumé
BACKGROUND
BACKGROUND
Anatomic virtual hepatectomy with precise liver segmentation for hemilivers, sectors, or Couinaud's segments using conventional three-dimensional simulation is not automated and artificial intelligence (AI)-based algorithms have not yet been applied.
METHODS
METHODS
Computed tomography data of 174 living-donor candidates for liver transplantation (training data) were used for developing a new two-step AI algorithm to automate liver segmentation that was validated in another 51 donors (validation data). The Pure-AI (no human intervention) and ground truth (GT, full human intervention) data groups were compared.
RESULTS
RESULTS
In the Pure-AI group, the median Dice coefficients of the right and left hemilivers were highly similar, 0.95 and 0.92, respectively; sectors, posterior to lateral: 0.86-0.92, and Couinaud's segments 1-8: 0.71-0.89. Labeling of the first-order branch as hemiliver, right or left portal vein perfectly matched; 92.8% of the second-order (sectors); 91.6% of third-order (segments) matched between the Pure-AI and GT data.
CONCLUSIONS
CONCLUSIONS
The two-step AI algorithm for liver segmentation automates anatomic virtual hepatectomy. The AI-based algorithm correctly divided all hemilivers, and more than 90% of the sectors and segments.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1205-1217Subventions
Organisme : Fujifilm Corporation
Organisme : Ministry of Education, Culture, Sports, Science, and Technology of Japan
ID : 19K09191
Informations de copyright
© 2023 Japanese Society of Hepato-Biliary-Pancreatic Surgery.
Références
Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71:209-249.
Cherqui D, Laurent A, Mocellin N, Tayar C, Luciani A, van Nhieu JT, et al. Liver resection for transplantable hepatocellular carcinoma: long-term survival and role of secondary liver transplantation. Ann Surg. 2009;250:738-746.
Zeyara A, Torén W, Søreide K, Andersson R. The liver-first approach for synchronous colorectal liver metastases: a systematic review and meta-analysis of completion rates and effects on survival. Scand J Surg. 2021;111:14574969211030131.
Mise Y, Hasegawa K, Satou S, Shindoh J, Miki K, Akamatsu N, et al. How has virtual hepatectomy changed the practice of liver surgery?: experience of 1194 virtual hepatectomy before liver resection and living donor liver transplantation. Ann Surg. 2018;268:127-133.
Wigmore SJ, Redhead DN, Yan XJ, Casey J, Madhavan K, Dejong CH, et al. Virtual hepatic resection using three-dimensional reconstruction of helical computed tomography angioportograms. Ann Surg. 2001;233:221-226.
Strasberg SM, Belghiti J, Clavien PA, Gadzijev E, Garden JO, Lau WY, et al. The Brisbane 2000 terminology of liver anatomy and resections. HPB. 2000;2:333-339.
Hasegawa K, Kokudo N, Imamura H, Matsuyama Y, Aoki T, Minagawa M, et al. Prognostic impact of anatomic resection for hepatocellular carcinoma. Ann Surg. 2005;242:252-259.
Shindoh J, Makuuchi M, Matsuyama Y, Mise Y, Arita J, Sakamoto Y, et al. Complete removal of the tumor-bearing portal territory decreases local tumor recurrence and improves disease-specific survival of patients with hepatocellular carcinoma. J Hepatol. 2016;64:594-600.
Lebre MA, Vacavant A, Grand-Brochier M, Rositi H, Abergel A, Chabrot P, et al. Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme. Comput Biol Med. 2019;110:42-51.
Alirr OI, Abd Rahni AA. Automatic atlas-based liver segmental anatomy identification for hepatic surgical planning. Int J Comput Assist Radiol Surg. 2020;15:239-248.
Kazami Y, Kaneko J, Keshwani D, Takahashi R, Kawaguchi Y, Ichida A, et al. Artificial intelligence enhances the accuracy of portal and hepatic vein extraction in computed tomography for virtual hepatectomy. J Hepatobiliary Pancreat Sci. 2021;29:359-368.
Wakabayashi G, Cherqui D, Geller DA, Abu Hilal M, Berardi G, Ciria R, et al. The Tokyo 2020 terminology of liver anatomy and resections: updates of the Brisbane 2000 system. J Hepatobiliary Pancreat Sci. 2021;29:6-15.
Bismuth H. Revisiting liver anatomy and terminology of hepatectomies. Ann Surg. 2013;257:383-386.
Le Foie CC. Etudes anatomiques et chirugicales. Paris: Masson & Cie; 1957.
Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 1986;323:533-536.
Dice LR. Measures of the amount of ecologic between species. Ecology. 1945;26:297-302.
Klyuzhin I, Chausse G, Bloise I, Lavista Ferres J, Uribe C, Rahmim A. Automated deep segmentation of healthy organs in PSMA PET/CT images. J Nucl Med. 2021;62:1410.
Bland JM, Altman DG. Comparing methods of measurement: why plotting difference against standard method is misleading. The Lancet. 1995;346:1085-1087.
Hashimoto D, Dohi T, Tsuzuki M, Horiuchi T, Ohta Y, Chinzei K, et al. Development of a computer-aided surgery system: three-dimensional graphic reconstruction for treatment of liver cancer. Surgery. 1991;109:589-596.
Kumon M. Anatomical study of the caudate lobe with special reference to portal venous and biliary branches using corrosion liver casts and clinical application. Liver Cancer. 2017;6:161-170.
Yoon JH, Lee JM, Jun JH, Suh KS, Coulon P, Han JK, et al. Feasibility of three-dimensional virtual surgical planning in living liver donors. Abdom Imaging. 2015;40:510-520.
Shindoh J, Mise Y, Satou S, Sugawara Y, Kokudo N. The intersegmental plane of the liver is not always flat-tricks for anatomical liver resection. Ann Surg. 2010;251:917-922.
Ishibashi Y, Sato TJ, Hirai I, Murakami G, Hata F, Hirata K. Ramification pattern and topographical relationship between the portal and hepatic veins in the left anatomical lobe of the human liver. Okajimas Folia Anat Jpn. 2001;78:75-82.
Sato F, Igami T, Ebata T, Yokoyama Y, Sugawara G, Mizuno T, et al. A study of the right intersectional plane (right portal scissura) of the liver based on virtual left hepatic trisectionectomy. World J Surg. 2014;38:3181-3185.