The application of artificial intelligence in the diagnosis and treatment of cholangiocarcinoma

doi:10.3969/j.issn.1006-7795.2026.01.024

Abstract

Abstract: Artificial intelligence (AI) has demonstrated significant potential in the diagnosis and treatment of cholangiocarcinoma. Deep learning-based imaging analysis techniques enable automated lesion segmentation, accurate differential diagnosis, and prediction of pathological behaviors such as lymph node metastasis, substantially improving diagnostic efficacy. Endoscopic assistance systems, utilizing convolutional neural networks, facilitate real-time identification of biliary structures and malignant strictures, optimizing procedural workflows. In pathological diagnosis, AI models leverage hyperspectral or conventional white-light pathological scanned images to achieve tumor classification and molecular subtyping, providing critical support for prognostic assessment and targeted therapy. Current challenges primarily include insufficient data standardization and limited model generalizability. Future advancements will require multicenter collaboration and algorithmic optimization to promote clinical translation.

Key words: cholangiocarcinoma, radiomics, differential diagnosis, artificial intelligence, deep learning, precision medicine

CLC Number:

R575

Liang Zheng, Liu Kuiliang, Ning Tingting, Li Peng, Zhang Shutian#, Wei Yongqiu. The application of artificial intelligence in the diagnosis and treatment of cholangiocarcinoma[J]. Journal of Capital Medical University, 2026, 47(1): 190-197.

