Skip to main content
SpringerLink
Log in

Development and Preliminary Validation of a Novel Convolutional Neural Network Model for Predicting Treatment Response in Patients with Unresectable Hepatocellular Carcinoma Receiving Hepatic Arterial Infusion Chemotherapy

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

The goal of this study was to evaluate the performance of a convolutional neural network (CNN) with preoperative MRI and clinical factors in predicting the treatment response of unresectable hepatocellular carcinoma (HCC) patients receiving hepatic arterial infusion chemotherapy (HAIC). A total of 191 patients with unresectable HCC who underwent HAIC in our hospital between May 2019 and March 2022 were retrospectively recruited. We selected InceptionV4 from three representative CNN models, AlexNet, ResNet, and InceptionV4, according to the cross-entropy loss (CEL). We subsequently developed InceptionV4 to fuse the information from qualified pretreatment MRI data and patient clinical factors. Radiomic information was evaluated based on several constant sequences, including enhanced T1-weighted sequences (with arterial, portal, and delayed phases), T2 FSE sequences, and dual-echo sequences. The performance of InceptionV4 was cross-validated in the training cohort (n = 127) and internally validated in an independent cohort (n = 64), with comparisons against single important clinical factors and radiologists in terms of receiver operating characteristic (ROC) curves. Class activation mapping was used to visualize the InceptionV4 model. The InceptionV4 model achieved an AUC of 0.871 (95% confidence interval [CI] 0.761–0.981) in the cross-validation cohort and an AUC of 0.826 (95% CI 0.682–0.970) in the internal validation cohort; these two models performed better than did the other methods (AUC ranges 0.783–0.873 and 0.708–0.806 for cross- and internal validations, respectively; P < 0.01). The present InceptionV4 model, which integrates radiomic information and clinical factors, helps predict the treatment response of unresectable HCC patients receiving HAIC treatment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Availability of Data and Materials

The data used in the article are available with reasonable request from the corresponding author.

Abbreviations

HCC:

Hepatocellular carcinoma

TACE:

Transarterial chemoembolization

HAIC:

Hepatic arterial infusion of oxaliplatin

CNNs:

Convolutional neural networks

BCLC:

Barcelona Clinic Liver Cancer

HbsAg:

Hepatitis B surface antigen

AFP:

Alpha fetoprotein

PIVKA-II:

Protein induced by vitamin K absence or antagonist-II

PLT:

Platelet

TB:

Total bilirubin

ALT:

Alanine aminotransferase

AST:

Aspartate aminotransferase

AKP:

Alkaline phosphatase

γ-GT:

Gamma-glutamyl transpeptidase

CRP:

C-reactive protein

OS:

Overall survival

PFS:

Progression-free survival

T2WI:

T2-weighted imaging

FSE:

Fast spin echo

TLs:

Target lesions

CR:

Complete response

PR:

Partial response

SD:

Stable disease

PD:

Progressive disease

ORR:

Objective response rate

DCR:

Disease control rate

CEL:

Cross entropy loss

SVM:

Support vector machine

AUC:

Area under the ROC curve

SEN:

Sensitivity

SPE:

Specificity

PPV:

Positive predictive value

NPV:

Negative predictive value

CAM:

Class activation mapping

IQR:

Interquartile range

NLR:

Neutrophil-lymphocyte ratio

FOV:

Field of view

UV:

Univariable

MV:

Multivariable

CI:

Confidence interval

HR:

Hazard ratio

References

  1. Asrani SK, Devarbhavi H, Eaton J, Kamath PS (2019) Burden of liver diseases in the world. J Hepatol 70:151-171

    Article  PubMed  Google Scholar 

  2. Roayaie S, Jibara G, Tabrizian P et al (2015) The role of hepatic resection in the treatment of hepatocellular cancer. Hepatology 62:440-451

    Article  CAS  PubMed  Google Scholar 

  3. Llovet JM, Ricci S, Mazzaferro V et al (2008) Sorafenib in advanced hepatocellular carcinoma. N Engl J Med 359:378-390

    Article  CAS  PubMed  Google Scholar 

  4. Kudo M, Finn RS, Qin S et al (2018) Lenvatinib versus sorafenib in first-line treatment of patients with unresectable hepatocellular carcinoma: a randomised phase 3 non-inferiority trial. Lancet 391:1163-1173

