The role of radiomics in hepato-bilio-pancreatic surgery: a literature review

Abstract

Radiomics is an advanced computational analysis of biomedical images that aims to obtain a detailed, objective, and multidimensional characterization of biological tissues. Radiomics features ultimately represent the physiopathology of the tissue under study and can be used to characterize and quantify the spatial distribution and interactions between the voxels that compose a biomedical image. The aim of this paper was to review the current role of radiomics in hepato-bilio-pancreatic surgery by analyzing systematic reviews, meta-analyses and the most relevant published series. Literature data revealed that radiomics is a promising tool in improving the non-invasive characterization and preoperative staging of hepato-bilio-pancreatic neoplasms. Nevertheless, there are major limitations in this approach, mainly linked to the lack of standardization in image acquisition, that result in a significant translational gap between research and clinical practice.

Keywords

Radiomics / liver / pancreas / bile ducts / computed tomography / magnetic resonance imaging

References

[1] Gillies RJ,Hricak H.Radiomics: images are more than pictures, they are data.Radiology2016;278:563-77 PMCID:PMC4734157

[2] Henry T,Lerousseau M.Investigation of radiomics based intra-patient inter-tumor heterogeneity and the impact of tumor subsampling strategies.Sci Rep2022;12:17244 PMCID:PMC9568579

[3] Varghese BA,Hwang DH.Texture analysis of imaging: what radiologists need to know.AJR Am J Roentgenol2019;212:520-8

[4] Lambin P,Deist TM.Radiomics: the bridge between medical imaging and personalized medicine.Nat Rev Clin Oncol2017;14:749-62

[5] Spadarella G,Akinci D’Antonoli T.Systematic review of the radiomics quality score applications: an EuSoMII radiomics auditing group initiative.Eur Radiol2023;33:1884-94 PMCID:PMC9935718

[6] Marrero JA,Sirlin CB.Diagnosis, staging, and management of hepatocellular carcinoma: 2018 practice guidance by the American Association for the study of liver diseases.Hepatology2018;68:723-50

[7] European Association for Study of Liver, European Organisation for Research and Treatment of Cancer. EASL-EORTC clinical practice guidelines: management of hepatocellular carcinoma.Eur J Cancer2012;48:599-641

[8] Singal A,Waljee A.Meta-analysis: surveillance with ultrasound for early-stage hepatocellular carcinoma in patients with cirrhosis.Aliment Pharmacol Ther2009;30:37-47 PMCID:PMC6871653

[9] Yao Z,Wu G.Preoperative diagnosis and prediction of hepatocellular carcinoma: radiomics analysis based on multi-modal ultrasound images.BMC Cancer2018;18:1089 PMCID:PMC6233500

[10] Harding-Theobald E,Maraj B.Systematic review: radiomics for the diagnosis and prognosis of hepatocellular carcinoma.Aliment Pharmacol Ther2021;54:890-901 PMCID:PMC8435007

[11] Dankerl P,Tsymbal A.A retrieval-based computer-aided diagnosis system for the characterization of liver lesions in CT scans.Acad Radiol2013;20:1526-34

[12] Mokrane FZ,Vavasseur A.Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules.Eur Radiol2020;30:558-70

[13] Laino ME,Ammirabile A.The added value of artificial intelligence to LI-RADS categorization: a systematic review.Eur J Radiol2022;150:110251

[14] Zhou L,Wang SB,Qu Q.Clinicopathological predictors of poor survival and recurrence after curative resection in hepatocellular carcinoma without portal vein tumor thrombosis.Pathol Oncol Res2015;21:131-8

[15] Mao B,Ning P.Preoperative prediction for pathological grade of hepatocellular carcinoma via machine learning-based radiomics.Eur Radiol2020;30:6924-32

[16] Wu M,Gao F.Predicting the grade of hepatocellular carcinoma based on non-contrast-enhanced MRI radiomics signature.Eur Radiol2019;29:2802-11

[17] Huang J,Zhang L.Preoperative prediction power of imaging methods for microvascular invasion in hepatocellular carcinoma: a systemic review and meta-analysis.Front Oncol2020;10:887 PMCID:PMC7333535

[18] Wang Q,Zhang J.Radiomics models for predicting microvascular invasion in hepatocellular carcinoma: a systematic review and radiomics quality score assessment.Cancers2021;13:5864 PMCID:PMC8616379

[19] Li L,Huang Y,Ye D.Radiomics for the preoperative evaluation of microvascular invasion in hepatocellular carcinoma: a meta-analysis.Front Oncol2022;12:831996 PMCID:PMC9021380

[20] Zhong X,Su L.Radiomics models for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis.Abdom Radiol2022;47:2071-88

