Role of three-dimensional printing and artificial intelligence in the management of hepatocellular carcinoma: Challenges and opportunities

doi:10.4251/wjgo.v14.i4.765

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 14, Issue 4

This Article

Academic Content and Language Evaluation of This Article

Academic Rules and Norms of This Article

Citation of this article

Corresponding Author of This Article

Research Domain of This Article

Article-Type of This Article

Open-Access Policy of This Article

Times Cited Counts in Google of This Article

Number of Hits and Downloads for This Article

Total Article Views (4357)

All Articles published online

The chart showing PDF series, WORD series, HTML series, Tables (1-4) series.

Item

Count

PDF

255

WORD

HTML

2493

Tables (1-4)

128

Sum=2956

Featured Article

The chart showing Browse series, Download series.

Item

Count

Browse

272

Download

296

Sum=568

Publishing Process of This Article

Item

Count

Browse

326

Download

507

Sum=833

Apr 15, 2022 (publication date) through Apr 27, 2024

Times Cited of This Article

Times Cited (6)

Journal Information of This Article

Publication Name

World Journal of Gastrointestinal Oncology

ISSN

1948-5204

Publisher of This Article

Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA

Review

World J Gastrointest Oncol. Apr 15, 2022; 14(4): 765-793
Published online Apr 15, 2022. doi: 10.4251/wjgo.v14.i4.765

Table 1 Artificial intelligence applications in the prevention of hepatocellular carcinoma

	First author	Parameters employed	AI classifier	Sizes of the training/validation sets	Outcomes	Performance	Ref.
1	Wang J	Genetic and epigenetic biomarkers	Several	137 HCC and 431 non-HCC patients	HCC screening	0.910-0.950¹^,², 0.897-0.938¹^,³, 75.0-91.5²^,⁴, 66.4-90.6³^,⁴, 1.0-88.8²^,⁵, 0.5-87.9³^,⁵	[47]
2	Nam JY	Laboratory results, clinicopathological parameters	DNN	424/316³patients	HCC development in HBV cirrhosis	0.719¹^,², 0.782¹^,³	[48]
3	Xia Q	Long non-coding RNAs	Several	38 healthy samples, 45 chronic HBV patients, 46 liver cirrhosis, and 46 HCC patients	HCC development in HBV cirrhosis	71.1-89.5³^,⁶	[49]
4	Chen S	HBV reverse transcriptase gene sequencing	RF, SVM, KNN	307 chronic HBV patients (202/105), 237 HCC patients (159/78)	HCC development in HBV cirrhosis	RF: 0.902-0.903¹^,², 0.903-0.943¹^,³, SVM: 0.879-0.924¹^,², 0.727-0.858¹^,³, KNN: 0.680-0.737¹^,², 0.734-0.747¹^,³	[50]
5	Hashem S	Laboratory results, clinicopathological parameters	Several	3099 chronic HCV patients1324 HCC patients	HCC development in HCV cirrhosis	93.2-95.6³^,⁶, 0.955-0.990¹^,³, 86.3-91.8³^,⁴, 93.9-97.3³^,⁵	[51]
6	Audureau E	Laboratory results, clinicopathological parameters	Several	836/668⁷	HCC development in HCV cirrhosis	0.633-0.807¹^,², 0.623-0.715¹^,⁷	[52]
7	Ioannou GN	Clinical/laboratory data extracted directly from electronic health records	DNN	48151 patients with HCV-related cirrhosis (training:test = 9:1)	HCC development in HCV cirrhosis	0.759-0.806¹^,³	[53]
8	Singal AG	Laboratory results, clinicopathological parameters	RF	442/1050⁷	HCC development in cirrhosis	0.71¹^,², 0.64¹^,⁷	[54]

¹Area under the receiver operating curve or c-index.

²Training.

³Internal validation.

⁴Sensitivity (%).

⁵Specificity (%).

⁶Accuracy (%).

⁷External validation/testing.

CCA: Cholangiocarcinoma; CNN: Convolutional neural network; CT: Computed tomography; DNN: Deep neural network; HBV: Hepatitis B virus; HCC: Hepatocellular carcinoma; HCV: Hepatitis C virus; KNN: K-nearest neighbor; RF: Random forest; SVM: Support vector machine; WSI: Whole-slide image.