    Article  CAS  PubMed  Google Scholar 

  5. Qin S, Bi F, Gu S et al (2021) Donafenib Versus Sorafenib in First-Line Treatment of Unresectable or Metastatic Hepatocellular Carcinoma: A Randomized, Open-Label, Parallel-Controlled Phase II-III Trial. J Clin Oncol 39:3002-3011

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Finn RS, Qin S, Ikeda M et al (2020) Atezolizumab plus Bevacizumab in Unresectable Hepatocellular Carcinoma. N Engl J Med 382:1894-1905

    Article  CAS  PubMed  Google Scholar 

  7. Qin S, Kudo M, Meyer T et al (2023) Tislelizumab vs Sorafenib as First-Line Treatment for Unresectable Hepatocellular Carcinoma: A Phase 3 Randomized Clinical Trial. JAMA Oncol. https://doi.org/10.1001/jamaoncol.2023.4003

    Article  PubMed  PubMed Central  Google Scholar 

  8. Llovet JM, Real MI, Montaña X et al (2002) Arterial embolisation or chemoembolisation versus symptomatic treatment in patients with unresectable hepatocellular carcinoma: a randomised controlled trial. Lancet 359:1734-1739

    Article  PubMed  Google Scholar 

  9. Lo CM, Ngan H, Tso WK et al (2002) Randomized controlled trial of transarterial lipiodol chemoembolization for unresectable hepatocellular carcinoma. Hepatology 35:1164-1171

    Article  CAS  PubMed  Google Scholar 

  10. Pinter M, Hucke F, Graziadei I et al (2012) Advanced-stage hepatocellular carcinoma: transarterial chemoembolization versus sorafenib. Radiology 263:590-599

    Article  PubMed  Google Scholar 

  11. Ota H, Nagano H, Sakon M et al (2005) Treatment of hepatocellular carcinoma with major portal vein thrombosis by combined therapy with subcutaneous interferon-alpha and intra-arterial 5-fluorouracil; role of type 1 interferon receptor expression. Br J Cancer 93:557-564

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Yoshikawa M, Ono N, Yodono H, Ichida T, Nakamura H (2008) Phase II study of hepatic arterial infusion of a fine-powder formulation of cisplatin for advanced hepatocellular carcinoma. Hepatol Res 38:474-483

    Article  CAS  PubMed  Google Scholar 

  13. Monden M, Sakon M, Sakata Y, Ueda Y, Hashimura E (2012) 5-fluorouracil arterial infusion + interferon therapy for highly advanced hepatocellular carcinoma: A multicenter, randomized, phase II study. Hepatol Res 42:150-165

    Article  CAS  PubMed  Google Scholar 

  14. Nouso K, Miyahara K, Uchida D et al (2013) Effect of hepatic arterial infusion chemotherapy of 5-fluorouracil and cisplatin for advanced hepatocellular carcinoma in the Nationwide Survey of Primary Liver Cancer in Japan. Br J Cancer 109:1904-1907

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Ueshima K, Ogasawara S, Ikeda M et al (2020) Hepatic Arterial Infusion Chemotherapy versus Sorafenib in Patients with Advanced Hepatocellular Carcinoma. Liver Cancer 9:583-595

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Kudo M, Kawamura Y, Hasegawa K et al (2021) Management of Hepatocellular Carcinoma in Japan: JSH Consensus Statements and Recommendations 2021 Update. Liver Cancer 10:181-223

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Chen LT, Martinelli E, Cheng AL et al (2020) Pan-Asian adapted ESMO Clinical Practice Guidelines for the management of patients with intermediate and advanced/relapsed hepatocellular carcinoma: a TOS-ESMO initiative endorsed by CSCO, ISMPO, JSMO, KSMO, MOS and SSO. Ann Oncol 31:334-351

    Article  PubMed  Google Scholar 

  18. Lyu N, Kong Y, Mu L et al (2018) Hepatic arterial infusion of oxaliplatin plus fluorouracil/leucovorin vs. sorafenib for advanced hepatocellular carcinoma. J Hepatol 69:60-69

    Article  PubMed  Google Scholar 

  19. He M, Li Q, Zou R et al (2019) Sorafenib Plus Hepatic Arterial Infusion of Oxaliplatin, Fluorouracil, and Leucovorin vs Sorafenib Alone for Hepatocellular Carcinoma With Portal Vein Invasion: A Randomized Clinical Trial. JAMA Oncol 5:953-960

