The application of artificial intelligence-based tools in the management of hepatocellular carcinoma: current status and future perspectives

Abstract

Artificial intelligence (AI) is rapidly advancing in hepatocellular carcinoma (HCC) management, offering promising applications across diagnosis, prognosis, and treatment. In histopathology, deep learning models have shown impressive accuracy in differentiating liver lesions and extracting prognostic information from tissue samples. For biomarker discovery, AI techniques applied to multi-omics data have identified novel prognostic signatures and predictors of immunotherapy response. In radiology, convolutional neural networks have demonstrated high performance in classifying hepatic lesions, grading tumors, and predicting microvascular invasion from computed tomography (CT) and magnetic resonance imaging (MRI) images. Multimodal AI models integrating histopathology, genomics, and clinical data are emerging as powerful tools for risk stratification. Large language models (LLMs) show potential to support clinical decision making and patient education, though concerns about accuracy remain. While AI holds immense promise, several challenges must be addressed, including algorithmic bias, data privacy, and regulatory compliance. The successful implementation of AI in HCC care will require ongoing collaboration between clinicians, data scientists, and ethicists. As AI technologies continue to evolve, they are expected to enable more personalized approaches to HCC management, potentially improving diagnosis, treatment selection, and patient outcomes. However, it is crucial to recognize that AI tools are designed to assist, not replace, clinical expertise. Continuous validation in diverse, real-world settings will be essential to ensure the reliability and generalizability of AI models in HCC care.

Keywords

Hepatocellular carcinoma / artificial intelligence / deep learning / precision medicine / radiomics

References

[1] Sung H,Siegel RL.Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.CA Cancer J Clin2021;71:209-49

[2] Rumgay H,Ferlay J.Global burden of primary liver cancer in 2020 and predictions to 2040.J Hepatol2022;77:1598-606 PMCID:PMC9670241

[3] Rodriguez LA,Liu L.Hepatocellular carcinoma in metabolic dysfunction-associated steatotic liver disease.JAMA Netw Open2024;7:e2421019 PMCID:PMC11240192

[4] Reig M.Antiviral therapy in the palliative setting of HCC (BCLC-B and -C).J Hepatol2021;74:1225-33

[5] Cabibbo G, Aghemo A, Lai Q, Masarone M, Montagnese S, Ponziani FR; Italian Association for the Study of the Liver (AISF). Optimizing systemic therapy for advanced hepatocellular carcinoma: the key role of liver function. Dig Liver Dis. 2022;54:452-60.

[6] Association for the Study of the Liver. EASL clinical practice guidelines: management of hepatocellular carcinoma.J Hepatol2018;69:182-236

[7] Singal AG,Yarchoan M.AASLD practice guidance on prevention, diagnosis, and treatment of hepatocellular carcinoma.Hepatology2023;78:1922-65 PMCID:PMC10663390

[8] Llovet JM, Villanueva A, Marrero JA, et al; AASLD Panel of Experts on Trial Design in HCC. Trial design and endpoints in hepatocellular carcinoma: AASLD consensus conference. Hepatology. 2021;73 Suppl 1:158-91.

[9] Calderaro J,Imbeaud S.Histological subtypes of hepatocellular carcinoma are related to gene mutations and molecular tumour classification.J Hepatol2017;67:727-38

[10] Sia D,Martinez-Quetglas I.Identification of an immune-specific class of hepatocellular carcinoma, based on molecular features.Gastroenterology2017;153:812-26

[11] Pecorelli A, Lenzi B, Gramenzi A, et al; Italian LiverCancer (ITA.LI.CA) group. Curative therapies are superior to standard of care (transarterial chemoembolization) for intermediate stage hepatocellular carcinoma. Liver Int. 2017;37:423-33.