[21] Yu Y,Wang X.Gd-EOB-DTPA-enhanced MRI radiomics to predict vessels encapsulating tumor clusters (VETC) and patient prognosis in hepatocellular carcinoma.Eur Radiol2022;32:959-70

[22] Lee CW,Yu MC.The expression of cytokeratin 19 in lymph nodes was a poor prognostic factor for hepatocellular carcinoma after hepatic resection.World J Surg Oncol2013;11:136 PMCID:PMC3708812

[23] Wang W,Wei J.A radiomics-based biomarker for cytokeratin 19 status of hepatocellular carcinoma with gadoxetic acid-enhanced MRI.Eur Radiol2020;30:3004-14

[24] Ji GW,Xu Q.Radiomic features at contrast-enhanced CT predict recurrence in early stage hepatocellular carcinoma: a multi-institutional study.Radiology2020;294:568-79

[25] Hectors SJ,Besa C.MRI radiomics features predict immuno-oncological characteristics of hepatocellular carcinoma.Eur Radiol2020;30:3759-69 PMCID:PMC7869026

[26] Kim J,Lee SH,Park H.Predicting survival using pretreatment CT for patients with hepatocellular carcinoma treated with transarterial chemoembolization: comparison of models using radiomics.AJR Am J Roentgenol2018;211:1026-34

[27] Kloth C,Kärgel R.Evaluation of texture analysis parameter for response prediction in patients with hepatocellular carcinoma undergoing drug-eluting bead transarterial chemoembolization (DEB-TACE) using biphasic contrast-enhanced ct image data: correlation with liver perfusion CT.Acad Radiol2017;24:1352-63

[28] Wu LF,Xu PJ.Pre-TACE kurtosis of ADC_total derived from histogram analysis for diffusion-weighted imaging is the best independent predictor of prognosis in hepatocellular carcinoma.Eur Radiol2019;29:213-23

[29] Shaghaghi M,Ameli S.Post-TACE changes in ADC histogram predict overall and transplant-free survival in patients with well-defined HCC: a retrospective cohort with up to 10 years follow-up.Eur Radiol2021;31:1378-90

[30] Yang X,Zhang Y,Wang Z.Predicting hepatocellular carcinoma early recurrence after ablation based on magnetic resonance imaging radiomics nomogram.Medicine2022;101:e32584 PMCID:PMC9803514

[31] Fiz F,Gionso M.Radiomics of biliary tumors: a systematic review of current evidence.Diagnostics2022;12:826 PMCID:PMC9024804

[32] Liu X,Namdar K.Can machine learning radiomics provide pre-operative differentiation of combined hepatocellular cholangiocarcinoma from hepatocellular carcinoma and cholangiocarcinoma to inform optimal treatment planning?.Eur Radiol2021;31:244-55

[33] Zhou C,Ma L,Yang C.Combined hepatocellular carcinoma-cholangiocarcinoma: MRI features correlated with tumor biomarkers and prognosis.Eur Radiol2022;32:78-88

[34] Ji GW,Zhang YD.A radiomics approach to predict lymph node metastasis and clinical outcome of intrahepatic cholangiocarcinoma.Eur Radiol2019;29:3725-35

[35] Chu H,Liang W.Radiomics using CT images for preoperative prediction of futile resection in intrahepatic cholangiocarcinoma.Eur Radiol2021;31:2368-76

[36] Qin H,Zhang J.Machine-learning radiomics to predict early recurrence in perihilar cholangiocarcinoma after curative resection.Liver Int2021;41:837-50

[37] Groot Koerkamp B,Allen PJ.American joint committee on cancer staging for resected perihilar cholangiocarcinoma: a comparison of the 6th and 7th editions.HPB2014;16:1074-82 PMCID:PMC4253330

[38] Jarnagin WR,DeMatteo RP.Staging, resectability, and outcome in 225 patients with hilar cholangiocarcinoma.Ann Surg2001;234:507-19 PMCID:PMC1422074

[39] Gazzaniga GM,Filauro M.Surgical treatment of proximal bile duct tumors.Int Surg1985;70:45-8

[40] Park HJ,Park SY.Preoperative prediction of postsurgical outcomes in mass-forming intrahepatic cholangiocarcinoma based on clinical, radiologic, and radiomics features.Eur Radiol2021;31:8638-48

[41] Zhang J,Zhao J.Intrahepatic cholangiocarcinoma: MRI texture signature as predictive biomarkers of immunophenotyping and survival.Eur Radiol2021;31:3661-72

[42] Mosconi C,Bruno A.Radiomics of cholangiocarcinoma on pretreatment CT can identify patients who would best respond to radioembolisation.Eur Radiol2020;30:4534-44

