Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Aug;33(4):903-915.
doi: 10.1007/s10278-020-00347-9.

Deep Multi-Scale 3D Convolutional Neural Network (CNN) for MRI Gliomas Brain Tumor Classification

Hiba Mzoughi  1   2 , Ines Njeh  3   4 , Ali Wali  5 , Mohamed Ben Slima  3   6 , Ahmed BenHamida  3   5 , Chokri Mhiri  7 , Kharedine Ben Mahfoudhe  8
Affiliations

Deep Multi-Scale 3D Convolutional Neural Network (CNN) for MRI Gliomas Brain Tumor Classification

Hiba Mzoughi et al. J Digit Imaging. 2020 Aug.

Abstract

Accurate and fully automatic brain tumor grading from volumetric 3D magnetic resonance imaging (MRI) is an essential procedure in the field of medical imaging analysis for full assistance of neuroradiology during clinical diagnosis. We propose, in this paper, an efficient and fully automatic deep multi-scale three-dimensional convolutional neural network (3D CNN) architecture for glioma brain tumor classification into low-grade gliomas (LGG) and high-grade gliomas (HGG) using the whole volumetric T1-Gado MRI sequence. Based on a 3D convolutional layer and a deep network, via small kernels, the proposed architecture has the potential to merge both the local and global contextual information with reduced weights. To overcome the data heterogeneity, we proposed a preprocessing technique based on intensity normalization and adaptive contrast enhancement of MRI data. Furthermore, for an effective training of such a deep 3D network, we used a data augmentation technique. The paper studied the impact of the proposed preprocessing and data augmentation on classification accuracy.Quantitative evaluations, over the well-known benchmark (Brats-2018), attest that the proposed architecture generates the most discriminative feature map to distinguish between LG and HG gliomas compared with 2D CNN variant. The proposed approach offers promising results outperforming the recently supervised and unsupervised state-of-the-art approaches by achieving an overall accuracy of 96.49% using the validation dataset. The obtained experimental results confirm that adequate MRI's preprocessing and data augmentation could lead to an accurate classification when exploiting CNN-based approaches.

Keywords: 3D convolutional neural network (CNN); Classification; Deep learning; Gliomas; Magnetic resonance imaging (MRI).

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflict of interest.

Figures

Fig. 1
Fig. 1
Flowchart of the proposed approach for glioma brain tumor classification
Fig. 2
Fig. 2
Preprocessing steps
Fig. 3
Fig. 3
Max pooling concept with 2 × 2 filters and stride 2
Fig. 4
Fig. 4
a High-grade (HG) glioma subject case. b Low-grade (LG) glioma subject case
Fig. 5
Fig. 5
Preprocessing impact on classification’s accuracy
Fig. 6
Fig. 6
Data augmentation technique’ impact on classification’ accuracy
Fig. 7
Fig. 7
Comparison of deep versus large kernels (5 × 5) based CNN architecture
Fig. 8
Fig. 8
Comparison of deep versus (7 × 7) large kernels with augmented features maps
Fig. 9
Fig. 9
Hyper-parameters’ validation. a Max pooling validation. b Relu activation function validation. c Adam optimize validation. d Glorot normal validation
See this image and copyright information in PMC

References

    1. M. L. Goodenberger, R. B. Jenkins, Genetics of adult glioma, Cancer genetics 205 (12) (2012) 613-621. - PubMed
    1. Louis D, Perry A, Reifenberger G, von Deimling A, Figarella-Branger D, Cavenee W, Ohgaki H, Wiestler O, Kleihues P, Ellison D. The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Actaneuropathol (berl). 2016;131:803–20. doi: 10.1007/s00401-016-1545-1. - DOI - PubMed
    1. F. B. Mesfin, M. A. Al-Dhahir, Cancer, brain, gliomas, in: StatPearls [Internet], StatPearls Publishing, 2018.
    1. H. Mzoughi, I. Njeh, M. B. Slima, A. B. Hamida, Histogram equalization-based techniques for contrast enhancement of MRI brain glioma tumor images: comparative study, in: 2018 4th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), IEEE, 2018,pp. 1. 6.510
    1. X. Bi, J. G. Liu, Y. S. Cao, Classification of low-grade and high-grade glioma using multiparametric radiomics model, in: 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), IEEE, 2019, pp. 574-577.