Skip to main content

Advertisement

SpringerLink
Log in

Deep convolutional neural network for differentiating between sarcoidosis and lymphoma based on [18F]FDG maximum-intensity projection images

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To compare the [18F]FDG PET/CT findings of untreated sarcoidosis and malignant lymphoma (ML) and develop convolutional neural network (CNN) models to differentiate between these diseases using maximum intensity projection (MIP) [18F]FDG PET images.

Methods

We retrospectively collected data on consecutive patients newly diagnosed with sarcoidosis and ML who underwent [18F]FDG PET/CT before treatment. Two nuclear radiologists reviewed the images. CNN models were created using MIP PET images and evaluated with k-fold cross-validation. The points of interest were visualized using gradient-weighted class activation mapping (Grad-CAM).

Results

A total of 56 patients with sarcoidosis and 62 patients with ML were included. Patients with sarcoidosis had more prominent FDG accumulation in the mediastinal lymph nodes and lung lesions, while those with ML had more prominent accumulation in the cervical lymph nodes (all p < 0.001). For the mediastinal lymph nodes, sarcoidosis patients had significant FDG accumulation in the level 2, 4, 7, and 10 lymph nodes (all p < 0.01). Otherwise, the accumulation in ML patients tended to be in the level 1 lymph nodes (p = 0.08). The CNN model using frontal and lateral MIP images achieved an average accuracy of 0.890 (95% CI: 0.804–0.977), a sensitivity of 0.898 (95% CI: 0.782–1.000), a specificity of 0.907 (95% CI: 0.799–1.000), and an area under the curve of 0.963 (95% CI: 0.899–1.000). Grad-CAM showed that the model focused on the sites of abnormal FDG accumulation.

Conclusions

CNN models based on differences in FDG accumulation sites archive high performance in differentiating between sarcoidosis and ML.

Clinical relevance statement

We developed a CNN model using MIP images of [18F]FDG PET/CT to distinguish between sarcoidosis and malignant lymphoma. It achieved high performance and could be useful in diagnosing diseases with involvement across organs and lymph nodes.

Key Points

• There are differences in FDG distribution when comparing whole-body [18F]FDG PET/CT findings in patients with sarcoidosis and malignant lymphoma before treatment.

• Convolutional neural networks, a type of deep learning technique, trained with maximum-intensity projection PET images from two angles showed high performance.

• A deep learning model that utilizes differences in FDG distribution may be helpful in differentiating between diseases with lesions that are characteristically widespread among organs and lymph nodes.

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
Fig. 6

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CNN:

Convolutional neural network

DLBCL:

Diffuse large B-cell lymphoma

GLUT-1:

Glucose transporter 1 isoforms

GLUT-3:

Glucose transporter 3 isoforms

Grad-CAM:

Gradient-weighted class activation mapping

MIP:

Maximum intensity projection

ML:

Malignant lymphoma

ROC:

Receiver operating characteristic

SUVmax:

Maximum standard uptake value

References

  1. Grunewald J, Grutters JC, Arkema EV, Saketkoo LA, Moller DR, Muller-Quernheim J (2019) Sarcoidosis. Nat Rev Dis Primers 5:45

    Article  PubMed  Google Scholar 

  2. Swerdlow SH, Campo E, Pileri SA et al (2016) The 2016 revision of the World Health Organization classification of lymphoid neoplasms. Blood 127:2375–2390

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Tana M, di Carlo S, Romano M, Alessandri M, Schiavone C, Montagnani A (2019) FDG-PET/CT assessment of pulmonary sarcoidosis: a guide for internists. Curr Med Imaging Rev 15:21–25

    Article  PubMed  Google Scholar 

  4. Gümüştaş S, Inan N, Akansel G, Başyïğït I, Cïftçi E (2013) Differentiation of lymphoma versus sarcoidosis in the setting of mediastinal - hilar lymphadenopathy: assessment with diffusion-weighted MR imaging. Sarcoidosis Vasc Diffuse Lung Dis 30:52–59

  5. Lale K, Harry AJ, Stantley JG (2003) Clinical role of FDG PET in evaluation of cancer patients. Radiographics 23:315–340

