An efficient approach to diagnose brain tumors through deep CNN

Bakhtyar Ahmed Mohammed; Muzhir Shaban Al-Ani; Bakhtyar Ahmed Mohammed; Muzhir Shaban Al-Ani

doi:10.3934/mbe.2021045

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 1: 851-867. doi: 10.3934/mbe.2021045

Previous Article Next Article

Research article Special Issues

An efficient approach to diagnose brain tumors through deep CNN

Bakhtyar Ahmed Mohammed ^{1
,
,},
Muzhir Shaban Al-Ani ²

1.
University of Human Development, College of Science and Technology, Department of Computer Science, Sulaymaniyah, KRG, Iraq and University of Sulaimani, College of Science, Department of Computer, Sulaymaniyah, KRG, Iraq
2.
University of Human Development, College of Science and Technology, Department of Information Technology, Sulaymaniyah, KRG, Iraq

Received: 01 October 2020 Accepted: 02 December 2020 Published: 25 December 2020

Background and objective Brain tumors are among the most common complications with debilitating or even death potential. Timely detection of brain tumors particularly at an early stage can lead to successful treatment of the patients. In this regard, numerous diagnosis methods have been proposed, among which deep convolutional neural networks (deep CNN) method based on brain MRI images has drawn huge attention. The present study was aimed at proposing a deep CNN-based systematic approach to diagnose brain tumors and evaluating its accuracy, sensitivity, and error rates. Materials and methodsThe present study was carried out on 1258 MRI images of 60 patients with three classes of brain tumors and a class of normal brain obtained from Radiopedia database recorded from 2015 to 2020 to make the dataset. The dataset distributed into 70% for training set, 20% for test set, and 10% for validation set. Deep Convolutional neural networks (deep CNN) method was used for feature learning of the dataset images which rely on training set. The processes were carried out through MATLAB software. For this purpose, the images were processed based on four classes, including ependymoma, meningioma, medulloblastoma, and normal brain. Results The results of the study indicated that the proposed deep CNN-based approach had an accuracy level of 96%. It was also observed that the feature learning accuracy of the proposed approach was 47.02% in case of using 1 epoch, which increased to 96% when the number of epochs rose to 15. The sensitivity of the approach also had a direct relationship with the number of epochs, such that it increased from 47.02 to 96% in cases of having 1 and 15 epochs, respectively. It was also seen that epoch number had a reverse relationship with error rate which decreased from 52.98 to 4% once the number of the epochs increased from 1 to 15. After that the system tested on 25 new MRI images of each of the classes with accuracy 96% according to the confusion matrix. ConclusionUsing deep CNN for feature learning, extraction, and classification based on MRI images is an efficient method with an accuracy rate of 96% in case of using 15 epochs. It exhibited the factors which cause increase accuracy of the work.
- brain tumor,
- deep convolutional neural networks (deep CNN),
- ependymoma,
- meningioma,
- medulloblastoma
Citation: Bakhtyar Ahmed Mohammed, Muzhir Shaban Al-Ani. An efficient approach to diagnose brain tumors through deep CNN[J]. Mathematical Biosciences and Engineering, 2021, 18(1): 851-867. doi: 10.3934/mbe.2021045

Related Papers:

Abstract

Background and objective Brain tumors are among the most common complications with debilitating or even death potential. Timely detection of brain tumors particularly at an early stage can lead to successful treatment of the patients. In this regard, numerous diagnosis methods have been proposed, among which deep convolutional neural networks (deep CNN) method based on brain MRI images has drawn huge attention. The present study was aimed at proposing a deep CNN-based systematic approach to diagnose brain tumors and evaluating its accuracy, sensitivity, and error rates. Materials and methodsThe present study was carried out on 1258 MRI images of 60 patients with three classes of brain tumors and a class of normal brain obtained from Radiopedia database recorded from 2015 to 2020 to make the dataset. The dataset distributed into 70% for training set, 20% for test set, and 10% for validation set. Deep Convolutional neural networks (deep CNN) method was used for feature learning of the dataset images which rely on training set. The processes were carried out through MATLAB software. For this purpose, the images were processed based on four classes, including ependymoma, meningioma, medulloblastoma, and normal brain. Results The results of the study indicated that the proposed deep CNN-based approach had an accuracy level of 96%. It was also observed that the feature learning accuracy of the proposed approach was 47.02% in case of using 1 epoch, which increased to 96% when the number of epochs rose to 15. The sensitivity of the approach also had a direct relationship with the number of epochs, such that it increased from 47.02 to 96% in cases of having 1 and 15 epochs, respectively. It was also seen that epoch number had a reverse relationship with error rate which decreased from 52.98 to 4% once the number of the epochs increased from 1 to 15. After that the system tested on 25 new MRI images of each of the classes with accuracy 96% according to the confusion matrix. ConclusionUsing deep CNN for feature learning, extraction, and classification based on MRI images is an efficient method with an accuracy rate of 96% in case of using 15 epochs. It exhibited the factors which cause increase accuracy of the work.

References

[1]	S. S. Khalsa, T. C. Hollon, R. A. Arja, Automated histologic diagnosis of CNS tumors with machine learning, CNS Oncol., 9 (2020), 56. doi: 10.2217/cns-2020-0003
[2]	M. Karuna, A. Joshi, Automatic detection and severity analysis of brain tumors using gui in matlab, Int. J. Res. Eng. Technol., 10 (2013), 586-594.
[3]	Q. T. Ostrom, G. Cioffi, H. Gittleman, CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2012-2016, Neurol. Oncol., 21 (2019), 1-100. doi: 10.1093/neuonc/noy189
[4]	E. M. Thompson, T. Hielscher, E. Bouffet, Prognostic value of medulloblastoma extent of resection after accounting for molecular subgroup: A retrospective integrated clinical and molecular analysis, Lancet Oncol., 17 (2016), 484-495. doi: 10.1016/S1470-2045(15)00581-1
[5]	J. P. Poonam, Review of image processing techniques for automatic detection of tumor in human brain, Int. J. Comput. Sci. Mobile Comput., 2 (2013), 117-122.
[6]	M. M. Ghazani, A. H. Phan, Graph convolutional neural networks for analysis of EEG signals, preprint, arXiv: 2006.14540.
[7]	R. Bayot, T. Gonalves, A survey on object classification using convolutional neural networks, Artif. Int. Rev., 53 (2015), 5455-5516.
[8]	X. Yan, Z. Jia, Y. Ai, F. Zhang, Deep convolutional activation features for large scale brain tumor histopathology image classification and segmentation, 2015 IEEE Int. Conf. Acoust. Speech Signal Process., (2015), 947-951.
[9]	Y. Pan, Brain tumor grading based on neural networks and convolutional neural networks, 2015 37th Ann. Int. Conf. IEEE Eng. Med. Biol. Soc., (2015), 699-702.
[10]	F. Samadi, G. Akbarizadeh, H. Kaabi, Change detection in SAR Images using deep belief network: A new training approach based on morphological images, IET Image Process., 13 (2019), 2255-2264. doi: 10.1049/iet-ipr.2018.6248
[11]	A. Comelli, A. Stefano, S. Bignardi, C. Coronnello, G. Russo, M. Sabini, et al., Tissue classification to support local active delineation of brain tumors, Ann. Conf. Med. Image Understanding Anal., (2020), 3-14.
[12]	A. Stefano, A. Comelli, V. Bravatà, S. Barone, I. Daskalovski, G. Savoca, G., et al., A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method, BMC Bioinformat., 21 (2019), 1-14.
[13]	I. Shahzadi, T. B. Tang, F. Meriadeau, A. Quyyum. CNNLSTM: Cascaded framework for brain tumour classification, IEEE-EMBS Conf. Biomed. Eng. Sci., (2018), 633-637.
[14]	A. Çinar, M. Yildirim, Detection of tumors on brain MRI images using the hybrid convolutional neural network architecture, Med. Hypotheses, 139 (2020), 109684. doi: 10.1016/j.mehy.2020.109684
[15]	M. Malathi, P. Sinthia, Brain tumour segmentation using convolutional neural network with tensor flow, Asian.Pac. J. Cancer Prev., 20 (2019), 2095-2101. doi: 10.31557/APJCP.2019.20.7.2095
[16]	R. Chelghoum, A. Ikhlef, A. Hameurlaine, Transfer learning using convolutional neural network architectures for brain tumor classification from MRI images, Artific. Int. Appl. Innovat., 583 (2020), 189-200.
[17]	M. Siar, M. Teshnehlab, Brain tumor detection using deep neural network and machine learning algorithm, 9th Int. Conf. Comput. Knowl. Eng., 2019.
[18]	T. Hossain, F. S. Shishir, M. Ashraf, Brain tumor detection using convolutional neural network. international conference on advances in science, Eng. Robot. Technol., 2019.
[19]	T. C. Hollon, B. Pandian, A. R. Adapa, Near real-time intraoperative brain tumor diagnosis using stimulated raman histology and deep neural networks, Nat. Med., 26 (2020), 52-58. doi: 10.1038/s41591-019-0715-9
[20]	B. N. Mostefa, S. Rachida, A. Mohamed, K. Rostom, Fully automatic brain tumor segmentation using end-to-end incremental deep neural networks in MRI images, Comput. Methods. Programs. Biomed., 166 (2018), 39-49. doi: 10.1016/j.cmpb.2018.09.007
[21]	S. S. Begum, D. R. Lakshmi. Combining optimal wavelet statistical texture and recurrent neural network for tumour detection and classification over MRI, Multimed. Tools. Appl, 79 (2020), 14009-14030. doi: 10.1007/s11042-020-08643-w
[22]	D. John, H. Elad, S. Yoram, Adaptive subgradient methods for online learning and stochastic optimization, J. Mach. Learn. Res., 12 (2011), 2121-2159.
[23]	L. Sun, S. Zhang, H. Chen, L. Luo, Brain tumor segmentation and survival prediction using multimodal MRI scans with deep learning, Front. Neurosci., 16 (2019).
[24]	T. Gupta, T. K. Gandhi, R. K. Gupta, B. K. Panigrahi, Classification of patients with tumor using MR FLAIR images, Pattern Recogn Lett., 139 (2017), 112-117.

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)