Skip to main content

Advertisement

SpringerLink
Log in

Automated identification and quantification of metastatic brain tumors and perilesional edema based on a deep learning neural network

  • Research
  • Published:
Journal of Neuro-Oncology Aims and scope Submit manuscript

Abstract

Purpose

This paper presents a deep learning model for use in the automated segmentation of metastatic brain tumors and associated perilesional edema.

Methods

The model was trained using Gamma Knife surgical data (90 MRI sets from 46 patients), including the initial treatment plan and follow-up images (T1-weighted contrast-enhanced (T1cWI) and T2-weighted images (T2WI)) manually annotated by neurosurgeons to indicate the target tumor and edema regions. A mask region-based convolutional neural network was used to extract brain parenchyma, after which the DeepMedic 3D convolutional neural network was in the segmentation of tumors and edemas.

Results

Five-fold cross-validation demonstrated the efficacy of the brain parenchyma extraction model, achieving a Dice similarity coefficient of 96.4%. The segmentation models used for metastatic tumors and brain edema achieved Dice similarity coefficients of 71.6% and 85.1%, respectively. This study also presents an intuitive graphical user interface to facilitate the use of these models in clinical analysis.

Conclusion

This paper introduces a deep learning model for the automated segmentation and quantification of brain metastatic tumors and perilesional edema trained using only T1cWI and T2WI. This technique could facilitate further research on metastatic tumors and perilesional edema as well as other intracranial 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

Similar content being viewed by others

Data availability

The datasets generated and/or analyzed during the current study are not publicly available, but they are available from the corresponding author on reasonable request. Note that all data was anonymized during the data evaluation process.

References

  1. Fox BD, Cheung VJ, Patel AJ, Suki D, Rao G (2011) Epidemiology of metastatic brain tumors. Neurosurg Clin N Am 22:1–6. https://doi.org/10.1016/j.nec.2010.08.007

    Article  PubMed  Google Scholar 

  2. Soffietti R, Rudā R, Mutani R (2002) Management of brain metastases. J Neurol 249:1357–1369. https://doi.org/10.1007/s00415-002-0870-6

    Article  PubMed  Google Scholar 

  3. Senger DR, Van de Water L, Brown LF, Nagy JA, Yeo KT, Yeo TK, Berse B, Jackman RW, Dvorak AM, Dvorak HF (1993) Vascular permeability factor (VPF, VEGF) in Tumor biology. Cancer Metastasis Rev 12:303–324. https://doi.org/10.1007/bf00665960

    Article  PubMed  CAS  Google Scholar 

  4. Wick W, Küker W (2004) Brain edema in neurooncology: radiological assessment and management. Onkologie 27:261–266. https://doi.org/10.1159/000077976

    Article  PubMed  CAS  Google Scholar 

  5. Tran TT, Jilaveanu LB, Omuro A, Chiang VL, Huttner A, Kluger HM (2019) Complications associated with immunotherapy for brain metastases. Curr Opin Neurol 32:907–916. https://doi.org/10.1097/wco.0000000000000756

    Article  PubMed  PubMed Central  Google Scholar 

  6. Jha RM, Raikwar SP, Mihaljevic S, Casabella AM, Catapano JS, Rani A, Desai S, Gerzanich V, Simard JM (2021) Emerging therapeutic targets for cerebral edema. Expert Opin Ther Targets 25:917–938. https://doi.org/10.1080/14728222.2021.2010045

    Article  PubMed  CAS  Google Scholar 

  7. Chou CJ, Lee CC, Chen CJ, Yang HC, Peng SJ (2021) Displacement of Gray Matter and Incidence of Seizures in patients with cerebral cavernous malformations. Biomedicines 9 https://doi.org/10.3390/biomedicines9121872

  8. He K, Gkioxari G, Dollar P, Girshick R (2020) Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 42:386–397. https://doi.org/10.1109/tpami.2018.2844175