[12] Davenport T.The potential for artificial intelligence in healthcare.Future Healthc J2019;6:94-8 PMCID:PMC6616181

[13] Cheng N,Zhou J.Deep learning-based classification of hepatocellular nodular lesions on whole-slide histopathologic images.Gastroenterology2022;162:1948-61.e7

[14] Shi JY,Ding GY.Exploring prognostic indicators in the pathological images of hepatocellular carcinoma based on deep learning.Gut2021;70:951-61

[15] Collins GS,Dhiman P.TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods.BMJ2024;385:e078378

[16] Rivera SC, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension. BMJ. 2020;370:m3210. PMCID:PMC7490785

[17] Chan HP,Hadjiiski LM.Deep learning in medical image analysis.Adv Exp Med Biol2020;1213:3-21 PMCID:PMC7442218

[18] Mall PK,Srivastav S.A comprehensive review of deep neural networks for medical image processing: recent developments and future opportunities.Healthc Anal2023;4:100216

[19] Rodriguez JPM,Silva VWK.Artificial intelligence as a tool for diagnosis in digital pathology whole slide images: a systematic review.J Pathol Inform2022;13:100138 PMCID:PMC9577128

[20] Kiani A,Rajpurkar P.Impact of a deep learning assistant on the histopathologic classification of liver cancer.NPJ Digit Med2020;3:23 PMCID:PMC7044422

[21] Chen RJ,Williamson DFK.Pan-cancer integrative histology-genomic analysis via multimodal deep learning.Cancer Cell2022;40:865-78.e6 PMCID:PMC10397370

[22] Le NQK,Cao Y.Sequence-based prediction model of protein crystallization propensity using machine learning and two-level feature selection.Brief Bioinform2023;24:bbad319

[23] Singhal K,Tu T.Large language models encode clinical knowledge.Nature2023;620:172-80 PMCID:PMC10396962

[24] Saillard C,Laifa O.Predicting survival after hepatocellular carcinoma resection using deep learning on histological slides.Hepatology2020;72:2000-13

[25] Yamashita R,Saleem A,Shen J.Deep learning predicts postsurgical recurrence of hepatocellular carcinoma from digital histopathologic images.Sci Rep2021;11:2047 PMCID:PMC7820423

[26] Chaudhary K,Lu L.Deep learning-based multi-omics integration robustly predicts survival in liver cancer.Clin Cancer Res2018;24:1248-59 PMCID:PMC6050171

[27] Zeng Q,Caruso S.Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology.J Hepatol2022;77:116-27

[28] Zeng Q, Klein C, Caruso S, et al; HCC-AI study group. Artificial intelligence-based pathology as a biomarker of sensitivity to atezolizumab-bevacizumab in patients with hepatocellular carcinoma: a multicentre retrospective study. Lancet Oncol. 2023;24:1411-22.

[29] Liu Y,Ma K.Identification of a tumour immune barrier in the HCC microenvironment that determines the efficacy of immunotherapy.J Hepatol2023;78:770-82

[30] Lipkova J,Chen B.Artificial intelligence for multimodal data integration in oncology.Cancer Cell2022;40:1095-110 PMCID:PMC10655164

[31] Nguyen HS,Nguyen NN,Tam KW.Predicting EGFR mutation status in non-small cell lung cancer using artificial intelligence: a systematic review and meta-analysis.Acad Radiol2024;31:660-83

[32] Hamm CA,Savic LJ.Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI.Eur Radiol2019;29:3338-47 PMCID:PMC7251621

[33] Zhen SH,Tao YB.Deep learning for accurate diagnosis of liver tumor based on magnetic resonance imaging and clinical data.Front Oncol2020;10:680 PMCID:PMC7271965

[34] Ding Y,Wang Y.Novel deep learning radiomics model for preoperative evaluation of hepatocellular carcinoma differentiation based on computed tomography data.Clin Transl Med2021;11:e570 PMCID:PMC8571950

[35] Xia TY,Meng XP.Predicting microvascular invasion in hepatocellular carcinoma using CT-based radiomics model.Radiology2023;307:e222729

[36] Jensen CT,Saleh MM.Reduced-dose deep learning reconstruction for abdominal CT of liver metastases.Radiology2022;303:90-8 PMCID:PMC8962777