References

［1］Vithayathil M, Khan S A. Current epidemiology of cholangiocarcinoma in Western countries［J］. J Hepatol, 2022, 77(6): 1690-1698.
［2］Khan S A, Tavolari S, Brandi G. Cholangiocarcinoma: epidemiology and risk factors［J］. Liver Int, 2019, 39(Suppl 1): 19-31.
［3］Louis C, Papoutsoglou P, Coulouarn C. Molecular classification of cholangiocarcinoma［J］. Curr Opin Gastroenterol, 2020, 36(2): 57-62.
［4］Harrison J M, Visser B C. Cholangiocarcinoma［J］. Surg Clin North Am, 2024, 104(6): 1281-1293.
［5］Gul S, Khan M S, Bibi A, et al. Deep learning techniques for liver and liver tumor segmentation: a review［J］. Comput Biol Med, 2022, 147: 105620.
［6］Li S, Tso G K F, He K J. Bottleneck feature supervised U-Net for pixel-wise liver and tumor segmentation［J］. Expert Syst Appl, 2020, 145: 113131.
［7］He F, Zhang G J, Yang H M, et al. Multi-scale attention module U-Net liver tumour segmentation method［J］. J Phys Conf Ser, 2020, 1678: 012107.
［8］Li W K, Jia M N, Yang C, et al. SPA-UNet: a liver tumor segmentation network based on fused multi-scale features［J］. Open Life Sci, 2023, 18(1): 20220685.
［9］Yang C M, Zhou Q, Li M D, et al. MRI-based automatic identification and segmentation of extrahepatic cholangiocarcinoma using deep learning network［J］. BMC Cancer, 2023, 23(1): 1089.
［10］Li C Q, Zheng X, Guo H L, et al. Differentiation between combined hepatocellular carcinoma and hepatocellular carcinoma: comparison of diagnostic performance between ultrasomics-based model and CEUS LI-RADS v2017［J］. BMC Med Imaging, 2022, 22(1): 36.
［11］Kim T K, Noh S Y, Wilson S R, et al. Contrast-enhanced ultrasound (CEUS) liver imaging reporting and data system (LI-RADS) 2017-a review of important differences compared to the CT/MRI system［J］. Clin Mol Hepatol, 2017, 23(4): 280-289.
［12］Xu X L, Mao Y F, Tang Y Q, et al. Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on radiomic analysis［J］. Comput Math Methods Med, 2022, 2022: 5334095.
［13］Mahmoudi S, Bernatz S, Ackermann J, et al. Computed tomography radiomics to differentiate intrahepatic cholangiocarcinoma and hepatocellular carcinoma［J］. Clin Oncol, 2023, 35(5): e312-e318.
［14］Huang J L, Sun Y, Wu Z H, et al. Differential diagnosis of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on spatial and channel attention mechanisms［J］. J Cancer Res Clin Oncol, 2023, 149(12): 10161-10168.
［15］Xu H Y, Zou X H, Zhao Y N, et al. Differentiation of intrahepatic cholangiocarcinoma and hepatic lymphoma based on radiomics and machine learning in contrast-enhanced computer tomography［J］. Technol Cancer Res Treat, 2021, 20: 15330338211039125.
［16］Midya A, Chakraborty J, Srouji R, et al. Computerized diagnosis of liver tumors from CT scans using a deep neural network approach［J］. IEEE J Biomed Health Inform, 2023, 27(5): 2456-2464.
［17］Wei Y, Yang M Y, Zhang M, et al. Focal liver lesion diagnosis with deep learning and multistage CT imaging［J］. Nat Commun, 2024, 15(1): 7040.
［18］Huang F, Liu X Y, Liu P, et al. The application value of MRI T2^∗WI radiomics nomogram in discriminating hepatocellular carcinoma from intrahepatic cholangiocarcinoma［J］. Comput Math Methods Med, 2022, 2022: 7099476.
［19］Wang X H, Wang S P, Yin X P, et al. MRI-based radiomics distinguish different pathological types of hepatocellular carcinoma［J］. Comput Biol Med, 2022, 141: 105058.
［20］Wang S P, Wang X H, Yin X P, et al. Differentiating HCC from ICC and prediction of ICC grade based on MRI deep-radiomics: using lesions and their extended regions［J］. Phys Med, 2024, 120: 103322.
［21］Liu X Y, Khalvati F, Namdar K, et al. Can machine learning radiomics provide pre-operative differentiation of combined hepatocellular cholangiocarcinoma from hepatocellular carcinoma and cholangiocarcinoma to inform optimal treatment planning?［J］. Eur Radiol, 2021, 31(1): 244-255.
［22］Hu R, Li H Z, Horng H, et al. Automated machine learning for differentiation of hepatocellular carcinoma from intrahepatic cholangiocarcinoma on multiphasic MRI［J］. Sci Rep, 2022, 12(1): 7924.
［23］Chen X, Chen Y, Chen H B, et al. Machine learning based on gadoxetic acid-enhanced MRI for differentiating atypical intrahepatic mass-forming cholangiocarcinoma from poorly differentiated hepatocellular carcinoma［J］. Abdom Radiol, 2023, 48(8): 2525-2536.
［24］Wang H J, Wang S, Zhou L H. Machine learning-based MRI LAVA dynamic enhanced scanning for the diagnosis of hilar lesions［J］. Comput Math Methods Med, 2022, 2022: 9592970.
［25］Bi L, Yang L, Ma J, et al. Dynamic contract-enhanced CT-based radiomics for differentiation of pancreatobiliary-type and intestinal-type periampullary carcinomas［J］. Clin Radiol, 2022, 77(1): e75-e83.
［26］Zhang S T, Huang S Y, He W, et al. Radiomics-based preoperative prediction of lymph node metastasis in intrahepatic cholangiocarcinoma using contrast-enhanced computed tomography［J］. Ann Surg Oncol, 2022, 29(11): 6786-6799.
［27］Ji G W, Zhu F P, Zhang Y D, et al. A radiomics approach to predict lymph node metastasis and clinical outcome of intrahepatic cholangiocarcinoma［J］. Eur Radiol, 2019, 29(7): 3725-3735.
