Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast-enhanced ultrasound

Abstract

Objectives

We aimed to establish and validate an artificial intelligence–based radiomics strategy for predicting personalized responses of hepatocellular carcinoma (HCC) to first transarterial chemoembolization (TACE) session by quantitatively analyzing contrast-enhanced ultrasound (CEUS) cines.

Methods

One hundred and thirty HCC patients (89 for training, 41 for validation), who received ultrasound examination (CEUS and B-mode) within 1 week before the first TACE session, were retrospectively enrolled. Ultrasonographic data was used for building and validating deep learning radiomics-based CEUS model (R-DLCEUS), machine learning radiomics-based time-intensity curve of CEUS model (R-TIC), and machine learning radiomics-based B-Mode images model (R-BMode), respectively, to predict responses (objective-response and non-response) to TACE with reference to modified response evaluation criteria in solid tumor. The performance of models was compared by areas under the receiver operating characteristic curve (AUC) and the DeLong test was used to compare different AUCs. The prediction robustness was assessed for each model.

Results

AUCs of R-DLCEUS, R-TIC, and R-BMode were 0.93 (95% CI, 0.80–0.98), 0.80 (95% CI, 0.64–0.90), and 0.81 (95% CI, 0.67–0.95) in the validation cohort, respectively. AUC of R-DLCEUS shows significant difference compared with that of R-TIC (p = 0.034) and R-BMode (p = 0.039), whereas R-TIC was not significantly different from R-BMode. The performance was highly reproducible with different training and validation cohorts.

Conclusions

DL-based radiomics method can effectively utilize CEUS cines to achieve accurate and personalized prediction. It is easy to operate and holds good potential for benefiting TACE candidates in clinical practice.

Key Points

• Deep learning (DL) radiomics-based CEUS model can accurately predict responses of HCC patients to their first TACE session by quantitatively analyzing their pre-operative CEUS cines.

• The visualization of the 3D CNN analysis adopted in CEUS model provided direct insight into what computers “see” on CEUS cines, which can help people understand the interpretation of CEUS data.

• The proposed prediction method is easy to operate and labor-saving for clinical practice, facilitating the clinical treatment decision of HCCs with very few time costs.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Abbreviations

AFP:

Alpha-fetoprotein

AI:

Artificial intelligence

AUC:

Area under the receiver operating characteristic curve

BCLC:

Barcelona Clinical Liver Cancer

C3D:

Convolutional 3D

CECT:

Contrast-enhanced CT

CEMRI:

Contrast-enhanced MRI

CEUS:

Contrast-enhanced ultrasound

CNN:

Convolutional neural network

CR:

Complete response

CT:

Computed tomography

DL:

Deep learning

FC:

Fully connected layer

GBRT:

Gradient Boosted Regression Trees

HBV:

Hepatitis B virus

HCC:

Hepatocellular carcinoma

HCV:

Hepatitis C virus

ML:

Machine learning

mRECIST:

Modified Response Evaluation Criteria in Solid Tumors

MRI:

Magnetic resonance imaging

NPV:

Negative predictive value

PD:

Progression disease

PPV:

Positive predictive value

PR:

Partial response

RBF:

Radial based function

ROI:

Region of interest

SD:

Stable disease

SVM:

Support vector machine

T:

Training cohort

TACE:

Transarterial chemoembolization

TIC:

Time-intensity curve

V:

Validation cohort

References

  1. 1.

    Heimbach JK, Kulik LM, Finn RS et al (2018) AASLD guidelines for the treatment of hepatocellular carcinoma. Hepatology 67:358–380

    Article  Google Scholar 

  2. 2.

    Park J, Chen M, Colombo M et al (2015) Global patterns of hepatocellular carcinoma management from diagnosis to death: the BRIDGE study. Liver Int 35:2155–2166

    Article  Google Scholar 

  3. 3.

    Lencioni R, de Baere T, Soulen MC, Rilling WS, Geschwind JF (2016) Lipiodol transarterial chemoembolization for hepatocellular carcinoma: a systematic review of efficacy and safety data. Hepatology 64:106–116

    CAS  Article  Google Scholar 

  4. 4.

    Llovet JM, Real MI, Montana X et al (2002) Arterial embolisation or chemoembolisation vs. symptomatic treatment in patients with unresectable hepatocellular carcinoma: a randomized controlled trial. Lancet 359:1734–1739

    Article  Google Scholar 

  5. 5.

    Peng ZW, Zhang YJ, Chen MS et al (2013) Radiofrequency ablation with or without transcatheter arterial chemoembolization in the treatment of hepatocellular carcinoma: a prospective randomized trial. J Clin Oncol 31:426–432

    Article  Google Scholar 

  6. 6.