[43] Fiz F,Gennaro N.Radiomics of liver metastases: a systematic review.Cancers2020;12:2881 PMCID:PMC7600822

[44] Wesdorp NJ,Kemna R.Advanced image analytics predicting clinical outcomes in patients with colorectal liver metastases: a systematic review of the literature.Surg Oncol2021;38:101578

[45] Jia LL,Zhao LP,Huang G.Current status and quality of radiomic studies for predicting KRAS mutations in colorectal cancer patients: a systematic review and meta-analysis.Eur J Radiol2023;158:110640

[46] Kelahan LC,Soliman M.Role of hepatic metastatic lesion size on inter-reader reproducibility of CT-based radiomics features.Eur Radiol2022;32:4025-33

[47] Ahn SJ,Park SJ.Prediction of the therapeutic response after FOLFOX and FOLFIRI treatment for patients with liver metastasis from colorectal cancer using computerized CT texture analysis.Eur J Radiol2016;85:1867-74

[48] Dercle L,Schwartz LH.Radiomics response signature for identification of metastatic colorectal cancer sensitive to therapies targeting EGFR pathway.J Natl Cancer Inst2020;112:902-12 PMCID:PMC7492770

[49] Dohan A,Guiu B.Early evaluation using a radiomic signature of unresectable hepatic metastases to predict outcome in patients with colorectal cancer treated with FOLFIRI and bevacizumab.Gut2020;69:531-9

[50] Creasy JM,Chakraborty J.Quantitative imaging features of pretreatment CT predict volumetric response to chemotherapy in patients with colorectal liver metastases.Eur Radiol2019;29:458-67 PMCID:PMC6301122

[51] Abunahel BM,Kumar H.Pancreas image mining: a systematic review of radiomics.Eur Radiol2021;31:3447-67

[52] Gao Y,Zhu L.A systematic review of prognosis predictive role of radiomics in pancreatic cancer: heterogeneity markers or statistical tricks?.Eur Radiol2022;32:8443-52

[53] Staal FCR,van der Velden D.GEP-NET radiomics: a systematic review and radiomics quality score assessment.Eur Radiol2022;32:7278-94

[54] Goggins M,Brand R.Management of patients with increased risk for familial pancreatic cancer: updated recommendations from the International Cancer of the Pancreas Screening (CAPS) Consortium.Gut2020;69:7-17 PMCID:PMC7295005

[55] Signoretti M,Zerboni G,Delle Fave G.Results of surveillance in individuals at high-risk of pancreatic cancer: a systematic review and meta-analysis.United Eur Gastroent J2018;6:489-99 PMCID:PMC5987280

[56] Paiella S,Cavestro GM.Results of first-round of surveillance in individuals at high-risk of pancreatic cancer from the AISP (Italian Association for the Study of the Pancreas) registry.Am J Gastroenterol2019;114:665-70

[57] Chhoda A,Wattamwar K.Late-stage pancreatic cancer detected during high-risk individual surveillance: a systematic review and meta-analysis.Gastroenterology2022;162:786-98

[58] Chu LC,Kawamoto S.Utility of CT radiomics features in differentiation of pancreatic ductal adenocarcinoma from normal pancreatic tissue.AJR Am J Roentgenol2019;213:349-57

[59] Qureshi TA,Wachsman AM.Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images.Cancer Biomark2022;33:211-7 PMCID:PMC9255993

[60] Javed S,Gaddam S.Risk prediction of pancreatic cancer using AI analysis of pancreatic subregions in computed tomography images.Front Oncol2022;12:1007990 PMCID:PMC9682250

[61] Mukherjee S,Khasawneh H.Radiomics-based machine-learning models can detect pancreatic cancer on prediagnostic computed tomography scans at a substantial lead time before clinical diagnosis.Gastroenterology2022;163:1435-46.e3

[62] Jeon SK,Yoo J,Park SJ.Assessment of malignant potential in intraductal papillary mucinous neoplasms of the pancreas using MR findings and texture analysis.Eur Radiol2021;31:3394-404

[63] Chakraborty J,Gazit L.CT radiomics to predict high-risk intraductal papillary mucinous neoplasms of the pancreas.Med Phys2018;45:5019-29 PMCID:PMC8050835

[64] Permuth JB,Balarunathan Y.Combining radiomic features with a miRNA classifier may improve prediction of malignant pathology for pancreatic intraductal papillary mucinous neoplasms.Oncotarget2016;7:85785-97 PMCID:PMC5349874