［28］Pan Y J, Wu S J, Zeng Y, et al. Intra-and peri-tumoral radiomics based on dynamic contrast enhanced-MRI to identify lymph node metastasis and prognosis in intrahepatic cholangiocarcinoma［J］. J Magn Reson Imaging, 2024, 60(6): 2669-2680.
［29］Xu L, Yang P F, Liang W J, et al. A radiomics approach based on support vector machine using MR images for preoperative lymph node status evaluation in intrahepatic cholangiocarcinoma［J］. Theranostics, 2019, 9(18): 5374-5385.
［30］Yang C M, Huang M P, Li S P, et al. Radiomics model of magnetic resonance imaging for predicting pathological grading and lymph node metastases of extrahepatic cholangiocarcinoma［J］. Cancer Lett, 2020, 470: 1-7.
［31］王小勇,曾艳艳,李运兴,等. MRI影像组学预测肝外胆管癌腹部淋巴结转移价值研究［J］.四川医学, 2023, 44(9): 947-952.
［32］Zhan P C, Yang T, Zhang Y, et al. Radiomics using CT images for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma: a multi-centric study［J］. Eur Radiol, 2024, 34(2): 1280-1291.
［33］Ma X J, Qian X L, Wang Q, et al. Radiomics nomogram based on optimal VOI of multi-sequence MRI for predicting microvascular invasion in intrahepatic cholangiocarcinoma［J］. Radiol Med, 2023, 128(11): 1296-1309.
［34］Zhou Y, Zhou G F, Zhang J L, et al. Radiomics signature on dynamic contrast-enhanced MR images: a potential imaging biomarker for prediction of microvascular invasion in mass-forming intrahepatic cholangiocarcinoma［J］. Eur Radiol, 2021, 31(9): 6846-6855.
［35］Gao W Y, Wang W T, Song D J, et al. A multiparametric fusion deep learning model based on DCE-MRI for preoperative prediction of microvascular invasion in intrahepatic cholangiocarcinoma［J］. J Magn Reson Imaging, 2022, 56(4): 1029-1039.
［36］Fiz F, Masci C, Costa G, et al. PET/CT-based radiomics of mass-forming intrahepatic cholangiocarcinoma improves prediction of pathology data and survival［J］. Eur J Nucl Med Mol Imaging, 2022, 49(10): 3387-3400.
［37］Peng Y T, Zhou C Y, Lin P, et al. Preoperative ultrasound radiomics signatures for noninvasive evaluation of biological characteristics of intrahepatic cholangiocarcinoma［J］. Acad Radiol, 2020, 27(6): 785-797.
［38］Liu Z W, Luo C, Chen X J, et al. Noninvasive prediction of perineural invasion in intrahepatic cholangiocarcinoma by clinicoradiological features and computed tomography radiomics based on interpretable machine learning: a multicenter cohort study［J］. Int J Surg, 2024, 110(2): 1039-1051.
［39］谢朝邦,汤子建,吴洋,等. 基于增强CT影像组学对肝内胆管细胞癌病理分化程度的预测研究［J］.临床放射学杂志, 2025, 44(5): 882-887.
［40］Tang Y, Yang C M, Su S, et al. Machine learning-based Radiomics analysis for differentiation degree and lymphatic node metastasis of extrahepatic cholangiocarcinoma［J］. BMC Cancer, 2021, 21(1): 1268.
［41］Song Y D, Zhou G Y, Zhou Y C, et al. Artificial intelligence CT radiomics to predict early recurrence of intrahepatic cholangiocarcinoma: a multicenter study［J］. Hepatol Int, 2023, 17(4): 1016-1027.
［42］Chen B, Mao Y C, Li J C, et al. Predicting very early recurrence in intrahepatic cholangiocarcinoma after curative hepatectomy using machine learning radiomics based on CECT: a multi-institutional study［J］. Comput Biol Med, 2023, 167: 107612.
［43］Bo Z Y, Chen B, Yang Y, et al. Machine learning radiomics to predict the early recurrence of intrahepatic cholangiocarcinoma after curative resection: a multicentre cohort study［J］. Eur J Nucl Med Mol Imaging, 2023, 50(8): 2501-2513.
［44］Park H J, Park B, Park S Y, et al. Preoperative prediction of postsurgical outcomes in mass-forming intrahepatic cholangiocarcinoma based on clinical, radiologic, and radiomics features［J］. Eur Radiol, 2021, 31(11): 8638-8648.
［45］Yao L W, Zhang J, Liu J, et al. A deep learning-based system for bile duct annotation and station recognition in linear endoscopic ultrasound［J］. EBioMedicine, 2021, 65: 103238.
［46］Saraiva M M, Ribeiro T, Ferreira J P S, et al. Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study［J］. Gastrointest Endosc, 2022, 95(2): 339-348.
［47］Robles-Medranda C, Baquerizo-Burgos J, Alcivar-Vasquez J, et al. Artificial intelligence for diagnosing neoplasia on digital cholangioscopy: development and multicenter validation of a convolutional neural network model［J］. Endoscopy, 2023, 55(8): 719-727.
［48］Marya N B, Powers P D, Petersen B T, et al. Identification of patients with malignant biliary strictures using a cholangioscopy-based deep learning artificial intelligence (with video)［J］. Gastrointest Endosc, 2023, 97(2): 268-278, e1.
［49］Sun L, Zhou M, Li Q L, et al. Diagnosis of cholangiocarcinoma from microscopic hyperspectral pathological dataset by deep convolution neural networks［J］. Methods, 2022, 202: 22-30.
［50］Chakrabarti S, Rao U S. Lightweight neural network for smart diagnosis of cholangiocarcinoma using histopathological images［J］. Sci Rep, 2023, 13(1): 18854.
［51］Jang H J, Go J H, Kim Y, et al. Deep learning for the pathologic diagnosis of hepatocellular carcinoma, cholangiocarcinoma, and metastatic colorectal cancer［J］. Cancers, 2023, 15(22): 5389.

