Artificial intelligence-based technology for enhancing the quality of simulation, navigation, and outcome prediction for hepatectomy

Abstract

In the past decade, artificial intelligence (AI)-based technology has been applied to develop a simulation and navigation system and a model for predicting surgical outcomes in hepatobiliary surgery. To identify the intrahepatic vascular structure and accurate liver segmentation and volumetry, AI technology has been applied in three-dimensional (3D) simulation software. Recently, 3D and 4D printing have been used as innovative technologies for tissue and organ fabrication, medical education, and preoperative planning. AI can empower 3D and 4D printing technologies. Attempts have been made to use AI technology in augmented reality for navigating and performing intraoperative ultrasound. To predict surgical outcomes and postoperative early recurrence in patients with hepatocellular carcinoma, a deep learning model can be useful. Indocyanine green fluorescence imaging is used in hepatobiliary surgery to visualize the anatomy of the bile duct, hepatic tumors, and hepatic segmental areas. AI technology was applied to fuse intraoperative near-infrared fluorescence and visible images. Preoperative simulation, intraoperative navigation, and models to predict surgical outcomes using AI technology can be clinically applied in hepatobiliary surgery. As shown in reliable and robust clinical studies, AI can be a useful tool in clinical practice to improve the safety and efficacy of hepatobiliary surgery.

Keywords

Artificial intelligence / hepatobiliary surgery / indocyanine green / preoperative imaging

References

[1] Gumbs AA,Karcz K.White paper: definitions of artificial intelligence and autonomous actions in clinical surgery.Art Int Surg2022;2:93-100

[2] Mise Y,Satou S.How has virtual hepatectomy changed the practice of liver surgery?.Ann Surg2018;268:127-33

[3] Kazami Y,Keshwani D.Artificial intelligence enhances the accuracy of portal and hepatic vein extraction in computed tomography for virtual hepatectomy.J Hepatobiliary Pancreat Sci2022;29:359-68

[4] Takamoto T,Nara S.Automated three-dimensional liver reconstruction with artificial intelligence for virtual hepatectomy.J Gastrointest Surg2022;26:2119-27

[5] Chen WF,Lin HY.Development of novel residual-dense-attention (RDA) U-net network architecture for hepatocellular carcinoma segmentation.Diagnostics2022;12:1916 PMCID:PMC9406579

[6] Koitka S,Theysohn JM.Fully automated preoperative liver volumetry incorporating the anatomical location of the central hepatic vein.Sci Rep2022;12:16479 PMCID:PMC9526715

[7] Mojtahed A,Connell J.Repeatability and reproducibility of deep-learning-based liver volume and Couinaud segment volume measurement tool.Abdom Radiol2022;47:143-51 PMCID:PMC8776724

[8] Lyu F,Yip TC,Yuen PC.Weakly supervised liver tumor segmentation using Couinaud segment annotation.IEEE Trans Med Imaging2022;41:1138-49

[9] Tanzi L,Porpiglia F.Real-time deep learning semantic segmentation during intra-operative surgery for 3D augmented reality assistance.Int J Comput Assist Radiol Surg2021;16:1435-45 PMCID:PMC8354939

[10] Lin J,Qi J.Dual-modality endoscopic probe for tissue surface shape reconstruction and hyperspectral imaging enabled by deep neural networks.Med Image Anal2018;48:162-76

[11] Luo H,Zhang S.Augmented reality navigation for liver resection with a stereoscopic laparoscope.Comput Methods Programs Biomed2020;187:105099

[12] Bertrand LR,Espinel Y.A case series study of augmented reality in laparoscopic liver resection with a deformable preoperative model.Surg Endosc2020;34:5642-8

[13] Phutane P,Poirot K.Preliminary trial of augmented reality performed on a laparoscopic left hepatectomy.Surg Endosc2018;32:514-5

[14] Barash Y,Lux A.Artificial intelligence for identification of focal lesions in intraoperative liver ultrasonography.Langenbecks Arch Surg2022;407:3553-60

[15] Mai RY,Meng WD.Artificial neural network model to predict post-hepatectomy early recurrence of hepatocellular carcinoma without macroscopic vascular invasion.BMC Cancer2021;21:283 PMCID:PMC7962237

[16] Mai RY,Bai T.Artificial neural network model for preoperative prediction of severe liver failure after hemihepatectomy in patients with hepatocellular carcinoma.Surgery2020;168:643-52

[17] Merath K,Mehta R.Use of machine learning for prediction of patient risk of postoperative complications after liver, pancreatic, and colorectal surgery.J Gastrointest Surg2020;24:1843-51

