Share：
Share this content in WeChat
X
[Chinese][PDF]79583
• Clinical Article •
Prediction of the early recurrence of HCC patients after TACE surgery based on T2 weighted image texture analysis
SUN Xianglin  YOU Yingning  ZHAO Xiangxuan  LU Zaiming 

Cite this article as: Sun XL, You YN, Zhang XX, et al. Prediction of the early recurrence of HCC patients after TACE surgery based on T2 weighted image texture analysis[J]. Chin J Magn Reson Imaging, 2021, 12(8): 22-26, 32. DOI:10.12015/issn.1674-8034.2021.08.005.


[Abstract] Objective To explore the value of texture analysis technology based on T2 weighted images in predicting the early recurrence of hepatocellular carcinoma (HCC) after transcatheter arterial chemoembolization (TACE). Materials andMethods A total of 121 patients with hepatocellular carcinoma were retrospectively collected, including 88 males and 33 females. All the patients meet the inclusion criteria and underwent MRI scan before surgery. Lesions of all the HCC patients were delineated manually, and post-processing software was used to extract the texture features automatically. All patients were divided into early recurrence group and non-early recurrence group according to the modified response evaluation criteria in solid tumors, and then analyzing the texture features and clinical features between the two groups. Using Logistic regression to analyze and construct the predictive model, and the diagnostic efficacy of radiomic features and clinical features in predicting the early recurrence after TACE were evaluated by ROC curves.Results A total of 371 texture features were obtained after T2WI image analysis of each patient, 7 significant texture features were selected after screening to construct the predictive model, specifically LongRunHighGreyLevelEmphasis_angle135_offset7, ClusterShade_AllDirection_offset4_SD, LongRunEmphasis_angle135_offset4, LongRunEmphasis_angle90_offset7, LongRunLowGreyLevelEmphasis_AllDirection_offset1_SD, ShortRunEmphasis_angle135_offset4, MinorAxisLength. The model has great predictive ability. The AUC of the training group is 0.728, the sensitivity and specificity were 71.11% and 71.79%. And the AUC of the verification group is 0.744, sensitivity and specificity were 85% and 58.82%. In addition, the AUC of the combined prediction model combined with clinical independent risk factors (tumor maximum diameter, GGT) and radiomic features was 0.807, showing better prediction efficacy (P＜0.05).Conclusions It is feasible to use MRI-based texture analysis technology to predict the early recurrence of HCC after TACE, which will help clinically provide better individualized treatment.
[Keywords] hepatocellular carcinoma；magnetic resonance imaging；texture analysis；transcatheter arterial chemoembolization；early recurrence

SUN Xianglin   YOU Yingning   ZHAO Xiangxuan   LU Zaiming*  

Department of Radiology, Shengjing Hospital of China Medical University, Shenyang 110000, China

Lu ZM, E-mail: luzm@sj-hospital.org

Conflicts of interest   None.

ACKNOWLEDGMENTS This work was part of National Natural Science Foundation of China (No. 81771947, 31371425) .
Received  2021-04-18
Accepted  2021-06-03
DOI: 10.12015/issn.1674-8034.2021.08.005
Cite this article as: Sun XL, You YN, Zhang XX, et al. Prediction of the early recurrence of HCC patients after TACE surgery based on T2 weighted image texture analysis[J]. Chin J Magn Reson Imaging, 2021, 12(8): 22-26, 32. DOI:10.12015/issn.1674-8034.2021.08.005.