［52］Calderaro J, Ghaffari Laleh N, Zeng Q H, et al. Deep learning-based phenotyping reclassifies combined hepatocellular-cholangiocarcinoma［J］. Nat Commun, 2023, 14(1): 8290.

［53］Ochi M, Komura D, Ishikawa S. Pathology foundation models［J］. JMA J, 2025, 8(1): 121-130.

［54］Chen R J, Ding T, Lu M Y, et al. Towards a general-purpose foundation model for computational pathology［J］. Nat Med, 2024, 30(3): 850-862.
［55］Vorontsov E, Bozkurt A, Casson A, et al. A foundation model for clinical-grade computational pathology and rare cancers detection［J］. Nat Med, 2024, 30(10): 2924-2935.
［56］Wang X Y, Yang S, Zhang J, et al. Transformer-based unsupervised contrastive learning for histopathological image classification［J］. Med Image Anal, 2022, 81: 102559.

[1]	Liu Yanyi, Zhang Yanyan, Li Hongjun. Research advances in radiomics combined with multi-omics in hepatocellular carcinoma [J]. Journal of Capital Medical University, 2025, 46(5): 934-939.
[2]	Liu Honglei, Yang Yingliang, Li Ronghao, Zhu Congmin, Zhang Xu. Application of artificial intelligence in the study of cancer diagnosis and treatment research [J]. Journal of Capital Medical University, 2025, 46(3): 395-400.
[3]	Wang Yongjun, Liu Tao, Liu Ziyang, Xiong Yunyun, Jing Jing, Xie Xuewei, Li Zixiao. The applications of artificial intelligence in the field of cerebrovascular diseases [J]. Journal of Capital Medical University, 2025, 46(2): 177-183.
[4]	Qu Junda, Yang Minfu, Li Chunlin, Sun Liwei, Gao He, Zhang Xu. Research progress on imaging segmentation and quantification methods for epicardial adipose tissue and its clinical applications [J]. Journal of Capital Medical University, 2025, 46(1): 99-105.
[5]	Luo Yi, Qin Qi, Wang Peihao, Guo Kangshun, Zhang Xinping, Cui Yong. Application and research progress of artificial intelligence combined with spectral diagnosis technology in the identification of lung cancer tissues [J]. Journal of Capital Medical University, 2023, 44(6): 1095-1102.