Table 2 Artificial intelligence application in hepatocellular carcinoma diagnosis

	First author	Diagnostic modality	AI classifier	Sizes of the training/validation sets	Outcomes	Performance	Ref.
1	Sato M	Laboratory results, clinicopathological parameters	Several	1582 patients	HCC early detection	81.65-87.36¹^,², 0.870-0.940³^,²	[55]
2	Zhao X	MicroRNA expression profiles	Several	392 patients	HCC early detection	RF: 0.982³, SVM: 0.970³, DT: 0.831³	[56]
3	Zhang ZM	Gene expression profiles	SVM	1333/336 HCC samples	HCC early detection	100¹^,², 100²^,⁴, 100²^,⁵, 0.9597³^,⁶, 91.93⁴^,⁶, 100⁵^,⁶	[57]
4	Tao K	Circulating tumor DNA	RF-based	209/76⁶/99⁶	HCC early detection	0.874-0.933¹^,², 0.812-0.920³^,⁶	[58]
5	Li G	MicroRNA and long non-coding RNA expression profiles	SVM, RF, DT	361 patients	HCC early detection	RF: 0.992¹^,², 95.6²^,⁴, 100²^,⁵; SVM: 0.992²^,³, 97.2²^,⁴, 98.0²^,⁵; DT: 0.927²^,³, 98.3²^,⁴, 92.0²^,⁵	[59]
6	Schmauch B	US imaging	CNN	109 images with focal liver lesions	Classification of benign from malignant focal liver lesions; classification among five focal liver lesions	0.916-0.942²^,³; 0.886-0.954²^,³	[60]
7	Yang Q	US imaging, clinical parameters	CNN	16500/4125²/3718⁶US images	Classification among 16 different focal liver lesions	0.859-0.966³^,⁷, 0.765-0.925²^,³, 0.750-0.924³^,⁶	[61]
8	Virmani J	B-mode US imaging	NNE	108 images	Classification among normal liver and four focal liver lesions	95.0¹^,²	[62]
9	Shiraishi J	Microflow imaging of contrast-enhanced US	ANN	103 focal liver lesions	Classification among HCC, metastasis, and hemangioma; histopathological grade	86.9-93.8¹^,²; 50.0-79.2¹^,²	[63]
10	Zhou J	Multiphasic CT scans	CNN	616 liver lesions	Classification of benign and malignant lesions. Classification of 6 types of focal liver lesions	76.6-88.4²^,⁴^,⁵, 82.5¹^,², 0.921²^,³, 46.4-93.1²^,⁴, 91.9-98.6²^,⁵, 73.4¹^,², 0.766-0.983²^,³	[64]
11	Yasaka K	Contrast-enhancedCT imaging	CNN	460/100⁶patients	Classification among five types of focal liver lesions	95¹^,⁷, 84¹^,⁶, 33-100⁴^,⁶	[65]
12	Shi W	Multiphasic CT scans	MP-CDN	449 focal lesions. Training:validation ratio = 8:2	Classification between HCC and non-HCC focal lesions	0.811-0.856¹^,², 0.862-0.925²^,³, 0.744-0.923²^,⁴, 0.725-0.941²^,⁵	[66]
13	Todoroki Y	Multiphasic CT imaging	CNN	89 patients	Classification among five focal liver lesions	79-100²^,⁴	[67]
14	Matake K	Clinicopathological parameters, CT imaging	ANN	120 patients	Classification among four types of focal liver lesions	0.961²^,³	[68]
15	Liang W	CT and MRI radiomics	RF	170 CT scans; 137 MRI scans	Classification of three types of focal liver lesions	CT model: 0.996³^,⁷, 0.879²^,³. MRI model: 0.999³^,⁷, 0.925²^,³	[69]
16	Hamm CA	Multiphasic MRI imaging	CNN	434/60 lesions	Classification among six types of focal liver lesions; identify HCC; classification of LI-RADS	92²^,⁴, 98²^,⁵; 0.992²^,³; 94⁴^,⁶, 97²^,⁵	[70,71]
17	Jansen MJA	MRI imaging	Extremely randomized trees classifier	95 patients	Classification among five different focal liver lesions	85-92¹^,², 62-93²^,⁴, 56-93²^,⁵	[72]
18	Zhen SH	MRI scans	CNN	1210/201⁶	Classification among seven different focal liver lesions	0.841-0.987³^,⁶, 40.5-100⁴^,⁶, 86.4-99.5⁵^,⁶	[73]
19	Kiani A	Hematoxylin and eosin-stained WSI	CNN	20⁷/26²/80⁶WSIs	Classification of HCC and CCA	88.5¹^,², 84.2¹^,⁶	[74]
