Share：
Share this content in WeChat
X
[Chinese][PDF]4501
• Clinical Article •
The value of radiomics models based on hepatobiliary phase images of Gd-EOB-DTPA enhanced MRI in prediction of microvascular invasion classification in hepatocellular carcinoma
LUO Ziwei  YU Haiyang  LIU Huaxiu  LI Zhiming  WANG Tao  ZANG Yichen  ZHOU Xiaoming 

Cite this article as: LUO Z W, YU H Y, LIU H X, et al. The value of radiomics models based on hepatobiliary phase images of Gd-EOB-DTPA enhanced MRI in prediction of microvascular invasion classification in hepatocellular carcinoma[J]. Chin J Magn Reson Imaging, 2023, 14(4): 95-101, 114. DOI:10.12015/issn.1674-8034.2023.04.016.


[Abstract] Objectives To evaluate the efficiency of radiomics models based on hepatobiliary phase (HBP) images of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced MRI in predicting the classification of microvascular invasion (MVI) in patients with primary hepatocellular carcinoma (HCC).Materials and Methods Three hundred seventy patients with HCC (M0∶M1∶M2=192∶132∶46) who underwent Gd-EOB-DTPA enhanced MRI before operation and were confirmed by pathology after operation were included in this study. The region of interest was delineated manually from HBP images, then the optimal radiomics features were extracted. The optimal features were combined with random forest (RF), logistic regression (LR), decision tree (DT) and K-nearest neighbor (KNN) to develop four three-category classification models. Accuracy and positive predictive value were used to evaluate the diagnostic efficacy of the models. Further, six binary classification models were constructed by one vs. rest and one vs. one strategies. Support vector machine (SVM) was used to construct the binary classification models. Receiver operator characteristic curve and area under the curve (AUC) were used to evaluate the diagnostic efficacy of the models.Results The accuracies of RF, LR, DT and KNN model in the training set were 76.00%, 61.00%, 66.00% and 62.00% respectively, in the validation set were 58.00%, 49.00%, 44.00% and 57.00% respectively. The three-category classification models had the highest positive predictive value for M0, and positive predictive value in the training set were 81.00%, 75.00%, 84.00% and 65.00% respectively, in the validation set were 68.00%, 63.00%, 69.00% and 62.00% respectively. Binary classification radiomics models showed good diagnostic ability for MVI classification. The AUC values in the training set of M0, M1 and M2 were 0.93, 0.77 and 0.79 respectively, and the AUC values of the validation set were 0.78, 0.67 and 0.76 respectively.Conclusion In the three-category classification models, the positive predictive value for predicting the M0 was the highest. Binary classification radiomics models had excellent diagnostic ability for MVI classification, and showed the highest diagnostic efficiency for predicting M0 and M2. The diagnostic efficiency of the binary classification model was better than that of the three-category classification model. Radiomics model based on Gd-EOB-DTPA enhanced MRI showed high value for predicting MVI classification in patients with HCC.
[Keywords] hepatocellular carcinoma；microvascular invasion classification；hepatobiliary phase；magnetic resonance imaging；radiomics；Gd-EOB-DTPA

LUO Ziwei1   YU Haiyang1   LIU Huaxiu1   LI Zhiming1   WANG Tao1   ZANG Yichen2   ZHOU Xiaoming1*  

1 Department of Radiology, Affiliated Hospital of Qingdao University, Qingdao 266000, China

2 Department of Ultrasonography, Affiliated Hospital of Qingdao University, Qingdao 266000, China

Corresponding author: Zhou XM, E-mail: zhouxm@qduhospital.cn

Conflicts of interest   None.

Received  2022-11-14
Accepted  2023-04-11
DOI: 10.12015/issn.1674-8034.2023.04.016
Cite this article as: LUO Z W, YU H Y, LIU H X, et al. The value of radiomics models based on hepatobiliary phase images of Gd-EOB-DTPA enhanced MRI in prediction of microvascular invasion classification in hepatocellular carcinoma[J]. Chin J Magn Reson Imaging, 2023, 14(4): 95-101, 114. DOI:10.12015/issn.1674-8034.2023.04.016.

