Artificial intelligence and cholangiocarcinoma: Updates and prospects

Table 1 Advantages and disadvantages of artificial intelligence models used for cholangiocarcinoma diagnosis in radiology

AI technology	Imaging modalities used in	Advantages	Disadvantages
Logistic regression	US/CT	Interpretable	Low precision
Support-vector machine	US/CT/MRI	Avoids overlearning and dimension disaster problems	Prone to missing data
Extreme learning machine	CT	Does not need high amount of data for training	Slow processing speed
Artificial neural network	CT/MRI	High generalization power	Needs long training time
Convolutional neural network	US/CT/MRI	Higher efficacy and speed as there is no need to compute features as first step	Needs large training data

AI: Artificial intelligence; CT: Computed tomography; MRI: Magnetic resonance imaging; US: Ultrasound.

Table 2 Studies utilizing artificial intelligence in the diagnosis of cholangiocarcinoma

Ref.	Year of publication	Title of study	Diagnostic modality	AI model
Chu et al[44]	2021	Radiomics using CT images for preoperative prediction of futile resection in intrahepatic cholangiocarcinoma	CT	LR
Ibragimov et al[45]	2020	Deep learning for identification of critical regions associated with toxicities after liver stereotactic body radiation therapy	CT	CNN
Liu et al[46]	2021	Can machine learning radiomics provide pre-operative differentiation of combined hepatocellular cholangiocarcinoma from hepatocellular carcinoma and cholangiocarcinoma to inform optimal treatment planning?	MRI, CT	SVM
Logeswaran[35]	2009	Cholangiocarcinoma--an automated preliminary detection system using MLP	MRCP	ANN
Midya et al[47]	2018	Deep convolutional neural network for the classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma	CT	CNN
Nakai et al[29]	2021	Convolutional neural network for classifying primary liver cancer based on triple-phase CT and tumor marker information: a pilot study	CT, tumor markers	CNN
Negrini et al[22]	2020	Machine Learning Model Comparison in the Screening of Cholangiocarcinoma Using Plasma Bile Acids Profiles	Serum bile acids	ML
Pattanapairoj et al[23]	2015	Improve discrimination power of serum markers for diagnosis of cholangiocarcinoma using data mining-based approach	Tumor markers	ANN
Peng et al[48]	2020	Preoperative Ultrasound Radiomics Signatures for Noninvasive Evaluation of Biological Characteristics of Intrahepatic Cholangiocarcinoma	US	SVM
Peng et al[49]	2020	Ultrasound-Based Radiomics Analysis for Preoperatively Predicting Different Histopathological Subtypes of Primary Liver Cancer	US	Radiomics
Ponnoprat et al[31]	2020	Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans	CT	CNN
Selvathi et al[50]	2013	Automatic segmentation and classification of liver tumor in CT images using adaptive hybrid technique and Contourlet based ELM classifier	CT	ELM
Sun et al[25]	2021	Diagnosis of cholangiocarcinoma from microscopic hyperspectral pathological dataset by deep convolution neural networks	Histology	CNN
Urman et al[24]	2020	Pilot Multi-Omic Analysis of Human Bile from Benign and Malignant Biliary Strictures: A Machine-Learning Approach	Bile acids, lipids	ANN
Uyumazturk et al[26]	2019	Deep learning for the digital pathologic diagnosis of cholangiocarcinoma and hepatocellular carcinoma: evaluating the impact of a web-based diagnostic assistant	Histology	DL
Wang et al[51]	2020	SCCNN: A Diagnosis Method for Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma Based on Siamese Cross Contrast Neural Network	CT	ANN
Wang et al[52]	2019	Deep learning for liver tumor diagnosis part II: convolutional neural network interpretation using radiologic imaging features	MRI	DL
Xu et al[33]	2019	A radiomics approach based on support vector machine using MR images for preoperative lymph node status evaluation in intrahepatic cholangiocarcinoma	MRI	SVM
Xu et al[30]	2021	Differentiation of Intrahepatic Cholangiocarcinoma and Hepatic Lymphoma Based on Radiomics and Machine Learning in Contrast-Enhanced Computer Tomography	Contrast enhanced CT	ML
Yang et al[36]	2020	Radiomics model of magnetic resonance imaging for predicting pathological grading and lymph node metastases of extrahepatic cholangiocarcinoma	MRI	Radiomics
Yao et al[34]	2020	A Novel Approach to Assessing Differentiation Degree and Lymph Node Metastasis of Extrahepatic Cholangiocarcinoma: Prediction Using a Radiomics-Based Particle Swarm Optimization and Support Vector Machine Model	MRI	SVM
Yasaka et al[53]	2018	Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study	CT	CNN
Zhang et al[32]	2020	Differentiation combined hepatocellular and cholangiocarcinoma from intrahepatic cholangiocarcinoma based on radiomics machine learning	CT	Radiomics
Zhao et al[28]	2020	CUP-AI-Dx: A tool for inferring cancer tissue of origin and molecular subtype using RNA gene-expression data and artificial intelligence	Tissue biopsy	CNN
Zhou et al[54]	2021	Automatic Detection and Classification of Focal Liver Lesions Based on Deep Convolutional Neural Networks: A Preliminary Study	Multiphasic CT	CNN

AI: Artificial intelligence; ANN: Artificial Neural Network; CCA: Cholangiocarcinoma; CNN: Convolutional neural network; CT: Computed tomography; DL: deep learning; ML: machine learning; ELM: Extreme learning machine; LR: Logistic regression; MRCP: Magnetic resonance cholangiopancreatography; MRI: Magnetic resonance imaging; SVM: Support-vector machine, US: Ultrasound.

Table 3 Studies utilizing artificial intelligence in the treatment and prognostication of cholangiocarcinoma

Ref.	Year of publication	Title of study	AI variables	AI model
Jeong et al[39]	2020	Latent Risk Intrahepatic Cholangiocarcinoma Susceptible to Adjuvant Treatment After Resection: A Clinical Deep Learning Approach	CT, albumin, platelets, Diabetes, CA 19-9	ML
Ji et al[55]	2019	Biliary Tract Cancer at CT: A Radiomics-based Model to Predict Lymph Node Metastasis and Survival Outcomes	CT reported LN features	ANN
Li et al[41]	2020	A Novel Prognostic Scoring System of Intrahepatic Cholangiocarcinoma With Machine Learning Basing on Real-World Data	CEA, CA 19-9, tumor stage	ML
Muller et al[42]	2021	Survival Prediction in Intrahepatic Cholangiocarcinoma: A Proof-of-Concept Study Using Artificial Intelligence for Risk Assessment	Tumor size, tumor boundary, serology	ANN
Shao et al[43]	2018	Artificial Neural Networking Model for the Prediction of Early Occlusion of Bilateral Plastic Stent Placement for Inoperable Hilar Cholangiocarcinoma	Tumor size, nodal involvement	ANN
Tang et al[40]	2021	The preoperative prognostic value of the radiomics nomogram based on CT combined with machine learning in patients with intrahepatic cholangiocarcinoma	Tumor size, cirrhosis in CT	Radiomics
Tsilimigras et al[37]	2020	A Novel Classification of Intrahepatic Cholangiocarcinoma Phenotypes Using Machine Learning Techniques: An International Multi-Institutional Analysis	Tumor size, nodal involvement, serology	ML

AI: Artificial intelligence; ANN: Artificial Neural Network; CA 19-9: Carbohydrate antigen 19-9; CCA: Cholangiocarcinoma; CEA: Carcinoembryonic antigen; CT: Computed tomography; ML: Machine learning.