20	Chen M	Hematoxylin and eosin-stained WSI	CNN	491 WSIs (402 HCC, 89 normal liver tissue)	Classification of HCC and normal liver tissue; histopathological grade	0.960¹^,², 0.961²^,³; 89.6¹^,²	[75]
21	Lin H	Multiphoton microscopy	CNN	217 images	Histopathological grade	0.812-0.941¹^,², 0.891-0.917²^,³	[76]
22	Yamashita R	Hematoxylin and eosin-stained WSI	CNN	28/4²/30⁶WSIs	HCC lesion detection	0.952²^,³, 0.956³^,⁶	[77]
23	Roy M	Hematoxylin and eosin-stained WSI	CAE	50 WSIs	Segmentation of viable tumors	91-95¹^,²	[78]
24	Giordano S	PESI-MS	SVM, RF	117 HCCs, 50 CCA, 151 non-tumor group	Classification of HCC, CCA, and non-tumor groups	SVM: 95.1-98.5¹^,⁶; RF: 94-94.9¹^,⁶	[79]
25	Guo LH	Contrast-enhanced ultrasound imaging	MKL	93 lesions	Classification of benign from malignant focal liver lesions	90.41¹^,², 93.56²^,⁴, 86.89²^,⁵	[80]
26	Bharti P	US imaging	Several	189 images	Classify among normal liver, chronic liver disease, cirrhosis, and HCC	96.6¹^,², 95.5-96.9²^,⁴, 98.0-99.8²^,⁵	[81]
27	Brehar R	US imaging	CNN	268 patients	Classification between HCC and cirrhotic parenchyma	84.84-91¹^,², 0.91-0.95²^,³, 86.79-94.37²^,⁴, 82.95%-88.38%²^,⁵	[82]
28	Mao B	Ultrasound radiomics	Several	114 patients	Classify primary from metastatic liver cancer	0.729-0.808¹^,², 0.737-0.793²^,³, 0.775-0.868²^,⁴, 0.667-0.880²^,⁵	[83]
29	Almotairi S	CT imaging	CNN	20 CT scans	Tumor segmentation	98.8¹^,⁷	[84]
30	Budak Ü	CT imaging	CNN	20 CT scans	Tumor segmentation	Volumetric overlap error: 9.05%²	[85]
31	Nayak A	Multiphasic CT imaging	SVM	40 patients	Classification between HCC and cirrhotic parenchyma	80-86.9¹^,², 0.93²^,³	[86]
32	Krishan A	CT scans	Several	1638 CT scans	Identification of liver lesions; classification between HCC and metastasis	98.39-100¹^,², 0.99-1.00²^,³; 76.38-87.01¹^,², 0.77-0.99²^,³	[87]
33	Chen WF	CT scans	SED	300 CT scans	Tumor segmentation	0.992¹, 0.95²^,³	[88]
34	Khan AA	CT scans	Several	179 patients	Classification between HCC and hemangioma	96.6-98.3¹^,⁶, 0.94-0.97³^,⁶, 94.23-97.03⁵^,⁶	[88]
35	Mokrane FZ	Multiphasic CT radiomics	Several	106/36²/36⁶	Classification between HCC and non-HCC lesions	0.81³^,⁷, 0.81⁴^,⁷, 0.72⁵^,⁷, 0.72²^,³, 0.66³^,⁶	[90]
36	Mao B	CT radiomics, clinical parameters	Gradient boosting	237/60⁶patients	Histopathological grade	61.18-97.05¹^,⁶, 0.7071-0.9964³^,⁷, 60.67-95.51⁴^,⁷, 51.35-80.41⁵^,⁷, 48.33-70.00¹^,⁶, 0.6128-0.8014³^,⁶, 43.48-65.22⁴^,⁶, 37.84-81.08⁵^,⁶	[91]
37	Preis O	PET/CT imaging	ANN	98 patients	Classification between benign and malignant liver lesions	0.896-0.905²^,³	[92]
38	Trivizakis E	Diffusion-weighted MRI	CNN, SVM	134 patients	Classification between primary liver cancer and metastasis	85.5¹^,⁷, 83¹^,², 0.80²^,³, 93²^,⁴, 67²^,⁵	[93]
39	Oestmann PM	Multiphasic MRI scans	CNN	150/10²	Classification of HCC and non-HCC lesions	94.1¹^,⁷, 87.3¹^,², 0.912²^,³. For HCC: 92.7²^,⁴, 82.0²^,⁵. For non-HCC: 82.0²^,⁴, 92.7²^,⁵	[94]
40	Bousabarah K	MRI scans	CNN, RF	174 patients/ 231 lesions	HCC detection	0.66-0.75²^,⁴, 0.55-0.73⁴^,⁶	[95]
41	Kim J	MRI scans	CNN	455²^,⁷/54⁶	HCC detection	0.97²^,³, 94²^,⁴, 99²^,⁵, 0.90³^,⁶, 87⁴^,⁶, 93⁵^,⁶	[96]
42	Jian W	Non-enhanced MRI scans	CNN	75/40⁶HCCs	HCC detection	65.00-77.00¹^,⁶, 0.70-0.82³^,⁶, 64.55-78.18⁴^,⁶, 65.56-75.56⁵^,⁶	[97]
43	Wu Y	Multiphasic MRI imaging	CNN	89 HCCs	Classification between LI-RADS 3 and LI-RADS 4/5	0.767-0.900¹^,⁶, 0.90-0.95³^,⁶, 0.76-1.00⁴^,⁶, 0.633-0.807⁵^,⁶	[98]

