Abstract
Glioblastoma is the most common and lethal primary brain tumor in adults. Magnetic resonance imaging (MRI) is a critical diagnostic tool for glioblastoma. Besides MRI, histopathology features and molecular subtypes like MGMT methylation, IDH mutation, 1p19q co-deletion, etc. are used for prognosis. Accurate tumor segmentation is a step towards fully utilizing the MRI data for radiogenomics that will allow use of MRI to predict genomic features of glioblastoma. With accurate tumor segmentation, we can get precise quantitative information about the 3D tumor volumetric features. We have developed an inference model for brain tumor segmentation using neural network algorithm with Resnet50 as an encoding layer. Major feature of our algorithm is the use of composite image generated from T1, T2, T1ce and FLAIR series. We report average Dice scores of 0.88716 for the whole tumor, 0.79052 for the necrotic core, and 0.72760 for the contrast-enhancing tumor on the validation set of BraTS 2021 Task1 challenge. For the final unseen test data, we report average Dice scores of 0.89656 for the whole tumor, 0.83734 for the necrotic core, and 0.81162 for the contrast-enhancing tumor.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baid, U., et al.: The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and Radiogenomic classification. arXiv 2107.02314, July 2021
Bakas, G., et al.: Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Nat. Sci. Data 4(170117), 1–13 (2017)
Menze, B.H., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015)
Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection [Dataset]. Cancer Imaging Arch. (2017). https://doi.org/10.7937/K9/TCIA.2017.KLXWJJ1Q
Bakas, G., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection. Cancer Imaging Arch. (2017). https://doi.org/10.7937/K9/TCIA.2017.GJQ7R0EF
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, December 2016, pp. 770–778. IEEE Computer Society (2015)
Implementation of Segnet, FCN, UNet, PSPNet and other models in Keras. https://github.com/divamgupta/image-segmentation-keras
Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_28
Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_28
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2014-September. International Conference on Learning Representations, ICLR (2014)
Hanif, F., et al.: Glioblastoma multiforme: a review of its epidemiology and pathogenesis through clinical presentation and treatment. Asian Pac. J. Cancer Prev. 18(1), 3–9 (2017)
Mrugala, M.M.: Advances and challenges in the treatment of glioblastoma: a clinician’s perspective. Discov Med. 15(83), 221–30 (2013)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation (2016)
Chen, W., Liu, B., Peng, S., Sun, J., Qiao, X.: S3D-UNet: separable 3D U-Net for brain tumor segmentation. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11384, pp. 358–368. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11726-9_32
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shah, D., Biswas, A., Sonpatki, P., Chakravarty, S., Shah, N. (2022). Neural Network Based Brain Tumor Segmentation. In: Crimi, A., Bakas, S. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2021. Lecture Notes in Computer Science, vol 12963. Springer, Cham. https://doi.org/10.1007/978-3-031-09002-8_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-09002-8_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09001-1
Online ISBN: 978-3-031-09002-8
eBook Packages: Computer ScienceComputer Science (R0)