1
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019[J]. CA Cancer J Clin, 2019, 69(1): 7-34. DOI: 10.3322/caac.21551.
2
Chen WQ, Zheng RS, Baade PD, et al. Cancer statistics in China, 2015[J]. CA Cancer J Clin, 2016, 66(2): 115-132. DOI: 10.3322/caac.21338.
3
Bruix J, Sherman M, American Association for the study of liver diseases. Management of hepatocellular carcinoma: an update[J]. Hepatology, 2011, 53(3): 1020-1022. DOI: 10.1002/hep.24199.
4
Ohki T, Sato K, Yamagami M, et al. Efficacy of transcatheter arterial chemoembolization followed by sorafenib for intermediate/advanced hepatocellular carcinoma in patients in Japan: a retrospective analysis[J]. Clin Drug Investig, 2015, 35(11): 751-759. DOI: 10.1007/s40261-015-0333-3.
5
Wáng YX, De Baere T, Idée JM, et al. Transcatheter embolization therapy in liver cancer: an update of clinical evidences[J]. Chin J Cancer Res, 2015, 27(2): 96-121. DOI: 10.3978/j.issn.1000-9604.2015.03.03.
6
Sun JY, Yin TL, Zhang XY, et al. Therapeutic advances for patients with intermediate hepatocellular carcinoma[J]. J Cell Physiol, 2019, 234(8): 12116-12121. DOI: 10.1002/jcp.28019.
7
Llovet JM, Bruix J. Novel advancements in the management of hepatocellular carcinoma in 2008[J]. J Hepatol, 2008, 48(Suppl 1): S20-37. DOI: 10.1016/j.jhep.2008.01.022.
8
Depeursinge A, Foncubierta-Rodriguez A, De Ville DV, et al. Three-dimensional solid texture analysis in biomedical imaging: review and opportunities[J]. Med Image Anal, 2014, 18(1): 176-196. DOI: 10.1016/j.media.2013.10.005.
9
Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
10
Medical Administration and Hospital Administration of the National Health Commission of the People's Republic of China. Standardization for diagnosis and treatment of primary hepatic carcinoma (2019 edition)[J]. Chin J Pract Surg, 2020, 40(2): 121-138. DOI: 10.19538/j.cjps.issn1005-2208.2020.02.01.
11
Lencioni R, Llovet JM. Modified RECIST (mRECIST) assessment for hepatocellular carcinoma[J]. Semin Liver Dis, 2010, 30(1): 52-60. DOI: 10.1055/s-0030-1247132.
12
Han K, Kim JH. Transarterial chemoembolization in hepatocellular carcinoma treatment: Barcelona clinic liver cancer staging system[J]. World J Gastroenterol, 2015, 21(36): 10327-10335. DOI: 10.3748/wjg.v21.i36.10327.
13
Kishore SA, Bajwa R, Madoff DC. Embolotherapeutic strategies for hepatocellular carcinoma: 2020 update[J]. Cancers (Basel), 2020, 12(4): 791. DOI: 10.3390/cancers12040791.
14
Yang HJ, Lee JH, Lee DH, et al. Small single-nodule hepatocellular carcinoma: comparison of transarterial chemoembolization, radiofrequency ablation, and hepatic resection by using inverse probability weighting[J]. Radiology, 2014, 271(3): 909-918. DOI: 10.1148/radiol.13131760.
15
Park HJ, Kim JH, Choi SY, et al. Prediction of therapeutic response of hepatocellular carcinoma to transcatheter arterial chemoembolization based on pretherapeutic dynamic CT and textural findings[J]. AJR Am J Roentgenol,2017, 209(4): W211-W220. DOI: 10.2214/AJR.16.17398.
16
Li ZJ, Mao Y, Huang W, et al. Texture-based classification of different single liver lesion based on SPAIR T2W MRI images[J]. BMC Med Imaging, 2017, 17(1):42. DOI: 10.1186/s12880-017-0212-x.
17
Zhou W, Zhang LJ, Wang KX, et al. Malignancy characterization of hepatocellular carcinomas based on texture analysis of contrast-enhanced MR images[J]. J Magn Reson Imaging, 2017, 45(5): 1476-1484. DOI: 10.1002/jmri.25454.
18