    Article  Google Scholar 

  6. Charito L, Maria BT, Gene GT, Christopher JP (2005) FDG PET of infection and inflammation. Radiographics 25:1357–1368

    Article  Google Scholar 

  7. Weclawek M, Ziora D, Jastrzebski D (2020) Imaging methods for pulmonary sarcoidosis. Adv Respir Med 88:18–26

    Article  PubMed  Google Scholar 

  8. Adams H, Keijsers RG, Korenromp IH, Grutters JC (2014) FDG PET for gauging of sarcoid disease activity. Semin Respir Crit Care Med 35:352–361

    Article  PubMed  Google Scholar 

  9. Khandani AH, Dunphy CH, Meteesatien P, Dufault DL, Ivanovic M, Shea TC (2009) Glut1 and Glut3 expression in lymphoma and their association with tumor intensity on 18F-fluorodeoxyglucose positron emission tomography. Nucl Med Comm 30:594–601

    Article  CAS  Google Scholar 

  10. Shetty A, Carter JD (2011) Sarcoidosis mimicking lymphoma on FDG-PET imaging. Radiol Case Rep 6:409

    Article  PubMed  Google Scholar 

  11. 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 

  12. Currie G, Rohren E (2021) Intelligent imaging in nuclear medicine: the principles of artificial intelligence, machine learning and deep learning. Semin Nucl Med 51:102–111

    Article  PubMed  Google Scholar 

  13. Sibille L, Seifert R, Avramovic N et al (2020) (18)F-FDG PET/CT uptake classification in lymphoma and lung cancer by using deep convolutional neural networks. Radiology 294:445–452

    Article  PubMed  Google Scholar 

  14. Kawauchi K, Furuya S, Hirata K et al (2020) A convolutional neural network-based system to classify patients using FDG PET/CT examinations. BMC Cancer 20:227

    Article  PubMed  PubMed Central  Google Scholar 

  15. Noriharu S, Yamaguchi T (2015) Diagnosis criteria and classification of disease severity for sarcoidosis in Japan. Jpn J Sarcoidosis Granuloma Dis 35:3–8

    Google Scholar 

  16. Tsuchiya J, Yokoyama K, Yamagiwa K et al (2021) Deep learning-based image quality improvement of (18)F-fluorodeoxyglucose positron emission tomography: a retrospective observational study. EJNMMI Phys 8:31

    Article  PubMed  PubMed Central  Google Scholar 

  17. Rusch VW, Asamura H, Watanabe H, Giroux DJ, Rami-Porta R, Goldstraw P (2009) The IASLC lung cancer staging project: a proposal for a new international lymph node map in the forthcoming seventh edition of the TNM classification for lung cancer. J Thorac Oncol 4:568-577

  18. Heo TY, Kim KM, Min HK et al (2020) Development of a deep-learning-based artificial intelligence tool for differential diagnosis between dry and neovascular age-related macular degeneration. Diagnostics (Basel) 10:216

    Google Scholar 

  19. Nalepa J, Marcinkiewicz M, Kawulok M (2019) Data augmentation for brain-tumor segmentation: a review. Front Comput Neurosci 13:83

    Article  PubMed  PubMed Central  Google Scholar 

  20. Ramprasaath RS, Michael C, Abhishek D, Ramakrishna V, Devi P, Dhruv B (2019) Grad-CAM: visual explanations from deep networks via gradient-based localization. Available at: https://doi.org/10.48550/arXiv.1610.02391. Accessed September 01, 2022

  21. Kanda Y (2013) Investigation of the freely available easy-to-use software ‘EZR’ for medical statistics. Bone Marrow Transplant 48:452–458

    Article  CAS  PubMed  Google Scholar 

  22. Diederik PK, Jimmy LB (2014) ADAM: a method for stochastic optimization. Available at: https://doi.org/10.48550/arXiv.1412.6980. Accessed September 01, 2022

  23. Takahashi K, Fujioka T, Oyama J et al (2022) Deep learning using multiple degrees of maximum-intensity projection for PET/CT image classification in breast cancer. Tomography 8:131–141

    Article  PubMed  PubMed Central  Google Scholar 

  24. Torres-Velazquez M, Chen WJ, Li X, McMillan AB (2021) Application and construction of deep learning networks in medical imaging. IEEE Trans Radiat Plasma Med Sci 5:137–159

    Article  PubMed  Google Scholar 

  25. Zhang Y, Du SS, Zhao MM et al (2022) Chest high-resolution computed tomography can make higher accurate stages for thoracic sarcoidosis than X-ray. BMC Pulm Med 22:146