¹Accuracy (%).

²Internal validation.

³Area under the receiver operating curve or c-index.

⁴Sensitivity (%).

⁵Specificity (%).

⁶External validation/testing.

⁷Training.

ANN: Artificial neural network; CAE: Convolutional autoencoder; CCA: Cholangiocarcinoma; CNN: Convolutional neural network; CT: Computed tomography; DNN: Deep neural network; DT: Decision tree; HCC: Hepatocellular carcinoma; LI-RADS: Liver imaging reporting and data system; MKL: Multiple kernel learning; MP-CDN: Multiphase convolutional dense networks; MRI: Magnetic resonance imaging; NGS: Next-generation sequencing; NNE: Neural network ensemble; PESI-MS: Probe electrospray ionization mass spectrometry; PET: Positron emission tomography; RF: Random forest; SED: Successive Encoder-Decoder; SVM: Support vector machine; US: Ultrasound; WSI: Whole-slide image.

Table 3 Artificial intelligence application in hepatocellular carcinoma treatment

	First author	Parameters employed	AI classifier	Sizes of the training/validation sets	Outcomes	Performance	Ref.
1	Tsilimigras DI	Laboratory results, clinicopathological parameters, tumor characteristics	CART	976	Determining factors of prognostic weight preoperatively within the BCLC staging system	-	[99]
2	Liu F	Contrast-enhanced US radiomics, laboratory tests, and clinicopathological parameters	CNN	293/126 patients	2-yr progression-free survival of patients following RFA or surgical resection	0.754-0.784¹^,², 0.726-0.741¹^,³	[100]
3	Choi GH	Demographics, laboratory results, tumor characteristics, clinicopathological parameters	RF	813/208 patients	Treatment recommendation. Survival prediction	76.6-88.4³^,⁴, 53.0-82.3³^,⁵, 69.3-95.8³^,⁶. 0.676-0.959¹^,³	[101]
4	Chen M	Hematoxylin and eosin-stained WSI	CNN	377 (training:validation = 3:1)/ 67⁷ patients	Mutation prediction	89.6-94.0³^,⁴, 0.720-0.805¹^,⁷	[75]
5	Liao H	Hematoxylin and eosin-stained WSI	CNN	309/65³/78⁷	Mutation prediction	0.519-0.903¹^,³, 0.605-0.797¹^,⁷	[103]
6	Gu J	Multiphasic CT scans	CNN	14 patients	Mutation prediction	67.7-77.3³^,⁴	[104]
7	Chen G	Laboratory results	LIME	1007/1085⁷ patients	MVI	0.918¹^,², 0.832¹^,³, 0.905¹^,⁷	[105]
8	Zhang Y	MRI scans	CNN	158/79 patients	MVI	0.81¹^,², 69²^,⁵, 79²^,⁶, 0.72¹^,³, 55³^,⁵, 81³^,⁶	[106]
9	Wang G	DWI	CNN	60/40² HCCs	MVI	66.81-77.50²^,³^,⁴, 68.65-79.69¹^,²^,³, 56.56-76.47²^,³^,⁵, 64.35-79.13²^,³^,⁶	[107]
10	Liu QP	CT radiomics	RF, SVM	494 patients	MVI	0.84¹^,², 0.79¹^,³	[108]
11	Jiang YQ	CT radiomics, clinical/laboratory parameters	Gradient boosting, CNN	405 patients [220 MVI (+)/185 MVI (-)]	MVI	Gradient boosting: 0.900-0.952¹^,², 0.873-0.887¹^,³. CNN: 80.2-85.2³^,⁴, 0.900-0.980¹^,², 0.875-0.906¹^,³, 0.659-0.932³^,⁵, 0.757-0.973³^,⁶	[109]
12	Cucchetti A	Laboratory results, clinicopathological parameters, radiological data, histological data	ANN	175/75³	MVI. Histopathological grade	0.92¹^,², 91.0³^,⁴. 0.94¹^,², 93.3³^,⁴	[110]
13	Mai RY	Laboratory results, clinicopathological parameters, liver volumetry	ANN	265/88 patients	Posthemihepatectomy liver failure	0.880¹^,², 0.876¹^,³	[111]
14	Shi HY	Laboratory results, clinicopathological parameters, surgery parameters	ANN	22926 hepatectomies	In-hospital mortality following surgical resection	97.28³^,⁴, 0.84¹^,³, 95.93⁴^,⁷, 0.82¹^,⁷, 78.40⁵^,⁷, 94.57⁶^,⁷	[112]
15	Liu D	US radiomics	CNN	89/41 patients	Classify full/partial response from stable disease/ progression in patients treated with TACE	78-98²^,⁴, 0.82-0.98¹^,², 78.6-98.2²^,⁵, 74.2-96.7²^,⁶, 0.80-0.90³^,⁴, 0.80-0.93¹^,³, 82.1-89.3³^,⁵, 73.3-92.3³^,⁶	[113]
16	Morshid A	Multiphasic CT scans, BCLC stage	CNN, RF	105 patients	Classify TACE-susceptible from TACE-refractory HCC	62.9-74.2³^,⁴, 0.733¹^,³	[114]
17	Peng J	CT imaging	CNN	562/89⁷/138⁷	Classification of complete response, partial response, stable disease, and progressive disease following TACE	84.0²^,⁴, 0.95-0.97¹^,², 82.8-85.1⁴^,⁷, 0.94-0.98¹^,⁷	[115]
18	Abajian A	MRI imaging, clinical data	RF	36 patients	Classification of responders and non-responders following TACE	66³^,⁴, 62.5³^,⁵, 67.9³^,⁶	[116]
19	Zhu Y	FF-OCT	SVM	285 en face images	Cancerous hepatic cell identification	0.9378¹^,⁷	[117]
20	Liang Z	X-ray imaging	CNN	2943/1542³/1442⁷ images	Localization of fiducial markers	98.6⁴^,⁷	[118]
21	Liu Y	CT/MRI imaging	Dense-cycle GAN	21 patients	Identify differences between synthetic CT and CT, and compare their dose distribution	-	[119]
22	Taebi A	Computational fluid dynamics	CNN	3804 samples	Yttrium-90 distribution in radioembolization	Mean square error: 0.54 ± 0.14	[120]
23	Tong Z	DNA profiling	SVM	43 patients	Drug target prediction	0.8827-0.8849¹^,³, 53-65.44³^,⁵, 88.76-93.63³^,⁶	[121]

¹Area under the receiver operating curve or c-index.

