Abstract
Gliomas are the most common primary malignant tumors of the brain caused by glial cell canceration of the brain and spinal cord. Its incidence accounts for the vast majority of intracranial tumors and has the characteristics of high incidence, high recurrence rate, high mortality, and low cure rate. Gliomas are graded into I to IV by the World Health Organization (WHO) and the treatment is highly dependent on the grade. Diagnosis and classification of brain tumors are traditionally done by pathologists, who examine tissue sections fixed on glass slides under a light microscope. This process is time-consuming and labor-intensive and does not necessarily lead to perfectly accurate results. The computer-aided method has the potential to improve tumor classification process. In this paper, we proposed two convolutional neural networks based models to predict the grade of gliomas from both radiology and pathology data. (1) 2D ResNet-based model for pathology whole slide image classification. (2) 3D DenseNet-based model for multimodal MRI images classification. Finally, we achieve first place in CPM-RadPath-2019 [1] challenge using these methods for the tasks of classifying lower grade astrocytoma (grade II or III), oligodendroglioma (grade II or III) and glioblastoma (grade IV).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Computational precision medicine: Radiology-pathology challenge on brain tumor classification 2019, CBICA. https://www.med.upenn.edu/cbica/cpm2019.html
Multimodal brain tumor segmentation challenge 2018. CBICA. https://www.med.upenn.edu/sbia/brats2018/evaluation.html
Buitinck, L., et al.: API design for machine learning software: experiences from the SCIKIT-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108–122 (2013)
Chen, Q., Wang, L., Wang, L., Deng, Z., Zhang, J., Zhu, Y.: Glioma grade predictions using scattering wavelet transform-based radiomics (2019)
Citak-Er, F., Firat, Z., Kovanlikaya, I., Ture, U., Ozturk-Isik, E.: Machine-learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3T. Comput. Biol. Med. 99, 154–160 (2018)
Decuyper, M., Van Holen, R.: Fully automatic binary glioma grading based on pre-therapy MRI using 3D convolutional neural networks (2019)
Ertosun, M.G., Rubin, D.L.: Automated grading of gliomas using deep learning in digital pathology images: a modular approach with ensemble of convolutional neural networks. In: AMIA Annual Symposium Proceedings, vol. 2015, p. 1899. American Medical Informatics Association (2015)
Goode, A., Gilbert, B., Harkes, J., Jukic, D., Satyanarayanan, M.: Openslide: a vendor-neutral software foundation for digital pathology. J. Pathol. Inform. 4, 27 (2013)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 (2016). http://arxiv.org/abs/1608.06993
Paszke, A., et al.: Automatic differentiation in pytorch (2017)
Tellez, D., et al.: Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology. CoRR abs/1902.06543 (2019). http://arxiv.org/abs/1902.06543
Wang, X., et al.: Machine learning models for multiparametric glioma grading with quantitative result interpretations. Front. Neurosci. 12, 1046 (2018)
Yang, Y., et al.: Glioma grading on conventional MR images: a deep learning study with transfer learning. Front. Neurosci. 12, 804 (2018)
Acknowledgements
This work was supported in part by Shenzhen Key Basic Science Program (JCYJ20170413162213765 and JCYJ20180507182437217), the Shenzhen Key Laboratory Program (ZDSYS201707271637577), the NSFC-Shenzhen Union Program (U1613221), and the National Key Research and Development Program (2017YFC0110903).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, X., Jia, F. (2020). Brain Tumor Classification with Multimodal MR and Pathology Images. In: Crimi, A., Bakas, S. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2019. Lecture Notes in Computer Science(), vol 11993. Springer, Cham. https://doi.org/10.1007/978-3-030-46643-5_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-46643-5_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46642-8
Online ISBN: 978-3-030-46643-5
eBook Packages: Computer ScienceComputer Science (R0)
