Skip to main content
SpringerLink
Log in

Semiautomated segmentation of hepatocellular carcinoma tumors with MRI using convolutional neural networks

  • Magnetic Resonance
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

To assess the performance of convolutional neural networks (CNNs) for semiautomated segmentation of hepatocellular carcinoma (HCC) tumors on MRI.

Methods

This retrospective single-center study included 292 patients (237 M/55F, mean age 61 years) with pathologically confirmed HCC between 08/2015 and 06/2019 and who underwent MRI before surgery. The dataset was randomly divided into training (n = 195), validation (n = 66), and test sets (n = 31). Volumes of interest (VOIs) were manually placed on index lesions by 3 independent radiologists on different sequences (T2-weighted imaging [WI], T1WI pre-and post-contrast on arterial [AP], portal venous [PVP], delayed [DP, 3 min post-contrast] and hepatobiliary phases [HBP, when using gadoxetate], and diffusion-weighted imaging [DWI]). Manual segmentation was used as ground truth to train and validate a CNN-based pipeline. For semiautomated segmentation of tumors, we selected a random pixel inside the VOI, and the CNN provided two outputs: single slice and volumetric outputs. Segmentation performance and inter-observer agreement were analyzed using the 3D Dice similarity coefficient (DSC).

Results

A total of 261 HCCs were segmented on the training/validation sets, and 31 on the test set. The median lesion size was 3.0 cm (IQR 2.0–5.2 cm). Mean DSC (test set) varied depending on the MRI sequence with a range between 0.442 (ADC) and 0.778 (high b-value DWI) for single-slice segmentation; and between 0.305 (ADC) and 0.667 (T1WI pre) for volumetric-segmentation. Comparison between the two models showed better performance in single-slice segmentation, with statistical significance on T2WI, T1WI-PVP, DWI, and ADC. Inter-observer reproducibility of segmentation analysis showed a mean DSC of 0.71 in lesions between 1 and 2 cm, 0.85 in lesions between 2 and 5 cm, and 0.82 in lesions > 5 cm.

Conclusion

CNN models have fair to good performance for semiautomated HCC segmentation, depending on the sequence and tumor size, with better performance for the single-slice approach. Refinement of volumetric approaches is needed in future studies.

Key Points

• Semiautomated single-slice and volumetric segmentation using convolutional neural networks (CNNs) models provided fair to good performance for hepatocellular carcinoma segmentation on MRI.

• CNN models’ performance for HCC segmentation accuracy depends on the MRI sequence and tumor size, with the best results on diffusion-weighted imaging and T1-weighted imaging pre-contrast, and for larger lesions.

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

Abbreviations

ADC:

Apparent diffusion coefficient

AI:

Artificial intelligence

AP:

Arterial phase

CNN:

Convolutional neural network

CT:

Computed tomography

DL:

Deep learning

DP:

Delayed phase

DSC:

Dice similarity coefficient

DWI:

Diffusion-weighted imaging

HBP:

Hepatobiliary phase

HCC:

Hepatocellular carcinoma

LI-RADS:

Liver Imaging Reporting and Data System

MRI:

Magnetic resonance imaging

PVP:

Portal venous phase

T1WI:

T1-weighted imaging

T2WI:

T2-weighted imaging

VOI:

Volume of interest

References

  1. Vietti Violi N, Lewis S, Hectors S, Said D, Taouli B (2019) Radiological diagnosis and characterization of HCC. In: Hoshida Y, (ed) Hepatocellular carcinoma: translational precision medicine approaches, Cham (CH), pp 71–92

  2. Cunha GM, Sirlin CB, Fowler KJ (2021) Imaging diagnosis of hepatocellular carcinoma: LI-RADS. Chin Clin Oncol 10:3

    Article  PubMed  Google Scholar 

  3. Gordic S, Corcuera-Solano I, Stueck A et al (2017) Evaluation of HCC response to locoregional therapy: validation of MRI-based response criteria versus explant pathology. J Hepatol 67:1213–1221