Feng MM, Zhang MC, Liu YQ, et al. Texture analysis of MR images to identify the differentiated degree in hepatocellular carcinoma: a retrospective study[J].BMC Cancer, 2020, 20(1): 611. DOI: 10.1186/s12885-020-07094-8.
19
Wilson GC, Cannella R, Fiorentini G, et al. Texture analysis on preoperative contrast-enhanced magnetic resonance imaging identifies microvascular invasion in hepatocellular carcinoma[J]. HPB (Oxford), 2020, 22(11): 1622-1630. DOI: 10.1016/j.hpb.2020.03.001.
20
Zhu YJ, Feng B, Wang S, et al. Model-based three-dimensional texture analysis of contrast-enhanced magnetic resonance imaging as a potential tool for preoperative prediction of microvascular invasion in hepatocellular carcinoma[J]. Oncol Lett,2019, 18(1): 720-732. DOI: 10.3892/ol.2019.10378.
21
Hui TCH, Chuah TK, Low HM, et al. Predicting early recurrence of hepatocellular carcinoma with texture analysis of preoperative MRI: a radiomics study[J]. Clin Radiol, 2018, 73(12): 1056. DOI: 10.1016/j.crad.2018.07.109.
22
Murakami T, Nakamura H, Tsuda K, et al. Treatment of hepatocellular carcinoma by chemoembolization: evaluation with 3DFT MR imaging[J]. AJR Am J Roentgenol, 1993, 160(2): 295-299. DOI: 10.2214/ajr.160.2.8380948.
23
Weng W, Lü XL, Zhang QQ, et al. Prediction of short-term prognosis of hepatocellular carcinoma after TACE surgery based on MRI texture analysis technology[J]. Natl Med J China, 2020, 100(11): 828-832. DOI: 10.3760/cma.j.cn112137-20190705-01502.
24
Sun YJ, Bai HL, Wang D, et al. Preoperative T2 MRI radiomics signature in predicting the short-term efficacy of interventional therapy for large HCC: a clinical study[J]. J Int Radiol, 2019, 28(11): 1036-1041. DOI: 10.3969/j.issn.1008-794X.2019.011.007.
25
Rou WS, Lee BS, Moon HS, et al. Risk factors and therapeutic results of early local recurrence after transcatheter arterial chemoembolization[J]. World J Gastroenterol, 2014, 20(22): 6995-7004. DOI: 10.3748/wjg.v20.i22.6995.
26
Nakano MM, Yamamoto A, Nishida N, et al. Risk factors for local recurrence of hepatocellular carcinoma after transcatheter arterial chemoembolization with drug-eluting beads (DEB-TACE)[J]. Jpn J Radiol, 2019, 37(7): 543-548. DOI: 10.1007/s11604-019-00840-4.
27
Chen DJ, Ding WB. Analysis of risk factors for early recurrence of patients with advanced primary liver cancer after TACE[J]. J Imaging Res Med Appli, 2020,4(13): 177-178. DOI: 10.3969/j.issn.2096-3807.2020.13.114.
28
Sun P, Li YL, Chang LJ, et al. Prognostic and clinicopathological significance of Gamma-Glutamyltransferase in patients with hepatocellular carcinoma: APRISMA-compliant meta-analysis[J]. Medicine (Baltimore), 2019, 98(19): e15603. DOI: 10.1097/MD.0000000000015603.
29
Li Q, Lu C, Li W, et al. The gamma-glutamyl transpeptidase-to-albumin ratio predicts significant fibrosis and cirrhosis in chronic hepatitis B patients[J]. J Viral Hepat2017, 24(12): 1143-1150. DOI: 10.1111/jvh.12751.
30
Corti A, Franzini M, Paolicchi A, et al. Gamma-glutamyltransferase of cancer cells at the crossroads of tumor progression, drug resistance and drug targeting[J]. Anticancer Res, 2010, 30(4): 1169-1181.

PREV The value of texture analysis based on diffusion tensor imaging in distinguishing hepatocellular carcinoma from intrahepatic cholangiocarcinoma
NEXT Preliminary study on risk model of clinical and MRI features of recurrent acute pancreatitis
  


LINK


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