²Training.

³Internal validation.

⁴Accuracy (%).

⁵Sensitivity (%).

⁶Specificity (%).

⁷External validation/ testing.

ANN: Artificial neural network; BCLC: Barcelona clinic liver cancer; CART: Classification and regression tree; CNN: Convolutional neural network; CT: Computed tomography; DWI: Diffusion-weighted imaging; FF-OCT: Full-field optical coherence tomography; GAN: Generative adversarial network; HCC: Hepatocellular carcinoma; LIME: Local Interpretable Model-agnostic Explanations; MRI: Magnetic resonance imaging; MVI: Microvascular invasion; RF: Random forest; RFA: Radiofrequency ablation; TACE: Transarterial chemoembolization; US: Ultrasound; WSI: Whole-slide image.

Table 4 Artificial intelligence application in hepatocellular carcinoma prognosis

	First author	Parameters employed	AI classifier	Sizes of the training/validation sets	Outcomes	Performance	Ref.
1	Chaudhary K	DNA methylation, RNA, and microRNA profiling	Several	360 patients (training:validation = 6:4)	Overall survival	0.70¹^,², 0.66-0.70¹^,³, 0.67-0.82¹^,⁴	[122]
2	Chicco D	50 laboratory and clinical parameters	Several	165 patients with HCC	Overall survival	RF: 77.2¹, 0.766⁵; Linear SVM: 77.1⁵, 0.763¹; MLP: 72.7⁵, 0.695¹; Radial SVM: 68.0⁵, 0.663¹; DT: 65.9⁵, 0.650¹	[123]
3	Liu X	Laboratory results, data from immunochemistry of peripheral blood mononuclear cells, tumor characteristics	GBA classifier	136/56³/105⁴	Risk of HCC-related death	0.844¹^,², 0.827¹^,³, 0.806¹^,⁴	[124]
4	Shi HY	Laboratory results, clinicopathological parameters, tumor characteristics	ANN	22926 patients	5-yr survival following surgical resection	96.57³^,⁵, 0.885¹^,³, 97.43⁴^,⁵, 0.871¹^,⁴, 74.23⁴^,⁶	[125]
5	Chiu HC	Laboratory results, clinicopathological parameters, tumor characteristics	ANN	434, 341, and 264 patients for 1-, 3-, and 5-year survival(training:validation = 8:2)	1-, 3-, and 5-yr overall survivalfollowing surgical resection	98.5-99.5²^,⁵, 0.980-0.993¹^,², 99.7-100²^,⁶, 96.2-99.2²^,⁷, 72.1-85.1³^,⁵, 0.798-0.875¹^,³, 71.4-88.6³^,⁶, 50.0-82.1³^,⁷	[126]
6	Qiao G	Laboratory results, clinicopathological parameters, tumor characteristics	ANN	362/181³/104⁴ patients	Survival following surgical resection	0.855¹^,², 80.00²^,⁶, 73.40²^,⁷, 0.832¹^,³, 78.67³^,⁶, 75.70³^,⁷, 0.829¹^,⁴, 77.42⁴^,⁶, 78.08⁴^,⁷	[127]
7	Guo L	RNA sequencing	RF	239/130 patients	Overall survival	89³^,⁵	[128]
8	Saillard C	Hematoxylin and eosin-stained WSI	CNN	309/342⁴ WSIs	Survival following surgical resection	0.75-0.78¹^,², 0.68-0.70¹^,⁴	[129]