[1]
BRAY F, FERLAY J, SOERJOMATARAM I, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2018, 68(6): 394-424. DOI: 10.3322/caac.21492.
[2]
GHOURI Y A, MIAN I, ROWE J H. Review of hepatocellular carcinoma: epidemiology, etiology, and carcinogenesis[J/OL]. J Carcinog, 2017, 16: 1 [2022-10-15]. https://doi.org/10.4103/jcar.JCar_9_16. DOI: 10.4103/jcar.JCar_9_16.
[3]
ISHIZAWA T, HASEGAWA K, AOKI T, et al. Neither multiple tumors nor portal hypertension are surgical contraindications for hepatocellular carcinoma[J]. Gastroenterology, 2008, 134(7): 1908-1916. DOI: 10.1053/j.gastro.2008.02.091.
[4]
RODRÍGUEZ-PERÁLVAREZ M, LUONG T V, ANDREANA L, et al. A systematic review of microvascular invasion in hepatocellular carcinoma: diagnostic and prognostic variability[J]. Ann Surg Oncol, 2013, 20(1): 325-339. DOI: 10.1245/s10434-012-2513-1.
[5]
HUANG Y, ZHANG Z Y, ZHOU Y F, et al. Should we apply sorafenib in hepatocellular carcinoma patients with microvascular invasion after curative hepatectomy?[J]. Onco Targets Ther, 2019, 12: 541-548. DOI: 10.2147/OTT.S187357.
[6]
HUANG C, ZHU X D, JI Y, et al. Microvascular invasion has limited clinical values in hepatocellular carcinoma patients at Barcelona Clinic Liver Cancer (BCLC) stages 0 or B[J/OL]. BMC Cancer, 2017, 17(1): 58 [2022-10-14]. https://doi.org/10.1186/s12885-017-3050-x. DOI: 10.1186/s12885-017-3050-x.
[7]
SHENG X, JI Y, REN G P, et al. A standardized pathological proposal for evaluating microvascular invasion of hepatocellular carcinoma: a multicenter study by LCPGC[J]. Hepatol Int, 2020, 14(6): 1034-1047. DOI: 10.1007/s12072-020-10111-4.
[8]
SHI M, GUO R P, LIN X J, et al. Partial hepatectomy with wide versus narrow resection margin for solitary hepatocellular carcinoma: a prospective randomized trial[J]. Ann Surg, 2007, 245(1): 36-43. DOI: 10.1097/01.sla.0000231758.07868.71.
[9]
OMATA M, CHENG A L, KOKUDO N, et al. Asia-Pacific clinical practice guidelines on the management of hepatocellular carcinoma: a 2017 update[J]. Hepatol Int, 2017, 11(4): 317-370. DOI: 10.1007/s12072-017-9799-9.
[10]
LIMKIN E J, SUN R, DERCLE L, et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology[J]. Ann Oncol, 2017, 28(6): 1191-1206. DOI: 10.1093/annonc/mdx034.
[11]
BRAMAN NATHANIEL M, MARYAM E, PRATEEK P, et al. Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI[J/OL]. Breast Cancer Res BCR, 2017, 19(1): 57 [2022-09-30]. https://doi.org/10.1186/s13058-017-0862-1. DOI: 10.1186/s13058-017-0846-1.
[12]
CHONG H H, YANG L, SHENG R F, et al. Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma ≤5 cm[J]. Eur Radiol, 2021, 31(7): 4824-4838. DOI: 10.1007/s00330-020-07601-2.
[13]
ZHANG H D, LI X M, ZHANG Y H, et al. Evaluation of preoperative microvascular invasion in hepatocellular carcinoma through multidimensional parameter combination modeling based on Gd-EOB-DTPA MRI[J]. J Clin Transl Hepatol, 2023, 11(2): 350-359. DOI: 10.14218/JCTH.2021.00546.
[14]
