Research progress in predicting the diagnosis, treatment and prognosis of hepatocellular carcinoma based on radiomics
-
摘要: 作为全球最普遍的癌症之一的肝细胞癌(HCC)，存在着复发率高、预后较差等问题。影像组学是一种拥有巨大潜力的新兴交叉学科，因其能无创获取肿瘤异质性信息而在HCC等癌症的诊疗及预后评估上具有广阔的应用前景。本文将从影像组学的工作流程，以及其在HCC的鉴别诊断、病理分级、免疫组化标记物的术前预测、预后预测和疗效评估等方面展开综述，并总结影像组学技术尚存在的局限及未来的发展方向，通过梳理影像组学在HCC诊疗及预后评估上的最新研究进展，旨在为未来HCC的诊治提供新的参考和思路。Abstract: Hepatocellular carcinoma (HCC), as one of the most prevalent cancers globally, confronts challenges such as a high recurrence rate and poor prognosis. Radiomics is an emerging interdisciplinary discipline with significant potential, showing broad applications in the diagnosis, treatment, and prognosis evaluation of HCC and other cancers. This is attributed to its capacity to noninvasively acquire tumor heterogeneity information. In this paper, we comprehensively examined the workflow of radiomics, exploring its applications in the differential diagnosis, pathological grading, preoperative prediction of immunohistochemical markers, prognosis prediction, and efficacy evaluation of HCC. Additionally, we summarized the limitations and outlined future directions for the development of radiomics technology, with the aim of providing a comprehensive overview of the latest research progress in the diagnosis and prognosis of HCC. This review also introduces novel references and ideas for the future diagnosis and treatment of HCC.
-
Key words:
- hepatocellular carcinoma /
- radiomics /
- differential diagnosis /
- prognostic evaluation
-
表 1 近5年来基于影像组学在HCC应用上的研究
Table 1. Research on the application of radiomics in HCC in the past five years
Study Classification Dataset Imaging Modality Modeling Approach AUC Nie, et al, 2021[26] Discrimination diagnosis Training set=93
Test set=38
Total=131Enhanced CT Logistic regression model 0.93-0.99 Lin, et al, 2020[27] Discrimination diagnosis Training set=87
Test set=37
Total=124Conventional gray scale ultrasound Multivariate Logistic regression model with tenfold cross-validation 0.94 Dong, et al, 2022[29] Pathological grading Training set=71
Test set=30
Total=101Contrast-enhanced ultrasound Logistic regression model 0.792-0.908 Chen, et al, 2021[31] Pathological grading Training set=112
Test set=49
Total=161Contrast-enhanced CT Support vector machine and logistic regression model 0.904-0.937 Mao, et al, 2022[30] Pathological grading Training set=85
Test set=37
Total=122Gd-EOB-DTPA enhanced MRI Artificial neural network and Logistic regression model 0.792-0.944 Wang, et al, 2020[36] Preoperative prediction of immunohistochemical markers Training set=159
Test set=68
Total=227Gadolinium-based contrast-enhanced MR Decision tree and logistic regression model 0.822-0.951 Yang, et al, 2021[37] MVI Prediction Training set=143
Test set=114
Total=257Gadolinium-based contrast-enhanced MRI Multivariate Logistic regression, SVM, random forest and artificial neural network 0.726-0.857 Liao, et al, 2022[39] Preoperative prediction of immunohistochemical markers 132 cases Contrast-enhanced CT Factor analysis, logistic regression, minimum absolute shrinkage and selection operator, random forest 0.694-0.771 Li, et al, 2021[47] MVI prediction Training set=50
Test set=30
Total=8018F FDG PET/CT Logistic regression and cox regression analysis 0.761-0.900 Liu, et al, 2022[55] Recurrence and survival prediction Training set=188
Test set=79
Total=267Contrast-enhanced CT Spearman correlation coefficient, LASSO, Cox regression analysis 0.754-0.810 Fu, et al, 2021[56] Recurrence and survival prediction Training set=281
Test set=85
Total=366Enhanced CT Multifactor logistic regression 0.877-0.836 Wang, et al, 2020[57] Recurrence and survival prediction 201 cases T1WI, T2WI, DWI and dynamic contrast-enhanced imaging Random forest with fivefold cross-validation, multifactor Logistic regression analysis 0.9804-0.7578 Saalfeld, et al, 2023[59] Recurrence and survival prediction 297 cases CT Random forest, SVM, decision tree, bayesian classification, LASSO 0.6930-0.9134 Kong, et al, 2021[62] TACE post-treatment Efficacy assessment Training set=69
Test set=30
Total=99Dynamic contrast MRI LASSO Logistic regression model 0.861-0.884 Liu, et al, 2020[63] TACE post-treatment Efficacy assessment Training set=89
Test set=41
Total=130Contrast-enhanced ultrasound LASSO Logistic regression model 0.80-0.98 
下载: 导出CSV
-
[1] Sung H, Ferlay J, Siegel RL, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-49. doi: 10.3322/caac.21660 [2] Sartoris R, Gregory J, Dioguardi Burgio M, et al. HCC advances in diagnosis and prognosis: digital and Imaging[J]. Liver Int, 2021, 41 (Suppl 1): 73-7. [3] Forner A, Reig M, Bruix J. Hepatocellular carcinoma[J]. Lancet, 2018, 391(10127): 1301-14. doi: 10.1016/S0140-6736(18)30010-2 [4] Guiot J, Vaidyanathan A, Deprez L, et al. A review in radiomics: making personalized medicine a reality via routine imaging[J]. Med Res Rev, 2022, 42(1): 426-40. doi: 10.1002/med.21846 [5] Peng ZY, Wang YM, Wang YX, et al. Application of radiomics and machine learning in head and neck cancers[J]. Int J Biol Sci, 2021, 17(2): 475-86. doi: 10.7150/ijbs.55716 [6] Jiang C, Cai YQ, Yang JJ, et al. Radiomics in the diagnosis and treatment of hepatocellular carcinoma[J]. Hepatobiliary Pancreat Dis Int, 2023, 22(4): 346-51. doi: 10.1016/j.hbpd.2023.03.010 [7] Liu ZY, Wang S, Dong D, et al. The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges[J]. Theranostics, 2019, 9(5): 1303-22. doi: 10.7150/thno.30309 [8] Castaldo A, De Lucia DR, Pontillo G, et al. State of the art in artificial intelligence and radiomics in hepatocellular carcinoma[J]. Diagnostics, 2021, 11(7): 1194. doi: 10.3390/diagnostics11071194 [9] Parmar C, Rios Velazquez E, Leijenaar R, et al. Robust Radiomics feature quantification using semiautomatic volumetric segmentation[J]. PLoS One, 2014, 9(7): e102107. doi: 10.1371/journal.pone.0102107 [10] Marschner S, Datar M, Gaasch A, et al. A deep image- to- image network organ segmentation algorithm for radiation treatment planning: principles and evaluation[J]. Radiat Oncol, 2022, 17(1): 129. doi: 10.1186/s13014-022-02102-6 [11] Zhu M, Li SJ, Kuang Y, et al. Artificial intelligence in the radiomic analysis of glioblastomas: a review, taxonomy, and perspective[J]. Front Oncol, 2022, 12: 924245. doi: 10.3389/fonc.2022.924245 [12] Mayerhoefer ME, Materka A, Langs G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-95. doi: 10.2967/jnumed.118.222893 [13] Miranda J, Horvat N, Fonseca GM, et al. Current status and future perspectives of radiomics in hepatocellular carcinoma[J]. World J Gastroenterol, 2023, 29(1): 43-60. doi: 10.3748/wjg.v29.i1.43 [14] Park T, Yoon MA, Cho YC, et al. Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy[J]. Sci Rep, 2022, 12(1): 6735. doi: 10.1038/s41598-022-10807-7 [15] Mu W, Schabath MB, Gillies RJ. Images are data: challenges and opportunities in the clinical translation of radiomics[J]. Cancer Res, 2022, 82(11): 2066-8. doi: 10.1158/0008-5472.CAN-22-1183 [16] 李双双, 侯震, 刘娟, 等. 影像组学分析与建模工具综述[J]. 中国医学物理学杂志, 2018, 35(9): 1043-9. doi: 10.3969/j.issn.1005-202X.2018.09.010 [17] Tseng PY, Chen YT, Wang CH, et al. Prediction of the development of acute kidney injury following cardiac surgery by machine learning[J]. Crit Care, 2020, 24(1): 478. doi: 10.1186/s13054-020-03179-9 [18] Bera K, Braman N, Gupta A, et al. Predicting cancer outcomes with radiomics and artificial intelligence in radiology[J]. Nat Rev Clin Oncol, 2022, 19(2): 132-46. doi: 10.1038/s41571-021-00560-7 [19] Ren S, Zhang JJ, Chen JY, et al. Evaluation of texture analysis for the differential diagnosis of mass-forming pancreatitis from pancreatic ductal adenocarcinoma on contrast-enhanced CT images[J]. Front Oncol, 2019, 9: 1171. doi: 10.3389/fonc.2019.01171 [20] Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-62. doi: 10.1038/nrclinonc.2017.141 [21] Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models[J]. Med Decis Making, 2006, 26(6): 565-74. doi: 10.1177/0272989X06295361 [22] Yang T, Wu YH, Zuo Y, et al. Development and validation of prognostic nomograms and a web-based survival rate calculator for sarcomatoid renal cell carcinoma in pre- and post-treatment patients[J]. Transl Androl Urol, 2021, 10(2): 754-64. doi: 10.21037/tau-20-1192 [23] Jiang HY, Chen J, Xia CC, et al. Noninvasive imaging of hepatocellular carcinoma: from diagnosis to prognosis[J]. World J Gastroenterol, 2018, 24(22): 2348-62. doi: 10.3748/wjg.v24.i22.2348 [24] 韩玉齐, 魏靖伟, 蒋涵羽, 等. 影像组学研究进展及其在肝癌中的临床应用[J]. 中国科学: 生命科学, 2020, 50(11): 1309-20. https://www.cnki.com.cn/Article/CJFDTOTAL-JCXK202011013.htm [25] Liu XY, Khalvati F, Namdar K, et al. Can machine learning radiomics provide pre- operative differentiation of combined hepatocellular cholangiocarcinoma from hepatocellular carcinoma and cholangiocarcinoma to inform optimal treatment planning?[J]. Eur Radiol, 2021, 31(1): 244-55. doi: 10.1007/s00330-020-07119-7 [26] Nie P, Wang N, Pang J, et al. CT- based radiomics nomogram: a potential tool for differentiating hepatocellular adenoma from hepatocellular carcinoma in the noncirrhotic liver[J]. Acad Radiol, 2021, 28(6): 799-807. doi: 10.1016/j.acra.2020.04.027 [27] 林莹, 冯湛, 蒋国平. 灰阶超声影像组学鉴别肝细胞肝癌与肿块型肝内胆管细胞癌的价值[J]. 中国医学影像学杂志, 2020, 28(4): 269-72. doi: 10.3969/j.issn.1005-5185.2020.04.007 [28] Zhou L, Rui JG, Zhou WX, et al. Edmondson-Steiner grade: a crucial predictor of recurrence and survival in hepatocellular carcinoma without microvascular invasio[J]. Pathol Res Pract, 2017, 213(7): 824-30. doi: 10.1016/j.prp.2017.03.002 [29] Dong Y, Zuo D, Qiu YJ, et al. Prediction of histological grades and ki- 67 expression of hepatocellular carcinoma based on sonazoid contrast enhanced ultrasound radiomics signatures[J]. Diagnostics, 2022, 12(9): 2175. doi: 10.3390/diagnostics12092175 [30] Mao YF, Wang JC, Zhu Y, et al. Gd- EOB-DTPA- enhanced MRI radiomic features for predicting histological grade of hepatocellular carcinoma[J]. Hepatobiliary Surg Nutr, 2022, 11(1): 13-24. doi: 10.21037/hbsn-19-870 [31] Chen W, Zhang T, Xu L, et al. Radiomics analysis of contrastenhanced CT for hepatocellular carcinoma grading[J]. Front Oncol, 2021, 11: 660509. doi: 10.3389/fonc.2021.660509 [32] Hectors SJ, Lewis S, Besa C, et al. MRI radiomics features predict immuno- oncological characteristics of hepatocellular carcinoma[J]. Eur Radiol, 2020, 30(7): 3759-69. doi: 10.1007/s00330-020-06675-2 [33] Maruyama H, Yamaguchi T, Nagamatsu H, et al. AI-based radiological imaging for HCC: current status and future of ultrasound[J]. Diagnostics, 2021, 11(2): 292. doi: 10.3390/diagnostics11020292 [34] Hu XX, Yang ZX, Liang HY, et al. Whole-tumor MRI histogram analyses of hepatocellular carcinoma: correlations with Ki- 67 labeling index[J]. J Magn Reson Imaging, 2017, 46(2): 383-92. doi: 10.1002/jmri.25555 [35] Zhuo JY, Lu D, Tan WY, et al. CK19- positive hepatocellular carcinoma is a characteristic subtype[J]. J Cancer, 2020, 11(17): 5069-77. doi: 10.7150/jca.44697 [36] Wang WT, Gu DS, Wei JW, et al. A radiomics-based biomarker for cytokeratin 19 status of hepatocellular carcinoma with gadoxetic acid-enhanced MRI[J]. Eur Radiol, 2020, 30(5): 3004-14. doi: 10.1007/s00330-019-06585-y [37] Yang F, Wan YD, Xu L, et al. MRI- radiomics prediction for cytokeratin 19- positive hepatocellular carcinoma: a multicenter study[J]. Front Oncol, 2021, 11: 672126. doi: 10.3389/fonc.2021.672126 [38] Yue XT, Zhao YH, Xu Y, et al. Mutant p53 in cancer: accumulation, gain-of-function, and therapy[J]. J Mol Biol, 2017, 429(11): 1595-606. doi: 10.1016/j.jmb.2017.03.030 [39] Liao HT, Jiang HY, Chen YT, et al. Predicting genomic alterations of phosphatidylinositol-3 kinase signaling in hepatocellular carcinoma: a radiogenomics study based on next-generation sequencing and contrast- enhanced CT[J]. Ann Surg Oncol, 2022. doi: 10.1245/s10434-022-11505-4. [40] Hu HT, Wang Z, Huang XW, et al. Ultrasound- based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma[J]. Eur Radiol, 2019, 29(6): 2890-901. doi: 10.1007/s00330-018-5797-0 [41] Lee S, Kim SH, Lee JE, et al. Preoperative gadoxetic acidenhanced MRI for predicting microvascular invasion in patients with single hepatocellular carcinoma[J]. J Hepatol, 2017, 67(3): 526-34. doi: 10.1016/j.jhep.2017.04.024 [42] McHugh PP, Gilbert J, Vera S, et al. Alpha-fetoprotein and tumour size are associated with microvascular invasion in explanted livers of patients undergoing transplantation with hepatocellular carcinoma[J]. HPB, 2010, 12(1): 56-61. doi: 10.1111/j.1477-2574.2009.00128.x [43] Renzulli M, Brocchi S, Cucchetti A, et al. Can current preoperative imaging be used to detect microvascular invasion of hepatocellular carcinoma?[J]. Radiology, 2016, 279(2): 432-42. doi: 10.1148/radiol.2015150998 [44] Ahn SY, Lee JM, Joo I, et al. Prediction of microvascular invasion of hepatocellular carcinoma using gadoxetic acid- enhanced MR and 18F-FDG PET/CT[J]. Abdom Imag, 2015, 40(4): 843-51. doi: 10.1007/s00261-014-0256-0 [45] Kaibori M, Ishizaki M, Matsui K, et al. Predictors of microvascular invasion before hepatectomy for hepatocellular carcinoma[J]. J Surg Oncol, 2010, 102(5): 462-8. doi: 10.1002/jso.21631 [46] Yang L, Gu DS, Wei JW, et al. A radiomics nomogram for preoperative prediction of microvascular invasion in hepatocellular carcinoma[J]. Liver Cancer, 2019, 8(5): 373-86. doi: 10.1159/000494099 [47] Li YC, Zhang Y, Fang Q, et al. Radiomics analysis of 18F- FDG PET/CT for microvascular invasion and prognosis prediction in very-early-and early-stage hepatocellular carcinoma[J]. Eur J Nucl Med Mol Imaging, 2021, 48(8): 2599-614. doi: 10.1007/s00259-020-05119-9 [48] Liu QP, Xu X, Zhu FP, et al. Prediction of prognostic risk factors in hepatocellular carcinoma with transarterial chemoembolization using multi-modal multi-task deep learning[J]. EClinicalMedicine, 2020, 23: 100379. doi: 10.1016/j.eclinm.2020.100379 [49] Liu QQ, Li J, Liu F, et al. A radiomics nomogram for the prediction of overall survival in patients with hepatocellular carcinoma after hepatectomy[J]. Cancer Imaging, 2020, 20(1): 82. doi: 10.1186/s40644-020-00360-9 [50] Lacaze L, Scotté M. Surgical treatment of intra hepatic recurrence of hepatocellular carcinoma[J]. World J Hepatol, 2015, 7(13): 1755-60. doi: 10.4254/wjh.v7.i13.1755 [51] Earl TM, Chapman WC. Hepatocellular carcinoma: resection versus transplantation[J]. Semin Liver Dis, 2013, 33(3): 282-92. doi: 10.1055/s-0033-1351783 [52] Poon RTP, Fan ST, Lo CM, et al. Long-term survival and pattern of recurrence after resection of small hepatocellular carcinoma in patients with preserved liver function: implications for a strategy of salvage transplantation[J]. Ann Surg, 2002, 235(3): 373-82. doi: 10.1097/00000658-200203000-00009 [53] Shah SA, Cleary SP, Wei AC, et al. Recurrence after liver resection for hepatocellular carcinoma: risk factors, treatment, and outcomes[J]. Surgery, 2007, 141(3): 330-9. doi: 10.1016/j.surg.2006.06.028 [54] Kim S, Shin J, Kim DY, et al. Radiomics on gadoxetic acidenhanced magnetic resonance imaging for prediction of postoperative early and late recurrence of single hepatocellular carcinoma[J]. Clin Cancer Res, 2019, 25(13): 3847-55. doi: 10.1158/1078-0432.CCR-18-2861 [55] Liu Y, Wei XQ, Zhang XR, et al. CT radiomics combined with clinical variables for predicting the overall survival of hepatocellular carcinoma patients after hepatectomy[J]. Transl Oncol, 2022, 26: 101536. doi: 10.1016/j.tranon.2022.101536 [56] Fu SR, Lai HR, Huang MY, et al. Multi-task deep learning network to predict future macrovascular invasion in hepatocellular carcinoma[J]. EClinicalMedicine, 2021, 42: 101201. doi: 10.1016/j.eclinm.2021.101201 [57] Wang XH, Long LH, Cui Y, et al. MRI-based radiomics model for preoperative prediction of 5- year survival in patients with hepatocellular carcinoma[J]. Br J Cancer, 2020, 122(7): 978-85. doi: 10.1038/s41416-019-0706-0 [58] Saalfeld S, Kreher R, Hille G, et al. Prognostic role of radiomicsbased body composition analysis for the 1-year survival for hepatocellular carcinoma patients[J]. J Cachexia Sarcopenia Muscle, 2023, 14(5): 2301-9. doi: 10.1002/jcsm.13315 [59] Liu F, Liu D, Wang K, et al. Deep learning radiomics based on contrast- enhanced ultrasound might optimize curative treatments for very-early or early-stage hepatocellular carcinoma patients[J]. Liver Cancer, 2020, 9(4): 397-413. doi: 10.1159/000505694 [60] 刘一萍, 李新平, 陈磊, 等. 基于人工智能的肝细胞癌精准影像学诊断和复发预测[J]. 临床肝胆病杂志, 2022, 38(3): 521-7. https://www.cnki.com.cn/Article/CJFDTOTAL-LCGD202203006.htm [61] Kim J, Choi SJ, Lee SH, et al. Predicting survival using pretreatment CT for patients with hepatocellular carcinoma treated with transarterial chemoembolization: comparison of models using radiomics[J]. AJR Am J Roentgenol, 2018, 211(5): 1026-34. doi: 10.2214/AJR.18.19507 [62] Kong CL, Zhao ZW, Chen WY, et al. Prediction of tumor response via a pretreatment MRI radiomics-based nomogram in HCC treated with TACE[J]. Eur Radiol, 2021, 31(10): 7500-11. doi: 10.1007/s00330-021-07910-0 [63] Liu D, Liu F, Xie XY, et al. Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast- enhanced ultrasound[J]. Eur Radiol, 2020, 30(4): 2365-76. doi: 10.1007/s00330-019-06553-6 [64] 李嘉颖, 丁洪蕾, 张华妮, 等. 原发性肝癌DWI影像组学特征与中医证型的相关性研究[J]. 中国中西医结合影像学杂志, 2022, 20(2): 146-50 https://www.cnki.com.cn/Article/CJFDTOTAL-JHYX202202010.htm -
点击查看大图
表(1)
计量
- 文章访问数: 138
- HTML全文浏览量: 37
- PDF下载量: 29
- 被引次数: 0