9	Zhong BY	ALBI/CTP stage	ANN	548/115⁴/175⁴	Survival of patients treated with chemoembolization as monotherapy	ALBI-based: 0.799¹^,⁴, 0.700¹^,⁴; CTP-based: 0.729¹^,⁴, 0.802¹^,⁴	[130]
10	Zhong BY	ALBI/CTP stage	ANN	319/61⁴/124⁴	Survival of patients treated with chemoembolization and sorafenib	ALBI-based: 0.716¹^,⁴, 0.823¹^,⁴; CTP-based: 0.779¹^,⁴, 0.693¹^,⁴	[131]
11	Zhang L	CT scans, clinical features	CNN	120/81³ patients	Survival of patients treated with chemoembolization and sorafenib	0.717¹^,², 0.714¹^,³	[132]
12	Liu QP	CT radiomics, clinical parameters	DNN-DAE	243 patients	Overall survival following TACE	0.87-0.93¹^,³	[108]
13	Mähringer-Kunz A	Routine laboratory tests and clinicopathological parameters	ANN	125/57 patients	1-yr overall survival following TACE	0.77¹^,², 0.83¹^,³, 77.8³^,⁶, 81.0³^,⁷	[133]
14	Liu X	Routine laboratory tests and clinicopathological parameters	ANN	1480/637 patients	Progression-free survival. Overall survival	0.866¹^,², 0.730¹^,³. 0.877¹^,², 0.804¹^,³	[134]
15	Ho WH	Laboratory results, clinicopathological parameters, surgery parameters	ANN, DT	427, 354, and 297 patients for 1-, 3-, and 5-yr survival (training:validation = 8:2)	1-, 3-, and 5-yr disease-free survival following surgical resection	ANN: 0.963-0.989¹^,², 93.5-96.3²^,⁶, 91.6-97.9²^,⁷, 0.774-0.864¹^,³, 70.0-78.7³^,⁶, 54.2-92.7³^,⁷. DT: 0.675-0.825¹^,², 19.6-94.8²^,⁶, 45.8-97.9²^,⁷, 0.561-0.718¹^,³, 0-88.5³^,⁶, 37.5-96.4³^,⁷	[135]
16	Bedon L	DNA methylation profiling	RF-based	300/74 specimens	6-mo progression-free survival	67.1-80.6²^,⁵, 64.8-80.2⁴^,⁵	[136]
17	Schoenberg MB	Routine laboratory tests and clinicopathological parameters	RFS	127/53 patients	Disease-free survival following resection	0.766-0.788¹^,³	[137]
18	Wu CF	Laboratory tests and clinicopathological parameters, treatment data	ANN	252 patients(training:validation = 8:2)	1-yr and 2-yr disease-free survival following RFA	0.72-0.77¹^,³, 56.3-63.6³^,⁶, 70.0-71.8³^,⁷	[138]
19	Divya R	Laboratory results, clinicopathological parameters, tumor characteristics	APO, SVM, RF	152 patients	Recurrence following RFA	95.5³^,⁵, 95.1³^,⁶, 95.8³^,⁷	[139]
20	Huang Y	Demographics, laboratory tests, tumor characteristics	GBS classifier	5928/1483 patients	Recurrence following surgical resection. Overall survival	0.704¹^,², 0.697-0.713¹^,³. 0.565-0.736¹^,², 0.551-0.751¹^,³	[140]
21	Shen J	Disease-free related genes sequencing	DT, SVM	315 HCC patients	Recurrence following surgical resection	DT: 74.19⁵, 0.75¹, 70.41⁴^,⁵. SVM: 80.65⁵, 0.595¹	[141]
22	Wang W	CT radiomics, clinical data	CNN, SVM, RF	167 patients	Early recurrence following surgical resection	0.723-0.825¹^,³	[142]