LIU H F, ZHANG Y Z, WANG Q, et al. A nomogram model integrating LI-RADS features and radiomics based on contrast-enhanced magnetic resonance imaging for predicting microvascular invasion in hepatocellular carcinoma falling the Milan criteria[J/OL]. Transl Oncol, 2023, 27: 101597 [2022-10-14]. https://doi.org/10.1016/j.tranon.2022.101597. DOI: 10.1016/j.tranon.2022.101597.
[15]
LU X Y, ZHANG J Y, ZHANG T, et al. Using pre-operative radiomics to predict microvascular invasion of hepatocellular carcinoma based on Gd-EOB-DTPA enhanced MRI[J/OL]. BMC Med Imaging, 2022, 22(1): 157 [2022-10-11]. https://doi.org/10.1186/s12880-022-00855-w. DOI: 10.1186/s12880-022-00855-w.
[16]
XU W, WANG Y G, YANG Z W, et al. New insights into a classification-based microvascular invasion prediction model in hepatocellular carcinoma: a multicenter study[J/OL]. Front Oncol, 2022, 12: 796311 [2022-10-14]. https://doi.org/10.3389/fonc.2022.796311. DOI: 10.3389/fonc.2022.796311.
[17]
CHEN S S, WANG C, GU Y W, et al. Prediction of microvascular invasion and its M2 classification in hepatocellular carcinoma based on nomogram analyses[J/OL]. Front Oncol, 2022, 11: 774800 [2022-10-14]. https://doi.org/10.3389/fonc.2021.774800. DOI: 10.3389/fonc.2021.774800.
[18]
WANG J, ZHENG J, SUN J, et al. The value of Gd-EOB-DTPA enhanced MRI in predicting microvascular invasion of hepatocellular carcinoma and its grade[J]. Chin J Magn Reson Imaging, 2021, 12(12): 79-83, 88. DOI: 10.12015/issn.1674-8034.2021.12.016.
[19]
CONG W M, BU H, CHEN J, et al. Guidelines for standardized pathological diagnosis of primary liver cancer (2015 edition)[J]. Chin J Clin Exp Pathol, 2015, 31(3): 241-246. DOI: 10.13315/j.cnki.cjcep.2015.03.001.
[20]
CHEN Y D, ZHANG L, ZHOU Z P, et al. Radiomics and nomogram of magnetic resonance imaging for preoperative prediction of microvascular invasion in small hepatocellular carcinoma[J]. World J Gastroenterol, 2022, 28(31): 4399-4416. DOI: 10.3748/wjg.v28.i31.4399.
[21]
CHEN Y D, XIA Y W, TOLAT P P, et al. Comparison of conventional gadoxetate disodium-enhanced MRI features and radiomics signatures with machine learning for diagnosing microvascular invasion[J]. AJR Am J Roentgenol, 2021, 216(6): 1510-1520. DOI: 10.2214/AJR.20.23255.
[22]
LAMBIN P, LEIJENAAR R T H, DEIST T M, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
[23]
SIM J Z T, HUI T C H, CHUAH T K, et al. Efficacy of texture analysis of pre-operative magnetic resonance imaging in predicting microvascular invasion in hepatocellular carcinoma[J]. World J Clin Oncol, 2022, 13(11): 918-928. DOI: 10.5306/wjco.v13.i11.918.
[24]
CERVANTES J, GARCIA-LAMONT F, RODRÍGUEZ-MAZAHUA L, et al. A comprehensive survey on support vector machine classification: applications, challenges and trends[J]. Neurocomputing, 2020, 408: 189-215. DOI: 10.1016/j.neucom.2019.10.118.
[25]
HSU C W, LIN C J. A comparison of methods for multiclass support vector machines[J]. IEEE Trans Neural Netw, 2002, 13(2): 415-425. DOI: 10.1109/72.991427.
[26]
HUANG S J, CAI N G, PACHECO P P, et al. Applications of support vector machine (SVM) learning in cancer genomics[J]. Cancer Genomics Proteomics, 2018, 15(1): 41-51. DOI: 10.21873/cgp.20063.