    Article  PubMed  PubMed Central  Google Scholar 

  20. Li QJ, He MK, Chen HW et al (2022) Hepatic Arterial Infusion of Oxaliplatin, Fluorouracil, and Leucovorin Versus Transarterial Chemoembolization for Large Hepatocellular Carcinoma: A Randomized Phase III Trial. J Clin Oncol 40:150-160

    Article  CAS  PubMed  Google Scholar 

  21. Zheng K, Zhu X, Fu S et al (2022) Sorafenib Plus Hepatic Arterial Infusion Chemotherapy versus Sorafenib for Hepatocellular Carcinoma with Major Portal Vein Tumor Thrombosis: A Randomized Trial. Radiology 303:455-464

    Article  PubMed  Google Scholar 

  22. Hsu SJ, Xu X, Chen MP et al (2021) Hepatic Arterial Infusion Chemotherapy with Modified FOLFOX as an Alternative Treatment Option in Advanced Hepatocellular Carcinoma Patients with Failed or Unsuitability for Transarterial Chemoembolization. Acad Radiol 28 Suppl 1:S157-s166

    Article  PubMed  Google Scholar 

  23. Hu J, Bao Q, Cao G et al (2020) Hepatic Arterial Infusion Chemotherapy Using Oxaliplatin Plus 5-Fluorouracil Versus Transarterial Chemoembolization/Embolization for the Treatment of Advanced Hepatocellular Carcinoma with Major Portal Vein Tumor Thrombosis. Cardiovasc Intervent Radiol 43:996-1005

    Article  PubMed  Google Scholar 

  24. Liu J, Zhang J, Wang Y, Shu G, Lou C, Du Z (2022) HAIC versus TACE for patients with unresectable hepatocellular carcinoma: A systematic review and meta-analysis. Medicine (Baltimore) 101:e32390

    Article  CAS  PubMed  Google Scholar 

  25. He X, Li K, Wei R et al (2023) A multitask deep learning radiomics model for predicting the macrotrabecular-massive subtype and prognosis of hepatocellular carcinoma after hepatic arterial infusion chemotherapy. Radiol Med. https://doi.org/10.1007/s11547-023-01719-1

    Article  PubMed  PubMed Central  Google Scholar 

  26. Xu Z, An C, Shi F et al (2023) Automatic prediction of hepatic arterial infusion chemotherapy response in advanced hepatocellular carcinoma with deep learning radiomic nomogram. Eur Radiol. https://doi.org/10.1007/s00330-023-09953-x

    Article  PubMed  PubMed Central  Google Scholar 

  27. Zhao Y, Huang F, Liu S et al (2023) Prediction of therapeutic response of unresectable hepatocellular carcinoma to hepatic arterial infusion chemotherapy based on pretherapeutic MRI radiomics and Albumin-Bilirubin score. J Cancer Res Clin Oncol 149:5181-5192

    Article  CAS  PubMed  Google Scholar 

  28. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500-510

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  29. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436-444

    Article  ADS  CAS  PubMed  Google Scholar 

  30. Huang H, Hu X, Zhao Y et al (2018) Modeling Task fMRI Data Via Deep Convolutional Autoencoder. IEEE Trans Med Imaging 37:1551-1561

    Article  PubMed  Google Scholar 

  31. Eisenhauer EA, Therasse P, Bogaerts J et al (2009) New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). Eur J Cancer 45:228-247

    Article  CAS  PubMed  Google Scholar 

  32. Bartkowski R, Berger MR, Aguiar JL et al (1986) Experiments on the efficacy and toxicity of locoregional chemotherapy of liver tumors with 5-fluoro-2’-deoxyuridine (FUDR) and 5-fluorouracil (5-FU) in an animal model. J Cancer Res Clin Oncol 111:42-46

    Article  CAS  PubMed  Google Scholar 

  33. Obi S, Sato S, Kawai T (2015) Current Status of Hepatic Arterial Infusion Chemotherapy. Liver Cancer 4:188-199

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  34. Park HJ, Kim JH, Choi SY et al (2017) Prediction of Therapeutic Response of Hepatocellular Carcinoma to Transcatheter Arterial Chemoembolization Based on Pretherapeutic Dynamic CT and Textural Findings. AJR Am J Roentgenol 209:W211-w220

    Article  PubMed  Google Scholar 

  35. Liu J, Pei Y, Zhang Y, Wu Y, Liu F, Gu S (2021) Predicting the prognosis of hepatocellular carcinoma with the treatment of transcatheter arterial chemoembolization combined with microwave ablation using pretreatment MR imaging texture features. Abdom Radiol (NY) 46:3748-3757

    Article  PubMed  Google Scholar 

  36. Miyaki D, Kawaoka T, Aikata H et al (2015) Evaluation of early response to hepatic arterial infusion chemotherapy in patients with advanced hepatocellular carcinoma using the combination of response evaluation criteria in solid tumors and tumor markers. J Gastroenterol Hepatol 30:726-732

    Article  CAS  PubMed  Google Scholar 

  37. Lyu N, Kong Y, Pan T et al (2019) Hepatic Arterial Infusion of Oxaliplatin, Fluorouracil, and Leucovorin in Hepatocellular Cancer with Extrahepatic Spread. J Vasc Interv Radiol 30:349-357.e342

    Article  ADS  PubMed  Google Scholar 

  38. Golub TR, Slonim DK, Tamayo P et al (1999) Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science 286:531-537

    Article  CAS  PubMed  Google Scholar 

  39. Liu B, Zeng Q, Huang J et al (2022) IVIM using convolutional neural networks predicts microvascular invasion in HCC. Eur Radiol 32:7185-7195

    Article  PubMed  Google Scholar 

  40. Kudo M, Ueshima K, Yokosuka O et al (2018) Sorafenib plus low-dose cisplatin and fluorouracil hepatic arterial infusion chemotherapy versus sorafenib alone in patients with advanced hepatocellular carcinoma (SILIUS): a randomised, open label, phase 3 trial. Lancet Gastroenterol Hepatol 3:424-432

    Article  PubMed  Google Scholar 

Download references

Funding

Funding for the study was provided by the National Natural Science Foundation of China (No. 81972889, Dr Yin; No. 81802320, Dr Li).

Author information

Authors and Affiliations

  1. Liver Cancer Institute, Zhongshan Hospital, Fudan University, Shanghai, 200032, China

    Bing Quan, Jinghuan Li, Miao Li, Wenfeng Liu, Fan Yao, Rongxin Chen, Zhenggang Ren & Xin Yin

  2. National Clinical Research Center for Interventional Medicine, Shanghai, 200032, China

    Bing Quan, Jinghuan Li, Miao Li, Wenfeng Liu, Fan Yao, Rongxin Chen, Zhenggang Ren & Xin Yin

  3. Department of Radiology, Zhongshan Hospital, Fudan University, 136 Yi Xue Yuan Road, Shanghai, 200032, China

    Yan Shan & Pengju Xu

  4. Department of Computer Science and Technology, Harbin Engineering University, Harbin, China

    Hailin Mi

Authors
  1. Bing Quan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jinghuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hailin Mi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Miao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Wenfeng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Fan Yao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Rongxin Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Yan Shan
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Pengju Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Zhenggang Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Xin Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Bing Quan, Jinghuan Li and Hailin Mi contributed to this work equally. Bing Quan: writing — original draft (lead). Jinghuan Li: methodology (lead). Hailin Mi: software (lead); validation (lead). Miao Li, Wenfeng Liu, Fan Yao: data curation (equal); Yan Shan, Pengju Xu: investigation (equal); visualization (equal). Zhenggang Ren, Xin Yin: conceptualization (lead); writing — review and editing (lead).

Corresponding author

Correspondence to Xin Yin.

Ethics declarations

Ethics Approval

Institutional Review Board approval was obtained.

Consent to Participate

Informed consent was obtained from all individual participants included in the study.

Consent for Publication

The authors affirm that human research participants provided informed consent for publication of the information in this study.

Competing Interests

The authors declare no competing interests.

Additional information

Publisher's Note

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

Key Points

Treatment response prediction of HCC patients after HAIC can be reliably diagnosed by CNN.

Jinghuan Li and Hailin Mi are co-first author.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 744 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Quan, B., Li, J., Mi, H. et al. Development and Preliminary Validation of a Novel Convolutional Neural Network Model for Predicting Treatment Response in Patients with Unresectable Hepatocellular Carcinoma Receiving Hepatic Arterial Infusion Chemotherapy. J Digit Imaging. Inform. med. (2024). https://doi.org/10.1007/s10278-024-01003-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10278-024-01003-2

Keywords

Search

Navigation