23	Ji GW	CT radiomics, laboratory results, clinicopathological parameters	Several	210/107³/153⁴ patients	Recurrence time following surgical resection	Radiomics model: 0.748-0.752¹^,², 0.781-0.801¹^,³, 0.733-0.741¹^,⁴. Clinical model: 0.716-0.727¹^,², 0.707-0.739¹^,³, 0.696-0.716¹^,⁴	[143]
24	Xu D	Routine laboratory tests and clinicopathological parameters, intra-operative parameters	BN-based	995 patients	Recurrence time following surgical resection	0.57³^,⁵, 0.57³^,⁶	[144]
25	Jianzhu B	Several including immune, tumor, nutrition, and indicators	CS-SVM	776 liver cancer recurrences	Recurrence time. Recurrence location	Mean square error = 9.2101, 95.7⁵, 0.95¹	[145]
26	Yamashita R	Hematoxylin and eosin-stained WSI	CNN	299/53³/198⁴ WSIs	Recurrence following surgical resection	0.724¹^,³, 0.683¹^,⁴	[77]
27	Liao H	Hematoxylin and eosin-stained WSI	RF	491 WSIs	Overall survival	0.563-0.706¹^,³, 0.565-0.621¹^,⁴	[146]
28	Saito A	Hematoxylin and eosin-stained WSI	SVM	69/89⁴	Recurrence time following surgical resection	99.8²^,⁵, 68.1-80.6⁴^,⁵	[147]
29	Liang JD	Laboratory results, clinicopathological parameters	SVM	83 patients	Recurrence following RFA	73-82³^,⁵, 0.60-0.69¹^,³, 77-86³^,⁶, 73-82³^,⁷	[148]
30	An C	MRI scans	CNN	141 HCC lesions	Local tumor progression following MWA	0.728¹	[149]
31	Nam JY	Routine laboratory tests and clinicopathological parameters	DNN	349/214 patients	Post-transplant HCC recurrence	0.62-0.75¹^,³, 0.63-0.76³^,⁶, 0.46-0.62³^,⁷	[150]
32	Nam JY	Laboratory results, clinicopathological parameters, tumor characteristics	DNN	349/214 transplanted patients	Post-transplant HCC recurrence	0.75¹^,³, 76³^,⁶, 46³^,⁷	[150]
33	Rodriguez-Luna H	Genotyping data from microsatellite mutations/deletions	ANN	19 transplanted patients	Post-transplant HCC recurrence	89.5³^,⁵	[151]
34	Guo D	Laboratory results, clinicopathological parameters CT radiomics	LASSO	93/40 transplanted patients	Recurrence free-survival following liver transplantation	0.675-0.785¹^,², 0.705-0.789¹^,³	[152]
35	Lau L	Laboratory results, clinicopathological parameters, donor characteristics	ANN, RF	90/90 transplants	Graft failure/primary nonfunction. 3-mo graft failure	ANN: 0.734-0.835¹^,³; RF: 0.787-0.818¹^,³. ANN: 0.559¹^,³, RF: 0.715¹^,³	[153]
36	Briceño J	Laboratory results, clinicopathological parameters, surgical parameters, donor characteristics	ANN	1003 liver transplants	3-mo graft failure	0.806-0.821¹^,³	[154]
37	Ershoff BD	Laboratory results, clinicopathological parameters, donor characteristics	DNN	46035/11509	90-d post-transplant survival	0.695-0.708¹^,³, 30.9-35.8³^,⁶, 88.1-90.8³^,⁷	[155]