    Meyer T, Fox R, Ma YT et al (2017) Sorafenib in combination with transarterial chemoembolisation in patients with unresectable hepatocellular carcinoma (TACE 2): a randomised placebo-controlled, double-blind, phase 3 trial. Lancet Gastroenterol Hepatol 2:565–575

    Article  Google Scholar 

  7. 7.

    Kim BK, Kim SU, Kim KA et al (2015) Complete response at first chemoembolization is still the most robust predictor for favorable outcome in hepatocellular carcinoma. J Hepatol 62:1304–1310

    Article  Google Scholar 

  8. 8.

    Kim BK, Kim KA, Park JY et al (2013) Prospective comparison of prognostic values of modified response evaluation criteria in solid tumours with European Association for the Study of the liver criteria in hepatocellular carcinoma following chemoembolisation. Eur J Cancer 49:826–834

    Article  Google Scholar 

  9. 9.

    European Association for the Study of the Liver (2018) EASL clinical practice guidelines: management of hepatocellular carcinoma. J Hepatol 69:182–236

    Article  Google Scholar 

  10. 10.

    Loosen SH, Schulze-Hagen M, Leyh C et al (2018) IL-6 and IL-8 serum levels predict tumor response and overall survival after TACE for primary and secondary hepatic malignancies. Int J Mol Sci 19:E1766

    Article  Google Scholar 

  11. 11.

    Abajian A, Murali N, Savic LJ et al (2018) Predicting treatment response to intra-arterial therapies for hepatocellular carcinoma with the use of supervised machine learning-an artificial intelligence concept. J Vasc Interv Radiol 29:850–857

    Article  Google Scholar 

  12. 12.

    Lahrsow M, Albrecht MH, Bickford MW, Vogl TJ (2017) Predicting treatment response of colorectal cancer liver metastases to conventional lipiodol-based transarterial chemoembolization using diffusion-weighted MR imaging: value of pretreatment apparent diffusion coefficients (ADC) and ADC changes under therapy. Cardiovasc Intervent Radiol 40:852–859

    Article  Google Scholar 

  13. 13.

    Kadalayil L, Benini R, Pallan L et al (2013) A simple prognostic scoring system for patients receiving transarterial embolisation for hepatocellular cancer. Ann Oncol 24:2565–2570

    CAS  Article  Google Scholar 

  14. 14.

    Hucke F, Pinter M, Graziadei I et al (2014) How to STATE suitability and START transarterial chemoembolization in patients with intermediate stage hepatocellular carcinoma. J Hepatol 61:1287–1296

    Article  Google Scholar 

  15. 15.

    Sieghart W, Hucke F, Pinter M et al (2013) The ART of decision making: retreatment with transarterial chemoembolization in patients with hepatocellular carcinoma. Hepatology 57:2261–2273

    CAS  Article  Google Scholar 

  16. 16.

    Alzaraa A, Gravante G, Chung WY et al (2013) Contrast-enhanced ultrasound in the preoperative, intraoperative and postoperative assessment of liver lesions. Hepatol Res 43:809–819

    Article  Google Scholar 

  17. 17.

    Moschouris H, Malagari K, Marinis A et al (2012) Hepatocellular carcinoma treated with transarterial chemoembolization: evaluation with parametric contrast-enhanced ultrasonography. World J Radiol 4:379–386

    Article  Google Scholar 

  18. 18.

    Song J, Shi J, Dong D et al (2018) A new approach to predict progression-free survival in stage IV EGFR-mutant NSCLC patients with EGFR-TKI therapy. Clin Cancer Res 24:3583–3592

    CAS  Article  Google Scholar 

  19. 19.

    Wang K, Lu X, Zhou H et al (2019) Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study. Gut 68:729–741

    CAS  Article  Google Scholar 

  20. 20.

    Liu Z, Zhang XY, Shi YJ et al (2017) Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res 23:1038–2017

    Google Scholar 

  21. 21.

    Kermany DS, Goldbaum M, Cai W et al (2018) Identifyingmedical diagnoses and treatable diseases by image-based deep learning. Cell 172:1122–1131

    CAS  Article  Google Scholar 

  22. 22.

    Huang YQ, Liang CH, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34:2157–2164

    Article  Google Scholar 

  23. 23.

    Liu M, Lin M, Lu M et al (2015) Comparison of contrast-enhanced ultrasound and contrast-enhanced computed tomography in evaluating the treatment response to transcatheter arterial chemoembolization of hepatocellular carcinoma using modified RECIST. Eur Radiol 25:2502–2511

    Article  Google Scholar 

  24. 24.

    Georgiades C, Geschwind JF, Harrison N et al (2012) Lack of response after initial chemoembolization for hepatocellular carcinoma: does it predict failure of subsequent treatment? Radiology 265:115–123

    Article  Google Scholar 

  25. 25.

