Skip to main content
SpringerLink
Log in

Deep learning–based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images

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

Abstract

Objectives

To demonstrate the effectiveness of automatic segmentation of diffuse large B-cell lymphoma (DLBCL) in 3D FDG-PET scans using a deep learning approach and validate its value in prognosis in an external validation cohort.

Methods

Two PET datasets were retrospectively analysed: 297 patients from a local centre for training and 117 patients from an external centre for validation. A 3D U-Net architecture was trained on patches randomly sampled within the PET images. Segmentation performance was evaluated by six metrics, including the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), sensitivity (Se), positive predictive value (PPV), Hausdorff distance 95 (HD 95), and average symmetric surface distance (ASSD). Finally, the prognostic value of predictive total metabolic tumour volume (pTMTV) was validated in real clinical applications.

Results

The mean DSC, JSC, Se, PPV, HD 95, and ASSD (with standard deviation) for the validation cohort were 0.78 ± 0.25, 0.69 ± 0.26, 0.81 ± 0.27, 0.82 ± 0.25, 24.58 ± 35.18, and 4.46 ± 8.92, respectively. The mean ground truth TMTV (gtTMTV) and pTMTV were 276.6 ± 393.5 cm3 and 301.9 ± 510.5 cm3 in the validation cohort, respectively. Perfect homogeneity in the Bland–Altman analysis and a strong positive correlation in the linear regression analysis (R2 linear = 0.874, p < 0.001) were demonstrated between gtTMTV and pTMTV. pTMTV (≥ 201.2 cm3) (PFS: HR = 3.097, p = 0.001; OS: HR = 6.601, p < 0.001) was shown to be an independent factor of PFS and OS.

Conclusions

The FCN model with a U-Net architecture can accurately segment lymphoma lesions and allow fully automatic assessment of TMTV on PET scans for DLBCL patients. Furthermore, pTMTV is an independent prognostic factor of survival in DLBCL patients.

Key Points

•The segmentation model based on a U-Net architecture shows high performance in the segmentation of DLBCL patients on FDG-PET images.

•The proposed method can provide quantitative information as a predictive TMTV for predicting the prognosis of DLBCL patients.

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

ASSD:

Average symmetric surface distance

DLBCL:

Diffuse large B-cell lymphoma

DSC:

Dice similarity coefficient

FCN:

Fully convolutional neural network

gtTMTV:

Ground truth total metabolic tumour volume

HD 95:

Hausdorff distance 95

IQR:

Interquartile range

JSC:

Jaccard similarity coefficient

NCCN-IPI:

National Comprehensive Cancer Network International Prognostic Index

OS:

Overall survival

PFS:

Progression-free survival

PPV:

Positive predictive value

pTMTV:

Predictive total metabolic tumour volume

ReLU:

Rectified linear unit

ROC:

Receiver operating characteristic

SD:

Standard deviation

Se:

Sensitivity

SUV:

Standardised uptake value

TLG:

Total lesion glycolysis

TMTV:

Total metabolic tumour volume

VOI:

Volume of interest

References

  1. Sehn LH, Salles G (2021) Diffuse large B-cell lymphoma. N Engl J Med 384:842–858

    Article  CAS  Google Scholar 

  2. Camicia R, Winkler HC, Hassa PO (2015) Novel drug targets for personalized precision medicine in relapsed/refractory diffuse large B-cell lymphoma: a comprehensive review. Mol Cancer 14:207

    Article  Google Scholar 

  3. International Non-Hodgkin’s Lymphoma Prognostic Factors Project (1993) A predictive model for aggressive non-Hodgkin’s lymphoma. N Engl J Med 329:987–994

    Article  Google Scholar 

  4. Zhou Z, Sehn LH, Rademaker AW et al (2014) An enhanced international prognostic index (NCCN-IPI) for patients with diffuse large B-cell lymphoma treated in the rituximab era. Blood 124:982–982

    CAS  Google Scholar 

  5. Ruppert AS, Dixon JG, Salles G et al (2020) International prognostic indices in diffuse large B-cell lymphoma: a comparison of IPI, R-IPI, and NCCN-IPI. Blood 135:2041–2048

    Article  CAS  Google Scholar 

  6. Sasanelli M, Meignan M, Haioun C et al (2014) Pretherapy metabolic tumour volume is an independent predictor of outcome in patients with diffuse large B-cell lymphoma. Eur J Nucl Med Mol Imaging 41:2017–2022

    Article  CAS  Google Scholar 

  7. Mikhaeel NG, Smith D, Dunn JT et al (2016) Combination of baseline metabolic tumour volume and early response on PET/CT improves progression-free survival prediction in DLBCL. Eur J Nucl Med Mol Imaging 43:1209–1219

    Article  CAS  Google Scholar 

  8. Jiang C, Teng Y, Zheng Z, Zhou Z, Xu J (2021) Value of total lesion glycolysis and cell-of-origin subtypes for prognostic stratification of diffuse large B-cell lymphoma patients. Quant Imaging Med Surg 11:2509–2520

    Article  CAS  Google Scholar 

  9. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A (eds) Medical image computing and computer-assisted intervention – MICCAI 2015. MICCAI 2015. Lecture notes in computer science, vol 9351. Springer, Cham, pp 234–241

    Google Scholar 

  10. Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH (2020) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203–211

    Article  Google Scholar 

  11. Weston AD, Korfiatis P, Kline TL et al (2019) Automated abdominal segmentation of CT scans for body composition analysis using deep learning. Radiology 290:669–679