    Article  PubMed  Google Scholar 

  4. Llovet JM, Lencioni R (2020) mRECIST for HCC: performance and novel refinements. J Hepatol 72:288–306

    Article  PubMed  Google Scholar 

  5. Forner A, Ayuso C, Varela M et al (2009) Evaluation of tumor response after locoregional therapies in hepatocellular carcinoma: are response evaluation criteria in solid tumors reliable? Cancer 115:616–623

    Article  PubMed  Google Scholar 

  6. Suzuki C, Torkzad MR, Jacobsson H et al (2010) Interobserver and intraobserver variability in the response evaluation of cancer therapy according to RECIST and WHO-criteria. Acta Oncol 49:509–514

    Article  PubMed  Google Scholar 

  7. Sohaib SA, Turner B, Hanson JA, Farquharson M, Oliver RT, Reznek RH (2000) CT assessment of tumour response to treatment: comparison of linear, cross-sectional and volumetric measures of tumour size. Br J Radiol 73:1178–1184

    Article  CAS  PubMed  Google Scholar 

  8. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577

    Article  PubMed  Google Scholar 

  9. Nougaret S, Vargas HA, Lakhman Y et al (2016) Intravoxel incoherent motion-derived histogram metrics for assessment of response after combined chemotherapy and radiation therapy in rectal cancer: initial experience and comparison between single-section and volumetric analyses. Radiology 280:446–454

    Article  PubMed  Google Scholar 

  10. van Heeswijk MM, Lambregts DM, van Griethuysen JJ et al (2016) Automated and semiautomated segmentation of rectal tumor volumes on diffusion-weighted MRI: can it replace manual volumetry? Int J Radiat Oncol Biol Phys 94:824–831

    Article  PubMed  Google Scholar 

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

    Article  CAS  PubMed  Google Scholar 

  12. Becker AS, Marcon M, Ghafoor S, Wurnig MC, Frauenfelder T, Boss A (2017) Deep learning in mammography: diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer. Invest Radiol 52:434–440

    Article  PubMed  Google Scholar 

  13. Drozdzal M, Chartrand G, Vorontsov E et al (2018) Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 44:1–13

    Article  PubMed  Google Scholar 

  14. Trebeschi S, van Griethuysen JJM, Lambregts DMJ et al (2017) Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR. Sci Rep 7:5301

    Article  PubMed  PubMed Central  Google Scholar 

  15. Vorontsov E, Cerny M, Régnier P et al (2019) Deep learning for automated segmentation of liver lesions at CT in patients with colorectal cancer liver metastases. Radiol Artif Intell 1:180014

    Article  PubMed  PubMed Central  Google Scholar 

  16. Isensee F, Petersen J, Klein A et al (2018) nnu-net: self-adapting framework for u-net-based medical image segmentation. arXiv preprint arXiv:180910486

  17. Hu P, Wu F, Peng J, Liang P, Kong D (2016) Automatic 3D liver segmentation based on deep learning and globally optimized surface evolution. Phys Med Biol 61:8676–8698

    Article  PubMed  Google Scholar 

  18. Lu F, Wu F, Hu P, Peng Z, Kong D (2017) Automatic 3D liver location and segmentation via convolutional neural network and graph cut. Int J Comput Assist Radiol Surg 12:171–182

    Article  PubMed  Google Scholar 

  19. van Gastel MDA, Edwards ME, Torres VE, Erickson BJ, Gansevoort RT, Kline TL (2019) Automatic Measurement of kidney and liver volumes from mr images of patients affected by autosomal dominant polycystic kidney disease. J Am Soc Nephrol 30:1514–1522

    Article  PubMed  PubMed Central  Google Scholar 

  20. Wang K, Mamidipalli A, Retson T et al (2019) Automated CT and MRI liver segmentation and biometry using a generalized convolutional neural network. Radiol Artif Intell 1:180022