    Lencioni R, Llovet JM (2010) Modified RECIST (mRECIST) assessment for hepatocellular carcinoma. Semin Liver Dis 30:52–60

    CAS  Article  Google Scholar 

  26. 26.

    Edeline J, Boucher E, Rolland Y et al (2012) Comparison of tumor response by response evaluation criteria in solid Tumors (RECIST) and modified RECIST in patients treated with sorafenib for hepatocellular carcinoma. Cancer 118:147–156

    CAS  Article  Google Scholar 

  27. 27.

    Yushkevich PA, Piven J, Hazlett HC et al (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31:1116–1128

    Article  Google Scholar 

  28. 28.

    Kono Y, Lyshchik A, Cosgrove D et al (2017) Contrast enhanced ultrasound (CEUS) liver imaging reporting and data system (LIRADS®): the official version by the American College of Radiology (ACR). Ultraschall Med 38:85–86

    Article  Google Scholar 

  29. 29.

    Ta CN, Eghtedari M, Mattrey RF et al (2014) 2-tier in-plane motion correction and out-of-plane motion filtering for contrast-enhanced ultrasound. Investig Radiol 49:707–719

    Article  Google Scholar 

  30. 30.

    Tran D, Bourdev L, Fergus R et al (2015) Learning spatiotemporal features with 3D convolutional networks. arXiv:1412.0767

  31. 31.

    Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional twostream network fusion for video action recognition. arXiv: 1604.06573

  32. 32.

    Wang L, Xiong Y, Wang Z et al (2016) Temporal segment networks: towards good practices for deep action recognition. arXiv: 1608.00859

  33. 33.

    Srivastava N, Mansimov E, Salakhutdinov R (2016) Unsupervised learning of video representations using LSTMs. arXiv:1502.04681

  34. 34.

    Goodfellow I, Bengio Y, Courville A (2016) Deep Learning, MIT Press

  35. 35.

    Francois C (2016) Xception: deep learning with depthwise separable convolutions. arXiv:1610.02357

  36. 36.

    Zhang B, Zhao Q, Feng W et al (2018) AlphaMEX: a smarter global pooling method for convolutional neural networks. Neurocomputing:36–48

  37. 37.

    Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232

    Article  Google Scholar 

  38. 38.

    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    Google Scholar 

  39. 39.

    Varma S, Simon R (2006) Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics 7:91

    Article  Google Scholar 

  40. 40.

    Ta CN, Kono Y, Eghtedari M et al (2017) Focal liver lesions: computer-aided diagnosis by using contrast-enhanced US cine recordings. Radiology 286:1062–1071

    Article  Google Scholar 

  41. 41.

    Selvaraju RR, Cogswell M, Das A (2017) Grad-CAM: visual explanations from deep networks via gradient-based localization. arXiv:1610.02391

  42. 42.

    MJG L, Vedder MM, JCM W et al (2014) Net reclassification improvement: computation, interpretation, and controversies: a literature review and clinician’s guide. Ann Intern Med 160:122–131

    Google Scholar 

  43. 43.

    van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:104–107

    Article  Google Scholar 

  44. 44.

    Bruix J, Sala M, Llovet JM (2004) Chemoembolization for hepatocellular carcinoma. Gastroenterology 127:S179–S188

    CAS  Article  Google Scholar 

  45. 45.

    Zhou LQ, Wang JY, Yu SY et al (2019) Artificial intelligence in medical imaging of the liver. World J Gastroenterol 25:672–682

    Article  Google Scholar 

  46. 46.

    Iwamoto S, Sanefuji H, Okuda K (2003) Angiographic subsegmentectomy for the treatment of patients with small hepatocellular carcinoma. Cancer 97:1051–1056

    Article  Google Scholar 

  47. 47.

    Matsui O, Kadoya M, Yoshikawa J et al (1993) Small hepatocellular carcinoma: treatment with subsegmental transcatheter arterial embolization. Radiology 188:79–83

    CAS  Article  Google Scholar 

Download references

Funding

This work was supported by grants from the Ministry of Science and Technology of China under Grant (No. 2017YFA0205200), National Natural Science Foundation of China under Grant (Nos. K0109003, 61671449, 81227901, and 81527805), and Chinese Academy of Sciences under Grant (Nos. GJJSTD20170004, XDBS01030200, and QYZDJ-SSW-JSC005).

Author information

Affiliations

Authors

Corresponding authors

Correspondence to Manxia Lin or Jie Tian.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jie Tian.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• Retrospective

• Diagnostic or prognostic study

• Performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

ESM 1

(DOC 11436 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Liu, D., Liu, F., Xie, X. et al. Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast-enhanced ultrasound. Eur Radiol 30, 2365–2376 (2020). https://doi.org/10.1007/s00330-019-06553-6

Download citation

Keywords

  • Therapeutic chemoembolization
  • Hepatocellular carcinoma
  • Ultrasonography
  • Deep learning