    Article  Google Scholar 

  12. Ye Y, Cai Z, Huang B et al (2020) Fully-automated segmentation of nasopharyngeal carcinoma on dual-sequence MRI using convolutional neural networks. Front Oncol 10:166

    Article  Google Scholar 

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

    Article  CAS  Google Scholar 

  14. Blanc-Durand P, Jégou S, Kanoun S et al (2021) 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  CAS  Google Scholar 

  15. Nioche C, Orlhac F, Boughdad S et al (2018) LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78:4786–4789

    Article  CAS  Google Scholar 

  16. Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. Proc ICML 30:3

    Google Scholar 

  17. Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40:834–848

    Article  Google Scholar 

  18. Drozdzal M, Vorontsov E, Chartrand G, Kadoury S, Pal C (2016) The importance of skip connections in biomedical image segmentation. In: Carneiro G, Mateus D, Pete L (eds) Deep learning and data labeling for medical applications. Springer, Cham, pp 179–187

    Chapter  Google Scholar 

  19. Shen D, Wu G, Suk H-I (2017) Deep learning in medical image analysis. Annu Rev Biomed Eng 19:221–248

    Article  CAS  Google Scholar 

  20. Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88

    Article  Google Scholar 

  21. Zhong Z, Kim Y, Zhou L et al (2018) 3D fully convolutional networks for co-segmentation of tumors on PET-CT images. Proc IEEE Int Symp Biomed Imaging 2018:228–231

    PubMed  PubMed Central  Google Scholar 

  22. Naser MA, van Dijk LV, He R, Wahid KA, Fuller CD (2020) Tumor segmentation in patients with head and neck cancers using deep learning based-on multi-modality PET/CT images. Head Neck Tumor Segmentation 12603:85–98

    Article  Google Scholar 

  23. Zucca E, Cascione L, Ruberto T et al (2020) Prognostic models integrating quantitative parameters from baseline and interim positron emission computed tomography in patients with diffuse large B-cell lymphoma: post-hoc analysis from the SAKK38/07 clinical trial. Hematol Oncol 38:715–725

    Article  CAS  Google Scholar 

  24. Chang C-C, Cho S-F, Chuang Y-W et al (2017) Prognostic significance of total metabolic tumor volume on (18)F-fluorodeoxyglucose positron emission tomography/ computed tomography in patients with diffuse large B-cell lymphoma receiving rituximab-containing chemotherapy. Oncotarget 8:99587–99600

    Article  Google Scholar 

  25. Shagera QA, Cheon GJ, Koh Y et al (2019) Prognostic value of metabolic tumour volume on baseline 18F-FDG PET/CT in addition to NCCN-IPI in patients with diffuse large B-cell lymphoma: further stratification of the group with a high-risk NCCN-IPI. Eur J Nucl Med Mol Imaging 46:1417–1427

    Article  CAS  Google Scholar 

  26. Vercellino L, Cottereau A-S, Casasnovas O et al (2021) High total metabolic tumor volume at baseline predicts survival independent of response to therapy. Blood 135:1396–1405

    Article  Google Scholar 

  27. Zhao P, Yu T, Pan Z (2021) Prognostic value of the baseline 18F-FDG PET/CT metabolic tumour volume (MTV) and further stratification in low-intermediate (L-I) and high-intermediate (H-I) risk NCCNIPI subgroup by MTV in DLBCL MTV predict prognosis in DLBCL. Ann Nucl Med 35:24–30

    Article  CAS  Google Scholar 

  28. Meignan M, Sasanelli M, Casasnovas RO et al (2014) Metabolic tumour volumes measured at staging in lymphoma: methodological evaluation on phantom experiments and patients. Eur J Nucl Med Mol Imaging 41:1113–1122

    Article  CAS  Google Scholar 

Download references

Funding

This work was supported in part by the National Nature Science Foundation of China under grant no. 62106101. This work was also supported in part by the Natural Science Foundation of Jiangsu Province under grant no. BK20210180. This work was also supported in part by the grant from Jiangsu Provincial Key R&D Program under no. BE2020620 and BE2020723.

Author information

Authors and Affiliations

  1. Department of Nuclear Medicine, Nanjing Drum Tower Hospital, the Affiliated Hospital of Nanjing University Medical School, No. 321, Zhongshan Road, Nanjing City, 210008, Jiangsu Province, China

    Chong Jiang, Yue Teng, Zhengyang Zhou & Jian He

  2. National Institute of Healthcare Data Science at Nanjing University, Nanjing, China

    Kai Chen, Yang Gao, Junhua Wu, Kelei He & Junfeng Zhang

  3. Department of Nuclear Medicine, the First Affiliated Hospital of Nanjing Medical University, Jiangsu Province Hospital, Nanjing, China

    Chongyang Ding

  4. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

    Yang Gao

  5. Medical School of Nanjing University, Nanjing, China

    Junhua Wu, Kelei He & Junfeng Zhang

Authors
  1. Chong Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kai Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yue Teng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chongyang Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhengyang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yang Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Junhua Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jian He
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Kelei He
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Junfeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Jian He or Kelei He.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jian He.

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 and 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.

Publisher’s note

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

Chong Jiang and Kai Chen contributed to the work equally and should be regarded as co-first authors

Supplementary Information

ESM 1

(DOC 926 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, C., Chen, K., Teng, Y. et al. Deep learning–based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images. Eur Radiol 32, 4801–4812 (2022). https://doi.org/10.1007/s00330-022-08573-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-08573-1

Keywords

Search

Navigation