[37] Peng J,Ning Z.Residual convolutional neural network for predicting response of transarterial chemoembolization in hepatocellular carcinoma from CT imaging.Eur Radiol2020;30:413-24 PMCID:PMC6890698

[38] Maida M,Lau LHS.The application of large language models in gastroenterology: a review of the literature.Cancers2024;16:3328 PMCID:PMC11475222

[39] Maida M, Ramai D, Mori Y, Dinis-Ribeiro M, Facciorusso A, Hassan C; and the AI-CORE (Artificial Intelligence COlorectal cancer Research) Working Group. The role of generative language systems in increasing patient awareness of colon cancer screening. Endoscopy. 2024;Online ahead of print.

[40] Truhn D,Kather JN.Large language models should be used as scientific reasoning engines, not knowledge databases.Nat Med2023;29:2983-4

[41] Clusmann J,Muti HS.The future landscape of large language models in medicine.Commun Med2023;3:141 PMCID:PMC10564921

[42] Cheng K,He Y.Artificial intelligence in sports medicine: could GPT-4 make human doctors obsolete?.Ann Biomed Eng2023;51:1658-62

[43] Yeo YH,Ng WH.Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma.Clin Mol Hepatol2023;29:721-32 PMCID:PMC10366789

[44] Cao JJ,Ghaziani TT.Accuracy of information provided by ChatGPT regarding liver cancer surveillance and diagnosis.AJR Am J Roentgenol2023;221:556-9

[45] Singal AG,Nahon P.Epidemiology and surveillance for hepatocellular carcinoma: new trends.J Hepatol2020;72:250-61 PMCID:PMC6986771

[46] Seyyed-Kalantari L,McDermott MBA,Ghassemi M.Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations.Nat Med2021;27:2176-82 PMCID:PMC8674135

[47] Chu CH,Khan SS.Age-related bias and artificial intelligence: a scoping review.Humanit Soc Sci Commun2023;10:510

[48] Kaissis GA,Rückert D.Secure, privacy-preserving and federated machine learning in medical imaging.Nat Mach Intell2020;2:305-11

[49] World Health Organization. Regulatory considerations on artificial intelligence for health: World Health Organization 2023. Available from: https://books.google.com/books?hl=zh-CN&lr=&id=YHoOEQAAQBAJ&oi=fnd&pg=PR5&dq=+Regulatory+considerations+on+artificial+intelligence+for+health:+World+Health+Organization+&ots=WpgouRrmWW&sig=GNSP3CzM51dMuoZ-AVVwV6C25jc#v=onepage&q=Regulatory%20considerations%20on%20artificial%20intelligence%20for%20health%3A%20World%20Health%20Organization&f=false. [Last accessed on 19 Dec 2024].

[50] Warraich HJ,Califf RM.FDA perspective on the regulation of artificial intelligence in health care and biomedicine.JAMA2024;Online ahead of print:

[51] Benjamens S,Meskó B.The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database.NPJ Digit Med2020;3:118 PMCID:PMC7486909

[52] U.S. Food and Drug Administration. Good machine learning practice for medical device development: guiding principles. Available from: https://www.fda.gov/medical-devices/software-medical-device-samd/good-machine-learning-practice-medical-device-development-guiding-principles. [Last accessed on 19 Dec 2024].

[53] Vokinger KN,Kesselheim AS.Continual learning in medical devices: FDA’s action plan and beyond.Lancet Digit Health2021;3:e337-8

[54] Mosqueira-Rey E,Alonso-Ríos D.Human-in-the-loop machine learning: a state of the art.Artif Intell Rev2023;56:3005-54

[55] Stefanini B,D'Alessio A.Delivering adjuvant and neoadjuvant treatments in the early stages of hepatocellular carcinoma.Expert Rev Gastroenterol Hepatol2024;18:647-60 PMCID:PMC11601036

[56] Marino IR,Scott VL.Efficacy and safety of basiliximab with a tacrolimus-based regimen in liver transplant recipients.Transplantation2004;78:886-91