¹Area under the receiver operating curve or c-index.

²Training.

³Internal validation.

⁴External validation/testing.

⁵Accuracy (%).

⁶Sensitivity (%).

⁷Specificity (%).

ALBI: Albumin-bilirubin; ANN: Artificial neural network; APO: Artificial plant optimization; BN: Bayesian network; CNN: Convolutional neural network; CS: Cuckoo-search; CT: Computed tomography; CTP: Child-Turcotte-Pugh; DNN: Deep neural network; DAE: Deep auto-encoder; DT: Decision tree; GBS: Gradient boosting survival; HCC: Hepatocellular carcinoma; LASSO: Least absolute shrinkage and selection operator; MLP: Multi-layer perceptron neural network; MRI: Magnetic resonance imaging; MWA: Microwave ablation; RF: Random forest; RFA: Radiofrequency ablation; SVM: Support vector machine; TACE: Transarterial chemoembolization; US: Ultrasound; WSI: Whole-slide image.

Citation: Christou CD, Tsoulfas G. Role of three-dimensional printing and artificial intelligence in the management of hepatocellular carcinoma: Challenges and opportunities. World J Gastrointest Oncol 2022; 14(4): 765-793
URL: https://www.wjgnet.com/1948-5204/full/v14/i4/765.htm
DOI: https://dx.doi.org/10.4251/wjgo.v14.i4.765