[65] Zhang H,Li Q.Two nomograms for differentiating mass-forming chronic pancreatitis from pancreatic ductal adenocarcinoma in patients with chronic pancreatitis.Eur Radiol2022;32:6336-47

[66] Wei R,Yan W.Computer-aided diagnosis of pancreas serous cystic neoplasms: a radiomics method on preoperative MDCT images.Technol Cancer Res Treat2019;18:1533033818824339 PMCID:PMC6374001

[67] Chang N,Luo Y,Yu B.Development and multicenter validation of a CT-based radiomics signature for discriminating histological grades of pancreatic ductal adenocarcinoma.Quant Imaging Med Surg2020;10:692-702 PMCID:PMC7136722

[68] Tikhonova VS,Kondratyev EV.Radiomics model-based algorithm for preoperative prediction of pancreatic ductal adenocarcinoma grade.Eur Radiol2023;33:1152-61

[69] Gu D,Ding H.CT radiomics may predict the grade of pancreatic neuroendocrine tumors: a multicenter study.Eur Radiol2019;29:6880-90

[70] De Robertis R,Cardobi N.Can histogram analysis of MR images predict aggressiveness in pancreatic neuroendocrine tumors?.Eur Radiol2018;28:2582-91

[71] Mori M,Muffatti F.Prediction of the characteristics of aggressiveness of pancreatic neuroendocrine neoplasms (PanNENs) based on CT radiomic features.Eur Radiol2023;33:4412-21

[72] Salinas-Miranda E,Grünwald B.Correlation of transcriptional subtypes with a validated CT radiomics score in resectable pancreatic ductal adenocarcinoma.Eur Radiol2022;32:6712-22

[73] Bailey P,Nones K.Genomic analyses identify molecular subtypes of pancreatic cancer.Nature2016;531:47-52

[74] Rigiroli F,Lerebours R.CT radiomic features of superior mesenteric artery involvement in pancreatic ductal adenocarcinoma: a pilot study.Radiology2021;301:610-22 PMCID:PMC9899097

[75] Bian Y,Jiang H.Relationship between radiomics and risk of lymph node metastasis in pancreatic ductal adenocarcinoma.Pancreas2019;48:1195-203 PMCID:PMC6830946

[76] De Robertis R,Tomaiuolo L.Liver metastases in pancreatic ductal adenocarcinoma: a predictive model based on CT texture analysis.Radiol Med2022;127:1079-84

[77] Tang TY,Zhang Q.Development of a novel multiparametric MRI radiomic nomogram for preoperative evaluation of early recurrence in resectable pancreatic cancer.J Magn Reson Imaging2020;52:231-45 PMCID:PMC7317738

[78] De Robertis R,Pasquazzo F.Correlation between ADC histogram-derived metrics and the time to metastases in resectable pancreatic adenocarcinoma.Cancers2022;14:6050 PMCID:PMC9775993

[79] Kulkarni A,Jiang NN.Hypovascular pancreas head adenocarcinoma: CT texture analysis for assessment of resection margin status and high-risk features.Eur Radiol2020;30:2853-60

[80] De Robertis R,Cardobi N.Correlation of MR features and histogram-derived parameters with aggressiveness and outcomes after resection in pancreatic ductal adenocarcinoma.Abdom Radiol2020;45:3809-18

[81] Kim HS,Kim KG.Preoperative CT texture features predict prognosis after curative resection in pancreatic cancer.Sci Rep2019;9:17389 PMCID:PMC6874598

[82] Xie T,Li M,Yu X.Pancreatic ductal adenocarcinoma: a radiomics nomogram outperforms clinical model and TNM staging for survival estimation after curative resection.Eur Radiol2020;30:2513-24

[83] Sandrasegaran K,Asare-Sawiri M,Tann M.CT texture analysis of pancreatic cancer.Eur Radiol2019;29:1067-73

[84] Healy GM,Jain R.Pre-operative radiomics model for prognostication in resectable pancreatic adenocarcinoma with external validation.Eur Radiol2022;32:2492-505

[85] Borhani AA,Furlan A.Assessment of response to neoadjuvant therapy using CT texture analysis in patients with resectable and borderline resectable pancreatic ductal adenocarcinoma.AJR Am J Roentgenol2020;214:362-9 PMCID:PMC7457395

[86] Kim BR,Ahn SJ.CT prediction of resectability and prognosis in patients with pancreatic ductal adenocarcinoma after neoadjuvant treatment using image findings and texture analysis.Eur Radiol2019;29:362-72

[87] Cozzi L,Fogliata A.Computed tomography based radiomic signature as predictive of survival and local control after stereotactic body radiation therapy in pancreatic carcinoma.PLoS One2019;14:e0210758 PMCID:PMC6338357