Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists - PubMed 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 6;10(8):565.
doi: 10.3390/diagnostics10080565.

Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists

Muhammad Attique Khan  1 , Imran Ashraf  2 , Majed Alhaisoni  3 , Robertas Damaševičius  4   5 , Rafal Scherer  6 , Amjad Rehman  7 , Syed Ahmad Chan Bukhari  8
Affiliations

Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists

Muhammad Attique Khan et al. Diagnostics (Basel). .

Abstract

Manual identification of brain tumors is an error-prone and tedious process for radiologists; therefore, it is crucial to adopt an automated system. The binary classification process, such as malignant or benign is relatively trivial; whereas, the multimodal brain tumors classification (T1, T2, T1CE, and Flair) is a challenging task for radiologists. Here, we present an automated multimodal classification method using deep learning for brain tumor type classification. The proposed method consists of five core steps. In the first step, the linear contrast stretching is employed using edge-based histogram equalization and discrete cosine transform (DCT). In the second step, deep learning feature extraction is performed. By utilizing transfer learning, two pre-trained convolutional neural network (CNN) models, namely VGG16 and VGG19, were used for feature extraction. In the third step, a correntropy-based joint learning approach was implemented along with the extreme learning machine (ELM) for the selection of best features. In the fourth step, the partial least square (PLS)-based robust covariant features were fused in one matrix. The combined matrix was fed to ELM for final classification. The proposed method was validated on the BraTS datasets and an accuracy of 97.8%, 96.9%, 92.5% for BraTs2015, BraTs2017, and BraTs2018, respectively, was achieved.

Keywords: ELM; PLS; brain tumor; deep learning features; feature fusion; feature selection; healthcare; linear contrast; transfer learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Sample images collected from Multimodal Brain Dataset (BRATS) [15].
Figure 2
Figure 2
Proposed architecture for multimodal brain tumor classification using deep learning features and extreme learning machine (ELM).
Figure 3
Figure 3
Results of the proposed hybrid local contrast enhancement using the MRI images of the Multimodal BRATS 2018 dataset. The results are shown from top to bottom.
Figure 4
Figure 4
A layered wise architecture of the VGG16 deep learning model.
Figure 5
Figure 5
A layered wise architecture of the VGG19 deep learning model.
Figure 6
Figure 6
Labeled results generated by the proposed system. The label is shown in red on green square.
Figure 7
Figure 7
Accuracy results with and without employing the contrast enhancement step.
Figure 8
Figure 8
Confidence interval of statistical test for different critical values of t-test (BraTS 2015 dataset).
Figure 9
Figure 9
Confidence interval of statistical test for different critical value of t-test (BraTS 2017 dataset).
Figure 10
Figure 10
Confidence interval of statistical test for different critical value of t-test (BraTS 2018 dataset).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Deepak S., Ameer P. Brain tumor classification using deep CNN features via transfer learning. Comput. Biol. Med. 2019;111:103345. doi: 10.1016/j.compbiomed.2019.103345. - DOI - PubMed
    1. Sert E., Özyurt F., Doğantekin A. A new approach for brain tumor diagnosis system: Single image super resolution based maximum fuzzy entropy segmentation and convolutional neural network. Med. Hypotheses. 2019;133:109413. doi: 10.1016/j.mehy.2019.109413. - DOI - PubMed
    1. Cancer.Net, Brain Tumor Statistics. [(accessed on 24 July 2020)];2020 Available online: https://www.cancer.net/cancer-types/brain-tumor/statistics.
    1. Roy S., Bandyopadhyay S.K. Detection and Quantification of Brain Tumor from MRI of Brain and It’s Symmetric Analysis. Int. J. Inf. Commun. Technol. Res. 2012;2:477–483.
    1. Pereira S., Pinto A., Alves V., Silva C.A. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans. Med. Imaging. 2016;35:1240–1251. doi: 10.1109/TMI.2016.2538465. - DOI - PubMed

LinkOut - more resources