[18] Chu T,Zhang J.Application of a convolutional neural network for multitask learning to simultaneously predict microvascular invasion and vessels that encapsulate tumor clusters in hepatocellular carcinoma.Ann Surg Oncol2022;29:6774-83 PMCID:PMC9492610

[19] Li X,Du H.Deep convolutional neural network for preoperative prediction of microvascular invasion and clinical outcomes in patients with HCCs.Eur Radiol2022;32:771-82

[20] Ishizawa T.Fluorescence imaging for minimally invasive cancer surgery.Surg Oncol Clin N Am2019;28:45-60

[21] Zhang C,Tian J.Adaptive brightness fusion method for intraoperative near-infrared fluorescence and visible images.Biomed Opt Express2022;13:1243-60 PMCID:PMC8973195

[22] Bari H,Dasari BVM.Role of artificial intelligence in hepatobiliary and pancreatic surgery.World J Gastrointest Surg2021;13:7-18 PMCID:PMC7830072

[23] Christou CD.Role of three-dimensional printing and artificial intelligence in the management of hepatocellular carcinoma: challenges and opportunities.World J Gastrointest Oncol2022;14:765-93 PMCID:PMC9048537

[24] Saito Y,Morine Y,Sugimoto M.Essential updates 2020/2021: current topics of simulation and navigation in hepatectomy.Ann Gastroenterol Surg2022;6:190-6 PMCID:PMC8889864

[25] Meiabadi MS,Karamimoghadam M.Modeling the producibility of 3D printing in polylactic acid using artificial neural networks and fused filament fabrication.Polymers2021;13:3219 PMCID:PMC8512372

[26] Rojek I,Kopowski J,Piechowiak M.Reducing waste in 3D printing using a neural network based on an own elbow exoskeleton.Materials2021;14:5074 PMCID:PMC8433981

[27] Pugliese R.Artificial intelligence-empowered 3D and 4D printing technologies toward smarter biomedical materials and approaches.Polymers2022;14:2794 PMCID:PMC9319487

[28] Giannone F,Cherkaoui Z,Pessaux P.Augmented reality and image-guided robotic liver surgery.Cancers2021;13:6268 PMCID:PMC8699460

[29] Adballah M,Calvet L.Augmented reality in laparoscopic liver resection evaluated on an ex-vivo animal model with pseudo-tumours.Surg Endosc2022;36:833-43

[30] Landsman ML,Mook GA.Light-absorbing properties, stability, and spectral stabilization of indocyanine green.J Appl Physiol1976;40:575-83

[31] Ishizawa T,Masuda K.Intraoperative fluorescent cholangiography using indocyanine green: a biliary road map for safe surgery.J Am Coll Surg2009;208:e1-4

[32] Ishizawa T,Kokudo N.Fluorescent cholangiography using indocyanine green for laparoscopic cholecystectomy: an initial experience.Arch Surg2009;144:381-2

[33] Ishizawa T,Ijichi M,Hasegawa K.Fluorescent cholangiography illuminating the biliary tree during laparoscopic cholecystectomy.Br J Surg2010;97:1369-77

[34] Kono Y,Tani K.Techniques of fluorescence cholangiography during laparoscopic cholecystectomy for better delineation of the bile duct anatomy.Medicine2015;94:e1005 PMCID:PMC4504575

[35] Terasawa M,Mise Y.Applications of fusion-fluorescence imaging using indocyanine green in laparoscopic hepatectomy.Surg Endosc2017;31:5111-8

[36] Liu Y,Ji Y.Infrared and visible image fusion through details preservation.Sensors2019;19:4556 PMCID:PMC6832652

[37] Shen B,Shi X.Real-time intraoperative glioma diagnosis using fluorescence imaging and deep convolutional neural networks.Eur J Nucl Med Mol Imaging2021;48:3482-92 PMCID:PMC8440289

[38] Young K,Kejriwal S,Aulakh SS.Intraoperative in vivo imaging modalities in head and neck cancer surgical margin delineation: a systematic review.Cancers2022;14:3416 PMCID:PMC9323577

[39] Ochoa M,Yao R,Barroso M.High compression deep learning based single-pixel hyperspectral macroscopic fluorescence lifetime imaging in vivo.Biomed Opt Express2020;11:5401-24 PMCID:PMC7587256

[40] Marsden M,Deng YC.FLImBrush: dynamic visualization of intraoperative free-hand fiber-based fluorescence lifetime imaging.Biomed Opt Express2020;11:5166-80 PMCID:PMC7510860

[41] Wakiya T,Kimura N.CT-based deep learning enables early postoperative recurrence prediction for intrahepatic cholangiocarcinoma.Sci Rep2022;12:8428 PMCID:PMC9120508