    Article  PubMed  Google Scholar 

  9. Kamnitsas K, Ledig C, Newcombe VFJ, Simpson JP, Kane AD, Menon DK, Rueckert D, Glocker B (2017) Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78. https://doi.org/10.1016/j.media.2016.10.004

    Article  PubMed  Google Scholar 

  10. Saha BN, Ray N, Greiner R, Murtha A, Zhang H (2012) Quick detection of brain tumors and edemas: a bounding box method using symmetry. Comput Med Imaging Graph 36:95–107. https://doi.org/10.1016/j.compmedimag.2011.06.001

    Article  PubMed  Google Scholar 

  11. Njeh I, Sallemi L, Ayed IB, Chtourou K, Lehericy S, Galanaud D, Hamida AB (2015) 3D multimodal MRI brain glioma Tumor and edema segmentation: a graph cut distribution matching approach. Comput Med Imaging Graph 40:108–119. https://doi.org/10.1016/j.compmedimag.2014.10.009

    Article  PubMed  Google Scholar 

  12. Zhang C, Shen X, Cheng H, Qian Q (2019) Brain Tumor Segmentation Based on Hybrid Clustering and Morphological Operations. Int J Biomed Imaging 2019: 7305832. https://doi.org/10.1155/2019/7305832

  13. Demirhan A, Toru M, Guler I (2015) Segmentation of Tumor and edema along with healthy tissues of brain using wavelets and neural networks. IEEE J Biomed Health Inform 19:1451–1458. https://doi.org/10.1109/jbhi.2014.2360515

    Article  PubMed  Google Scholar 

  14. Pennig L, Shahzad R, Caldeira L, Lennartz S, Thiele F, Goertz L, Zopfs D, Meißner AK, Fürtjes G, Perkuhn M, Kabbasch C, Grau S, Borggrefe J, Laukamp KR (2021) Automated detection and segmentation of Brain metastases in Malignant Melanoma: evaluation of a dedicated Deep Learning Model. AJNR Am J Neuroradiol 42:655–662. https://doi.org/10.3174/ajnr.A6982

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  15. Garde E, Mortensen EL, Krabbe K, Rostrup E, Larsson HB (2000) Relation between age-related decline in intelligence and cerebral white-matter hyperintensities in healthy octogenarians: a longitudinal study. Lancet 356:628–634. https://doi.org/10.1016/s0140-6736(00)02604-0

    Article  PubMed  CAS  Google Scholar 

  16. Haller S, Kövari E, Herrmann FR, Cuvinciuc V, Tomm AM, Zulian GB, Lovblad KO, Giannakopoulos P, Bouras C (2013) Do brain T2/FLAIR white matter hyperintensities correspond to myelin loss in normal aging? A radiologic-neuropathologic correlation study. Acta Neuropathol Commun 1:14. https://doi.org/10.1186/2051-5960-1-14

    Article  PubMed  PubMed Central  Google Scholar 

  17. Kerschbaumer J, Bauer M, Popovscaia M, Grams AE, Thomé C, Freyschlag CF (2017) Correlation of Tumor and Peritumoral Edema Volumes with survival in patients with cerebral metastases. Anticancer Res 37:871–875. https://doi.org/10.21873/anticanres.11392

    Article  PubMed  Google Scholar 

  18. Pan HC, Sun MH, Chen CC, Chen CJ, Lee CH, Sheehan J (2008) Neuroimaging and quality-of-life outcomes in patients with brain Metastasis and peritumoral edema who undergo Gamma Knife Surgery. J Neurosurg 109 Suppl:90–98. https://doi.org/10.3171/jns/2008/109/12/s15

    Article  PubMed  Google Scholar 

  19. Fábián K, Gyulai M, Furák J, Várallyay P, Jäckel M, Bogos K, Döme B, Pápay J, Tímár J, Szállási Z, Moldvay J (2016) Significance of primary Tumor Location and Histology for Brain Metastasis Development and Peritumoral Brain Edema in Lung Cancer. Oncology 91:237–242. https://doi.org/10.1159/000447517