  21. Yasaka K, Akai H, Kunimatsu A, Abe O, Kiryu S (2018) Liver fibrosis: deep convolutional neural network for staging by using gadoxetic acid-enhanced hepatobiliary Phase MR images. Radiology 287:146–155

    Article  PubMed  Google Scholar 

  22. Choi KJ, Jang JK, Lee SS et al (2018) Development and validation of a deep learning system for staging liver fibrosis by using contrast agent-enhanced CT images in the liver. Radiology 289:688–697

    Article  PubMed  Google Scholar 

  23. 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

    Article  CAS  PubMed  Google Scholar 

  24. Bousabarah K, Letzen B, Tefera J et al (2020) Automated detection and delineation of hepatocellular carcinoma on multiphasic contrast-enhanced MRI using deep learning. Abdom Radiol (NY). https://doi.org/10.1007/s00261-020-02604-5

    Article  PubMed  Google Scholar 

  25. Yasaka K, Akai H, Abe O, Kiryu S (2018) Deep learning with convolutional neural network for differentiation of liver masses at dynamic contrast-enhanced CT: a preliminary study. Radiology 286:887–896

    Article  PubMed  Google Scholar 

  26. Hamm CA, Wang CJ, Savic LJ et al (2019) Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI. Eur Radiol. https://doi.org/10.1007/s00330-019-06205-9

    Article  PubMed  PubMed Central  Google Scholar 

  27. Chartrand G, Cheng PM, Vorontsov E et al (2017) Deep learning: a primer for radiologists. Radiographics 37:2113–2131

    Article  PubMed  Google Scholar 

  28. Li X, Morgan PS, Ashburner J, Smith J, Rorden C (2016) The first step for neuroimaging data analysis: DICOM to NIfTI conversion. J Neurosci Methods 264:47–56

    Article  PubMed  Google Scholar 

  29. Tustison NJ, Avants BB, Cook PA et al (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29:1310–1320

    Article  PubMed  PubMed Central  Google Scholar 

  30. Chernyak V, Fowler KJ, Kamaya A et al (2018) Liver Imaging Reporting and Data System (LI-RADS) version 2018: imaging of hepatocellular carcinoma in at-risk patients. Radiology 289:816–830

    Article  PubMed  Google Scholar 

  31. Zunair H, Ben Hamza A (2021) Sharp U-Net: depthwise convolutional network for biomedical image segmentation. Comput Biol Med 136:104699

    Article  PubMed  Google Scholar 

  32. Lowekamp BC, Chen DT, Ibanez L, Blezek D (2013) The Design of SimpleITK. Front Neuroinform 7:45

    Article  PubMed  PubMed Central  Google Scholar 

  33. Besa C, Kakite S, Cooper N, Facciuto M, Taouli B (2015) Comparison of gadoxetic acid and gadopentetate dimeglumine-enhanced MRI for HCC detection: prospective crossover study at 3 T. Acta Radiologica Open 4:2047981614561285

    Article  PubMed  PubMed Central  Google Scholar 

  34. ViettiVioli N, Argiriadi P, Rosen A et al (2020) Gadoxetate disodium-enhanced MRI: Assessment of arterial phase artifacts and hepatobiliary uptake in a large series. Eur J Radiol 132:109313

    Article  Google Scholar 

  35. Brismar TB, Dahlstrom N, Edsborg N, Persson A, Smedby O, Albiin N (2009) Liver vessel enhancement by Gd-BOPTA and Gd-EOB-DTPA: a comparison in healthy volunteers. Acta Radiol 50:709–715

    Article  CAS  PubMed  Google Scholar 

  36. Tamada T, Ito K, Sone T et al (2009) Dynamic contrast-enhanced magnetic resonance imaging of abdominal solid organ and major vessel: comparison of enhancement effect between Gd-EOB-DTPA and Gd-DTPA. J Magn Reson Imaging 29:636–640

    Article  PubMed  Google Scholar 

  37. Vorontsov E, Cerny M, Regnier P et al (2019) Deep learning for automated segmentation of liver lesions at CT in patients with colorectal cancer liver metastases. Radiol Artif Intell 1:180014

    Article  PubMed  PubMed Central  Google Scholar 

  38. Ouhmich F, Agnus V, Noblet V, Heitz F, Pessaux P (2019) Liver tissue segmentation in multiphase CT scans using cascaded convolutional neural networks. Int J Comput Assist Radiol Surg 14:1275–1284

    Article  PubMed  Google Scholar 

  39. Lewis S, Hectors S, Taouli B (2021) Radiomics of hepatocellular carcinoma. Abdom Radiol (NY) 46:111–123

    Article  PubMed  Google Scholar 

  40. Said D, Hectors SJ, Wilck E et al (2020) Characterization of solid renal neoplasms using MRI-based quantitative radiomics features. Abdom Radiol (NY) 45:2840–2850

    Article  PubMed  Google Scholar 

Download references

Funding

This work was partially funded by Owkin Inc.

Author information

Author notes

  1. Daniela Said and Guillermo Carbonell are equal contributors.

Authors and Affiliations

  1. BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, NY, USA

    Daniela Said, Guillermo Carbonell, Daniel Stocker, Stefanie Hectors, Octavia Bane, Xing Chin, Myron Schwartz, Parissa Tabrizian, Sara Lewis, Hayit Greenspan & Bachir Taouli

  2. Department of Radiology, Clínica Universidad de los Andes, Santiago, Chile

    Daniela Said

  3. Department of Radiology, University Hospital Virgen de La Arrixaca, Murcia, Spain

    Guillermo Carbonell

  4. Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, Zurich, Switzerland

    Daniel Stocker

  5. Department of Radiology, Lausanne University Hospital, Lausanne, Switzerland

    Naik Vietti-Violi

  6. Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY, 10029, USA

    Sara Lewis & Bachir Taouli

  7. Owkin, Paris, France

    Simon Jégou, Jean-Baptiste Schiratti & Paul Jehanno

Authors
  1. Daniela Said
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guillermo Carbonell
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daniel Stocker
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Stefanie Hectors
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Naik Vietti-Violi
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Octavia Bane
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xing Chin
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Myron Schwartz
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Parissa Tabrizian
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Sara Lewis
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Hayit Greenspan
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Simon Jégou
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Jean-Baptiste Schiratti
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Paul Jehanno
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Bachir Taouli
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bachir Taouli.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Bachir Taouli.

Conflict of interest

Daniela Said: None to declare relating to this study.

Guillermo Carbonell: None to declare relating to this study.

Daniel Stocker: None to declare relating to this study.

Naik Vietti Violi: None to declare relating to this study.

Octavia Bane: None to declare relating to this study.

Xing Chin: None to declare relating to this study.

Myron Schwartz: None to declare relating to this study.

Parissa Tabrizian: None to declare relating to this study.

Sara Lewis: None to declare relating to this study.

Daniel Stocker: None to declare relating to this study.

Stefanie Hectors: Employee of Regeneron.

Hayit Greenspan: None to declare relating to this study.

Jean-Baptiste Schiratti: Employee of Owkin.

Simon Jégou: Employee of Owkin.

Paul Jehanno: Employee of Owkin.

Bachir Taouli: Consultancy and/or advisory roles for Bayer, Guerbet, and Helio Health and research funding/support from Bayer, Takeda, Regeneron, Siemens, and Echosens.

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.

Study subjects or cohorts overlap

None.

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.

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

Said, D., Carbonell, G., Stocker, D. et al. Semiautomated segmentation of hepatocellular carcinoma tumors with MRI using convolutional neural networks. Eur Radiol 33, 6020–6032 (2023). https://doi.org/10.1007/s00330-023-09613-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09613-0

Keywords

Search

Navigation