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Capobianco N, Meignan M, Cottereau AS et al (2021) Deep-learning (18)F-FDG uptake classification enables total metabolic tumor volume estimation in diffuse large B-cell lymphoma. J Nucl Med 62:30–36

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Blanc-Durand P, Jegou S, Kanoun S et al (2020) Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network. Eur J Nucl Med Mol Imaging 48:1362–1370

    Article  PubMed  Google Scholar 

  28. Wang X (2015) PET/CT: appropriate application in lymphoma. Chin Clin Oncol 4:4

    PubMed  Google Scholar 

  29. Khan AB, Barrington SF, Mikhaeel NG et al (2013) PET-CT staging of DLBCL accurately identifies and provides new insight into the clinical significance of bone marrow involvement. Blood 122:61–67

    Article  CAS  PubMed  Google Scholar 

  30. Mehrian P, Ebrahimzadeh SA (2013) Differentiation between sarcoidosis and Hodgkin’s lymphoma based on mediastinal lymph node involvement pattern: evaluation using spiral CT scan. Pol J Radiol 78:15–20

    Article  PubMed  PubMed Central  Google Scholar 

  31. Santos FS, Verma N, Marchiori E et al (2021) MRI-based differentiation between lymphoma and sarcoidosis in mediastinal lymph nodes. J Bras Pneumol 47:e20200055

    Article  PubMed  PubMed Central  Google Scholar 

  32. Lovinfosse P, Ferreira M, Withofs N et al (2022) Distinction of lymphoma from sarcoidosis at FDG PET/CT - evaluation of radiomic-feature guided machine learning versus human reader performance. J Nucl Med. https://doi.org/10.2967/jnumed.121.263598

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

This study was supported by a grant to the Diffuse Lung Diseases Research Group from the Ministry of Health, Labor and Welfare, Japan (grant number 20FC1033).

Author information

Authors and Affiliations

  1. Department of Respiratory Medicine, Tokyo Medical and Dental University, 1-5-45, Yushima, Tokyo, Bunkyo-ku, 113-8510, Japan

    Hikaru Aoki, Yasunari Miyazaki, Tsuyoshi Shirai, Sho Shibata, Rie Sakakibara, Takahiro Mitsumura, Takayuki Honda, Haruhiko Furusawa, Tsukasa Okamoto, Tomoya Tateishi & Meiyo Tamaoka

  2. Department of Biostatistics, M&D Data Science Center, Tokyo Medical and Dental University, Tokyo, Japan

    Tatsuhiko Anzai & Kunihiko Takahashi

  3. Department of Diagnostic Radiology and Nuclear Medicine, Tokyo Medical and Dental University, Tokyo, Japan

    Kota Yokoyama, Junichi Tsuchiya & Ukihide Tateishi

  4. Department of Hematological Medicine, Tokyo Medical and Dental University, Tokyo, Japan

    Masahide Yamamoto

  5. Department of Human Pathology, Tokyo Medical and Dental University, Tokyo, Japan

    Tetsuo Yamaguchi

  6. Shinjuku Tsurukame Clinic, Tokyo, Japan

    Tetsuo Yamaguchi

Authors
  1. Hikaru Aoki
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yasunari Miyazaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tatsuhiko Anzai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kota Yokoyama
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junichi Tsuchiya
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Tsuyoshi Shirai
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Sho Shibata
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Rie Sakakibara
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Takahiro Mitsumura
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Takayuki Honda
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Haruhiko Furusawa
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Tsukasa Okamoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Tomoya Tateishi
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Meiyo Tamaoka
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Masahide Yamamoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Kunihiko Takahashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Ukihide Tateishi
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Tetsuo Yamaguchi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yasunari Miyazaki.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Yasunari Miyazaki.

Conflict of Interest

The authors declare no competing interests.

Statistics and Biometry

One of the authors has significant statistical expertise.

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

Not applicable.

Methodology

• retrospective

• diagnostic or prognostic study

• multicenter study

Additional information

Publisher's note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 215 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

Aoki, H., Miyazaki, Y., Anzai, T. et al. Deep convolutional neural network for differentiating between sarcoidosis and lymphoma based on [18F]FDG maximum-intensity projection images. Eur Radiol 34, 374–383 (2024). https://doi.org/10.1007/s00330-023-09937-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09937-x

Keywords

Search

Navigation