    Article  PubMed  Google Scholar 

  20. Yaltirik Bilgin E, Unal O, Ciledag N (2022) Vasogenic Edema Pattern in Brain Metastasis. J Coll Physicians Surg Pak 32:1020–1025. https://doi.org/10.29271/jcpsp.2022.08.1020

    Article  PubMed  Google Scholar 

  21. Tini P, Nardone V, Pastina P, Battaglia G, Vinciguerra C, Carfagno T, Rubino G, Carbone SF, Sebaste L, Cerase A, Federico A, Pirtoli L (2017) Perilesional edema in brain Metastasis from non-small cell Lung cancer (NSCLC) as predictor of response to radiosurgery (SRS). Neurol Sci 38:975–982. https://doi.org/10.1007/s10072-017-2876-y

    Article  PubMed  Google Scholar 

  22. Meyer HJ, Hamerla G, Höhn AK, Hoffmann KT, Surov A (2021) Perifocal edema volume is not associated with immunohistochemical features reflecting proliferation potential, microvessel density, neoangiogenesis and invasiveness in brain Metastasis. Clin Neurol Neurosurg 202:106537. https://doi.org/10.1016/j.clineuro.2021.106537

    Article  PubMed  Google Scholar 

Download references

Funding

This work was financially supported in part by the National Science and Technology Council, Taiwan, under the project NSTC 112-2628-E-038-001-MY3, and in part by the Higher Education Sprout Project by the Ministry of Education (MOE), Taiwan. We thank the National Center for High-performance Computing (NCHC) of National Applied Research Laboratories (NARLabs) in Taiwan for providing computational and storage resources.

Author information

Authors and Affiliations

  1. Division of Neurosurgery, Department of Surgery, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan

    Chi-Jen Chou

  2. School of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Hsinchu, Taiwan

    Huai-Che Yang, Hsiu-Mei Wu & I-Chun Lai

  3. Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan

    Huai-Che Yang & Chun-Fu Lin

  4. Department of Electrical Engineering, National Central University, Taoyuan, Taiwan

    Po-Yao Chang

  5. Department of Neurological Surgery, University of Virginia Health System, Charlottesville, VA, 22903, USA

    Ching-Jen Chen

  6. Department of Radiology, Taipei Veterans General Hospital, Taipei, Taiwan

    Hsiu-Mei Wu

  7. Department of Heavy Particles & Radiation Oncology, Taipei Veterans General Hospital, Taipei, Taiwan

    I-Chun Lai

  8. Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, No.250, Wuxing St., Xinyi Dist., Taipei City, 110, Taiwan

    Syu-Jyun Peng

  9. Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei Medical University, Taipei, Taiwan

    Syu-Jyun Peng

Authors
  1. Chi-Jen Chou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Huai-Che Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Po-Yao Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ching-Jen Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hsiu-Mei Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chun-Fu Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. I-Chun Lai
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Syu-Jyun Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, supervision, and project administration were performed by Chi-Jen Chou and Syu-Jyun Peng. The original draft was written by Chi-Jen Chou and Syu-Jyun Peng and all authors commented on previous versions of the manuscript. Data curation, formal analysis, software and methodology selection were performed by Chi-Jen Chou, Huai-Che Yang, Po-Yao Chang, and Syu-Jyun Peng. Investigation, data sourcing, and visualization were performed by Chi-Jen Chou, Huai-Che Yang, Ching-Jen Chen, Hsiu-Mei Wu, Chun-Fu Lin, I-Chun Lai, and Syu-Jyun Peng. All authorshave read and approved the final manuscript.

Corresponding author

Correspondence to Syu-Jyun Peng.

Ethics declarations

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.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary figures

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

Chou, CJ., Yang, HC., Chang, PY. et al. Automated identification and quantification of metastatic brain tumors and perilesional edema based on a deep learning neural network. J Neurooncol 166, 167–174 (2024). https://doi.org/10.1007/s11060-023-04540-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11060-023-04540-y

Keywords

Search

Navigation