[27]
VAN BEERS B E, PASTOR C M, HUSSAIN H K. Primovist, eovist: what to expect?[J]. J Hepatol, 2012, 57(2): 421-429. DOI: 10.1016/j.jhep.2012.01.031.
[28]
FENG S T, JIA Y M, LIAO B, et al. Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI[J]. Eur Radiol, 2019, 29(9): 4648-4659. DOI: 10.1007/s00330-018-5935-8.
[29]
ZHONG X, LONG H Y, SU L Y, et al. Radiomics models for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis[J]. Abdom Radiol (NY), 2022, 47(6): 2071-2088. DOI: 10.1007/s00261-022-03496-3.
[30]
ZHANG S, XU G Z, DUAN C F, et al. Radiomics analysis of MR imaging with Gd-EOB-DTPA for preoperative prediction of microvascular invasion in hepatocellular carcinoma: investigation and comparison of different hepatobiliary phase delay times[J/OL]. Biomed Res Int, 2021, 2021: 6685723 [2022-10-14]. https://doi.org/10.1155/2021/6685723. DOI: 10.1155/2021/6685723.
[31]
YANG L, GU D S, WEI J W, et al. A radiomics nomogram for preoperative prediction of microvascular invasion in hepatocellular carcinoma[J]. Liver Cancer, 2019, 8(5): 373-386. DOI: 10.1159/000494099.
[32]
JIANG H Y, WEI J W, FU F F, et al. Predicting microvascular invasion in hepatocellular carcinoma: a dual-institution study on gadoxetate disodium-enhanced MRI[J]. Liver Int, 2022, 42(5): 1158-1172. DOI: 10.1111/liv.15231.
[33]
ZHANG X M, RUAN S J, XIAO W B, et al. Contrast-enhanced CT radiomics for preoperative evaluation of microvascular invasion in hepatocellular carcinoma: a two-center study[J/OL]. Clin Transl Med, 2020, 10(2): e111 [2022-09-30]. https://doi.org/10.1002/ctm2.111. DOI: 10.1002/ctm2.111.
[34]
LIU Y Q, ZHAO X X. Risk factors for predicting the grade of microvascular invasion in primary hepatocellular carcinoma[J]. Radiol Pract, 2020, 35(11): 1453-1457. DOI: 10.13609/j.cnki.1000-0313.2020.11.016.
[35]
NEBBIA G, ZHANG Q, AREFAN D, et al. Pre-operative microvascular invasion prediction using multi-parametric liver MRI radiomics[J]. J Digit Imaging, 2020, 33(6): 1376-1386. DOI: 10.1007/s10278-020-00353-x.
[36]
TIAN Y Q, HUA H, PENG Q Q, et al. Preoperative evaluation of Gd-EOB-DTPA-enhanced MRI radiomics-based nomogram in small solitary hepatocellular carcinoma (≤3 cm) with microvascular invasion: a two-center study[J]. J Magn Reson Imaging, 2022, 56(5): 1459-1472. DOI: 10.1002/jmri.28157.
[37]
GAO L M, XIONG M L, CHEN X J, et al. Multi-region radiomic analysis based on multi-sequence MRI can preoperatively predict microvascular invasion in hepatocellular carcinoma[J/OL]. Front Oncol, 2022, 12: 818681 [2023-03-01]. https://doi.org/10.3389/fonc.2022.818681. DOI: 10.3389/fonc.2022.818681.

PREV Quantitative assessment of liver and pancreatic fat infiltration and its correlation with insulin resistance in type 2 diabetic patients by 3D-IDEAL-IQ
NEXT The diagnostic value of radiomics based on HRT2WI and DWI in the breakthrough of the muscularis propria layer of rectal cancer
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn