Prediction of microvascular invasion in hepatocellular carcinoma patients with MRI radiomics based on susceptibility weighted imaging and T2-weighted imaging.

Hepatocellular carcinoma Microvascular invasion Radiomics Susceptibility-weighted imaging (SWI) T2-weighted imaging (T2WI)

Journal

La Radiologia medica
ISSN: 1826-6983
Titre abrégé: Radiol Med
Pays: Italy
ID NLM: 0177625

Informations de publication

Date de publication:
13 Jul 2024
Historique:
received: 11 10 2023
accepted: 01 07 2024
medline: 13 7 2024
pubmed: 13 7 2024
entrez: 12 7 2024
Statut: aheadofprint

Résumé

The accurate identification of microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) is of great clinical importance. To develop a radiomics nomogram based on susceptibility-weighted imaging (SWI) and T2-weighted imaging (T2WI) for predicting MVI in early-stage (Barcelona Clinic Liver Cancer stages 0 and A) HCC patients. A prospective cohort of 189 participants with HCC was included for model training and testing, and an additional 34 participants were enrolled for external validation. ITK-SNAP was used to manually segment the tumour, and PyRadiomics was used to extract radiomic features from the SWI and T2W images. Variance filtering, student's t test, least absolute shrinkage and selection operator regression and random forest (RF) were applied to select meaningful features. Four machine learning classifiers, including K-nearest neighbour, RF, logistic regression and support vector machine-based models, were established. Independent clinical and radiological risk factors were also determined to establish a clinical model. The best radiomics and clinical models were further evaluated in the validation set. In addition, a nomogram was constructed from the radiomic model and independent clinical factors. Diagnostic efficacy was evaluated by receiver operating characteristic curve analysis with fivefold cross-validation. AFP levels greater than 400 ng/mL [odds ratio (OR) 2.50; 95% confidence interval (CI) 1.239-5.047], tumour diameter greater than 5 cm (OR 2.39; 95% CI 1.178-4.839), and absence of pseudocapsule (OR 2.053; 95% CI 1.007-4.202) were found to be independent risk factors for MVI. The areas under the curve (AUCs) of the best radiomic model were 1.000 and 0.882 in the training and testing cohorts, respectively, while those of the clinical model were 0.688 and 0.6691. In the validation set, the radiomic model achieved better diagnostic performance (AUC = 0.888) than the clinical model (AUC = 0.602). The combination of clinical factors and the radiomic model yielded a nomogram with the best diagnostic performance (AUC = 0.948). SWI and T2WI-derived radiomic features are valuable for noninvasively and accurately identifying MVI in early-stage HCC. Furthermore, the integration of radiomics and clinical factors yielded a predictive nomogram with satisfactory diagnostic performance and potential clinical benefits.

Sections du résumé

BACKGROUND BACKGROUND
The accurate identification of microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC) is of great clinical importance.
PURPOSE OBJECTIVE
To develop a radiomics nomogram based on susceptibility-weighted imaging (SWI) and T2-weighted imaging (T2WI) for predicting MVI in early-stage (Barcelona Clinic Liver Cancer stages 0 and A) HCC patients.
MATERIALS AND METHODS METHODS
A prospective cohort of 189 participants with HCC was included for model training and testing, and an additional 34 participants were enrolled for external validation. ITK-SNAP was used to manually segment the tumour, and PyRadiomics was used to extract radiomic features from the SWI and T2W images. Variance filtering, student's t test, least absolute shrinkage and selection operator regression and random forest (RF) were applied to select meaningful features. Four machine learning classifiers, including K-nearest neighbour, RF, logistic regression and support vector machine-based models, were established. Independent clinical and radiological risk factors were also determined to establish a clinical model. The best radiomics and clinical models were further evaluated in the validation set. In addition, a nomogram was constructed from the radiomic model and independent clinical factors. Diagnostic efficacy was evaluated by receiver operating characteristic curve analysis with fivefold cross-validation.
RESULTS RESULTS
AFP levels greater than 400 ng/mL [odds ratio (OR) 2.50; 95% confidence interval (CI) 1.239-5.047], tumour diameter greater than 5 cm (OR 2.39; 95% CI 1.178-4.839), and absence of pseudocapsule (OR 2.053; 95% CI 1.007-4.202) were found to be independent risk factors for MVI. The areas under the curve (AUCs) of the best radiomic model were 1.000 and 0.882 in the training and testing cohorts, respectively, while those of the clinical model were 0.688 and 0.6691. In the validation set, the radiomic model achieved better diagnostic performance (AUC = 0.888) than the clinical model (AUC = 0.602). The combination of clinical factors and the radiomic model yielded a nomogram with the best diagnostic performance (AUC = 0.948).
CONCLUSION CONCLUSIONS
SWI and T2WI-derived radiomic features are valuable for noninvasively and accurately identifying MVI in early-stage HCC. Furthermore, the integration of radiomics and clinical factors yielded a predictive nomogram with satisfactory diagnostic performance and potential clinical benefits.

Identifiants

pubmed: 38997568
doi: 10.1007/s11547-024-01845-4
pii: 10.1007/s11547-024-01845-4
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Subventions

Organisme : Medical Science and Technology Foundation of Guangdong Province
ID : C2022061

Informations de copyright

© 2024. Italian Society of Medical Radiology.

Références

Villanueva A (2019) Hepatocellular carcinoma. N Engl J Med 380(15):1450–1462. https://doi.org/10.1056/NEJMra1713263
doi: 10.1056/NEJMra1713263 pubmed: 30970190
Lee S, Kang TW, Song KD, Lee MW, Rhim H, Lim HK, Kim SY, Sinn DH, Kim JM, Kim K, Ha SY (2021) Effect of Microvascular invasion risk on early recurrence of hepatocellular carcinoma after surgery and radiofrequency ablation. Ann Surg 273(3):564–571. https://doi.org/10.1097/sla.0000000000003268
doi: 10.1097/sla.0000000000003268 pubmed: 31058694
Xu XF, Diao YK, Zeng YY, Li C, Li FW, Sun LY, Wu H, Lin KY, Yao LQ, Wang MD, Zhang CW, Lau WY, Shen F, Yang T (2023) Association of severity in the grading of microvascular invasion with long-term oncological prognosis after liver resection for early-stage hepatocellular carcinoma: a multicenter retrospective cohort study from a hepatitis B virus-endemic area. Int J surg (London, England) 109(4):841–849. https://doi.org/10.1097/js9.0000000000000325
doi: 10.1097/js9.0000000000000325
Chan AWH, Zhong J, Berhane S, Toyoda H, Cucchetti A, Shi K, Tada T, Chong CCN, Xiang BD, Li LQ, Lai PBS, Mazzaferro V, García-Fiñana M, Kudo M, Kumada T, Roayaie S, Johnson PJ (2018) Development of pre and post-operative models to predict early recurrence of hepatocellular carcinoma after surgical resection. J Hepatol 69(6):1284–1293. https://doi.org/10.1016/j.jhep.2018.08.027
doi: 10.1016/j.jhep.2018.08.027 pubmed: 30236834
Yang P, Si A, Yang J, Cheng Z, Wang K, Li J, Xia Y, Zhang B, Pawlik TM, Lau WY, Shen F (2019) A wide-margin liver resection improves long-term outcomes for patients with HBV-related hepatocellular carcinoma with microvascular invasion. Surgery 165(4):721–730. https://doi.org/10.1016/j.surg.2018.09.016
doi: 10.1016/j.surg.2018.09.016 pubmed: 30554724
Erstad DJ, Tanabe KK (2019) Prognostic and therapeutic implications of microvascular invasion in hepatocellular carcinoma. Ann Surg Oncol 26(5):1474–1493. https://doi.org/10.1245/s10434-019-07227-9
doi: 10.1245/s10434-019-07227-9 pubmed: 30788629
Lin WD, Ye LN, Song ZS, Wang KP, Feng YF, Pan CY (2023) Wide surgical margins improve prognosis for HCC with microvascular invasion. Eur Rev Med Pharmacol Sci 27(5):2052–2059. https://doi.org/10.26355/eurrev_202303_31576
doi: 10.26355/eurrev_202303_31576 pubmed: 36930503
Cha DI, Kang TW, Jeong WK, Kim JM, Choi GS, Joh JW, Yi NJ, Ahn SH (2023) Preoperative assessment of microvascular invasion risk using gadoxetate-enhanced MRI for predicting outcomes after liver transplantation for single hepatocellular carcinoma within the Milan criteria. Eur Radiol. https://doi.org/10.1007/s00330-023-09936-y
doi: 10.1007/s00330-023-09936-y pubmed: 37938383
Cuadrado A, Fortea JI, Rodriguez-Lope C, Puente A, Fernandez-Vilchez V, Echavarria VJ, Castillo Suescun FJ, Fernandez R, Echeverri JA, Achalandabaso M, Toledo E, Pellon R, Rodriguez Sanjuan JC, Crespo J, Fabrega E (2023) Risk of Recurrence of Hepatocarcinoma after liver transplantation: performance of recurrence predictive models in a cohort of transplant patients. J Clin Med 12(17):5457. https://doi.org/10.3390/jcm12175457
doi: 10.3390/jcm12175457 pubmed: 37685524 pmcid: 10488177
Wang J, Zeng K, Li H, Deng Y, Zhang Y, Zhang T, Yi S, Wang G, Yang Y, Chen G (2021) Clinical study of microvascular invasion on prognosis of recipients after liver transplantation for liver cancer. Organ Transplant 12(3):309–316. https://doi.org/10.3969/j.issn.1674-7445.2021.03.009
doi: 10.3969/j.issn.1674-7445.2021.03.009
Scapicchio C, Gabelloni M, Barucci A, Cioni D, Saba L, Neri E (2021) A deep look into radiomics. Radiol Med (Torino) 126(10):1296–1311. https://doi.org/10.1007/s11547-021-01389-x
doi: 10.1007/s11547-021-01389-x pubmed: 34213702
Haller S, Haacke EM, Thurnher MM, Barkhof FJR (2021) Susceptibility-weighted imaging: technical essentials and clinical neurologic applications. Radiology 299(1):3–26. https://doi.org/10.1148/radiol.2021203071
doi: 10.1148/radiol.2021203071 pubmed: 33620291
Tao R, Zhang J, Dai Y, You Z, Fan Y, Cui J, Wang J (2012) Characterizing hepatocellular carcinoma using multi-breath-hold two-dimensional susceptibility-weighted imaging: comparison to conventional liver MRI. Clin Radiol 67(12):e91-97. https://doi.org/10.1016/j.crad.2012.08.015
doi: 10.1016/j.crad.2012.08.015 pubmed: 22981726
Li C, Hu J, Zhou D, Zhao J, Ma K, Yin X, Wang J (2014) Differentiation of bland from neoplastic thrombus of the portal vein in patients with hepatocellular carcinoma: application of susceptibility-weighted MR imaging. BMC Cancer 14:590. https://doi.org/10.1186/1471-2407-14-590
doi: 10.1186/1471-2407-14-590 pubmed: 25123782 pmcid: 4141102
Chen W, DelProposto Z, Liu W, Kassir M, Wang Z, Zhao J, Xie B, Wen Y, Wang J, Hu J (2014) Susceptibility-weighted imaging for the noncontrast evaluation of hepatocellular carcinoma: a prospective study with histopathologic correlation. PLoS ONE 9(5):e98303. https://doi.org/10.1371/journal.pone.0098303
doi: 10.1371/journal.pone.0098303 pubmed: 24879409 pmcid: 4039503
Dai Y, Zeng M, Li R, Rao S, Chen C, DelProposto Z, Haacke EM, Hu J, Renate J (2011) Improving detection of siderotic nodules in cirrhotic liver with a multi-breath-hold susceptibility-weighted imaging technique. J Magn Reson Imaging 34(2):318–325. https://doi.org/10.1002/jmri.22607
doi: 10.1002/jmri.22607 pubmed: 21780226
Zhou Q, Zhou C, Yin Y, Chen W, Liu C, Atyah M, Weng J, Shen Y, Yi Y, Ren N (2021) Development and validation of a nomogram combining hematological and imaging features for preoperative prediction of microvascular invasion in hepatocellular carcinoma patients. Ann Transl Med 9(5):402. https://doi.org/10.21037/atm-20-4695
doi: 10.21037/atm-20-4695 pubmed: 33842623 pmcid: 8033313
Matsuo M, Kanematsu M, Murakami T, Kim T, Hori M, Kondo H, Nakamura H, Hoshi H (2000) T2-weighted MR imaging for focal hepatic lesion detection: supplementary value of breath-hold imaging with half-Fourier single-shot fast spin-echo and multishot spin-echo echoplanar sequences. J Magn Reson Imaging 12(3):444–452
doi: 10.1002/1522-2586(200009)12:3<444::AID-JMRI10>3.0.CO;2-# pubmed: 10992312
Li H, Hu C, Yang Y, Zhao Y, Lin C, Li Z, Liu Q (2022) Single-breath-hold T2WI MRI with artificial intelligence-assisted technique in liver imaging: as compared with conventional respiratory-triggered T2WI. Magn Reson Imaging 93:175–180. https://doi.org/10.1016/j.mri.2022.08.012
doi: 10.1016/j.mri.2022.08.012 pubmed: 35987419
Zhou J, Sun H, Wang Z, Cong W, Wang J, Zeng M, Zhou W, Bie P, Liu L, Wen T, Han G, Wang M, Liu R, Ligong L, Ren Z, Chen M, Zeng Z, Liang P, Liang C, Chen M, Yan F, Wang W, Ji Y, Yun J, Cai D, Chen Y, Cheng W, Cheng S, Dai C, Guo W, Hua B, Huang X, Jia W, Li Y, Li Y, Liang J, Liu T, Lv G, Mao Y, Peng T, Ren W, Shi H, Shi G, Tao K, Wang W, Wang X, Wang Z, Xiang B, Xing B, Jianming Xu, Yang J, Yang J, Yang Y, Yang Y, Ye S, Yin Z, Zhang B, Zhang B, Zhang L, Zhang S, Zhang T, Zhao Y, Zheng H, Zhu J, Zhu K, Liu R, Shi Y, Xiao Y, Dai Z, Teng G, Cai J, Wang W, Cai X, Li Q, Shen F, Qin S, Dong J, Fan J (2020) Guidelines for the diagnosis and treatment of hepatocellular carcinoma (2019 edition). Liver Cancer 9(6):682–720. https://doi.org/10.1159/000509424
doi: 10.1159/000509424 pubmed: 33442540 pmcid: 7768108
Lee S, Kim SH, Lee JE, Sinn DH, Park CK (2017) Preoperative gadoxetic acid-enhanced MRI for predicting microvascular invasion in patients with single hepatocellular carcinoma. J Hepatol 67(3):526–534. https://doi.org/10.1016/j.jhep.2017.04.024
doi: 10.1016/j.jhep.2017.04.024 pubmed: 28483680
Chong HH, Yang L, Sheng RF, Yu YL, Wu DJ, Rao SX, Yang C, Zeng MS (2021) Multi-scale and multi-parametric radiomics of gadoxetate disodium-enhanced MRI predicts microvascular invasion and outcome in patients with solitary hepatocellular carcinoma </= 5 cm. Eur Radiol 31(7):4824–4838. https://doi.org/10.1007/s00330-020-07601-2
doi: 10.1007/s00330-020-07601-2 pubmed: 33447861 pmcid: 8213553
Yang L, Gu D, Wei J, Yang C, Rao S, Wang W, Chen C, Ding Y, Tian J, Zeng M (2019) A radiomics nomogram for preoperative prediction of microvascular invasion in hepatocellular carcinoma. Liver Cancer 8(5):373–386. https://doi.org/10.1159/000494099
doi: 10.1159/000494099 pubmed: 31768346
Xia TY, Zhou ZH, Meng XP, Zha JH, Yu Q, Wang WL, Song Y, Wang YC, Tang TY, Xu J, Zhang T, Long XY, Liang Y, Xiao WB, Ju SH (2023) Predicting Microvascular invasion in hepatocellular carcinoma using CT-based radiomics model. Radiology 307(4):e222729. https://doi.org/10.1148/radiol.222729
doi: 10.1148/radiol.222729 pubmed: 37097141
Wymer DT, Patel KP, Burke WF, Bhatia VK (2020) Phase-contrast MRI: physics, techniques, and clinical applications. Radio Gr 40(1):122–140. https://doi.org/10.1148/rg.2020190039
doi: 10.1148/rg.2020190039
Soman S, Holdsworth SJ, Barnes PD, Rosenberg J, Andre JB, Bammer R, Yeom KW (2013) Improved T2* imaging without increase in scan time: SWI processing of 2D gradient echo. AJNR Am J Neuroradiol 34(11):2092–2097. https://doi.org/10.3174/ajnr.A3595
doi: 10.3174/ajnr.A3595 pubmed: 23744690 pmcid: 7964849
Li RK, Zeng MS, Rao SX, Qiang JW, Dai YM, Ji Y, Chen CZ, Renate J (2012) Using a 2D multibreath-hold susceptibility-weighted imaging to visualize intratumoral hemorrhage of hepatocellular carcinoma at 3T MRI: correlation with pathology. J Magn Reson Imaging 36(4):900–906. https://doi.org/10.1002/jmri.23734
doi: 10.1002/jmri.23734 pubmed: 22744981
Wu M, Tan H, Gao F, Hai J, Ning P, Chen J, Zhu S, Wang M, Dou S, Shi D (2019) Predicting the grade of hepatocellular carcinoma based on non-contrast-enhanced MRI radiomics signature. Eur Radiol 29(6):2802–2811. https://doi.org/10.1007/s00330-018-5787-2
doi: 10.1007/s00330-018-5787-2 pubmed: 30406313
Sun Y, Bai H, Xia W, Wang D, Zhou B, Zhao X, Yang G, Xu L, Zhang W, Liu P, Xu J, Meng S, Liu R, Gao X (2020) Predicting the outcome of transcatheter arterial embolization therapy for unresectable hepatocellular carcinoma based on radiomics of preoperative multiparameter MRI. J Magn Reson Imaging 52(4):1083–1090. https://doi.org/10.1002/jmri.27143
doi: 10.1002/jmri.27143 pubmed: 32233054
Gao L, Xiong M, Chen X, Han Z, Yan C, Ye R, Zhou L, Li Y (2022) Multi-region radiomic analysis based on multi-sequence MRI can preoperatively predict microvascular invasion in hepatocellular carcinoma. Front Oncol 12:818681. https://doi.org/10.3389/fonc.2022.818681
doi: 10.3389/fonc.2022.818681 pubmed: 35574328 pmcid: 9094629
Xiao DD, Yan PF, Wang YX, Osman MS, Zhao HY (2018) Glioblastoma and primary central nervous system lymphoma: Preoperative differentiation by using MRI-based 3D texture analysis. Clin Neurol Neurosurg 173:84–90. https://doi.org/10.1016/j.clineuro.2018.08.004
doi: 10.1016/j.clineuro.2018.08.004 pubmed: 30092408
Wakabayashi T, Ouhmich F, Gonzalez-Cabrera C, Felli E, Saviano A, Agnus V, Savadjiev P, Baumert TF, Pessaux P, Marescaux J, Gallix B (2019) Radiomics in hepatocellular carcinoma: a quantitative review. Hepatol Int 13(5):546–559. https://doi.org/10.1007/s12072-019-09973-0
doi: 10.1007/s12072-019-09973-0 pubmed: 31473947
Sagir Kahraman A (2020) Radiomics in hepatocellular carcinoma. J Gastrointest Cancer 51(4):1165–1168. https://doi.org/10.1007/s12029-020-00493-x
doi: 10.1007/s12029-020-00493-x pubmed: 32844349
Lei Z, Li J, Wu D, Xia Y, Wang Q, Si A, Wang K, Wan X, Lau WY, Wu M, Shen F (2016) Nomogram for Preoperative estimation of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma within the Milan criteria. JAMA Surg 151(4):356–363. https://doi.org/10.1001/jamasurg.2015.4257
doi: 10.1001/jamasurg.2015.4257 pubmed: 26579636
Li Y, Zhang Y, Fang Q, Zhang X, Hou P, Wu H, Wang X (2021) Radiomics analysis of [(18)F] FDG PET/CT for microvascular invasion and prognosis prediction in very-early- and early-stage hepatocellular carcinoma. Eur J Nucl Med Mol Imaging 48(8):2599–2614. https://doi.org/10.1007/s00259-020-05119-9
doi: 10.1007/s00259-020-05119-9 pubmed: 33416951
Xu X, Zhang HL, Liu QP, Sun SW, Zhang J, Zhu FP, Yang G, Yan X, Zhang YD, Liu XS (2019) Radiomic analysis of contrast-enhanced CT predicts microvascular invasion and outcome in hepatocellular carcinoma. J Hepatol 70(6):1133–1144. https://doi.org/10.1016/j.jhep.2019.02.023
doi: 10.1016/j.jhep.2019.02.023 pubmed: 30876945

Auteurs

Zhijun Geng (Z)

Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China.

Shutong Wang (S)

Department of Hepatic Surgery, First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, 510080, People's Republic of China.

Lidi Ma (L)

Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China.

Cheng Zhang (C)

Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China.

Zeyu Guan (Z)

Macau University of Science and Technology, Avenida Wai Long, Taipa, Macau, China.

Yunfei Zhang (Y)

United Imaging Healthcare Co., Ltd, Shanghai, 201807, China.

Shaohan Yin (S)

Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China.

Shanshan Lian (S)

Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China.

Chuanmiao Xie (C)

Department of Radiology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in Southern China, No. 651 Dongfeng East Road, Guangzhou, 510060, People's Republic of China. xchuanm@sysucc.org.cn.

Classifications MeSH