Abstract
In the current study, the capability of pre-trained Deep Convolutional Neural Network (DCNN) by ImageNet features is proposed for categorization of brain tumors by utilizing MR images. The pre-trained models like ResNet50, InceptionV3, Xception, DenseNet121, MobileNetV3Large, EffcientNetB0, EfficientNetV2L, EfficientNetV2B0 have been exploited for classification purpose. The selection criteria is based upon the diverse proficiency each model depicts. For e.g., EfficientNetB0, ResNet50, MobileNet, Xception employ lower number of training parameters that makes them time efficient whereas, VGG16 though has higher number of training parameters, while increasing the training time without compromising with accuracy. The AlexNet on the other hand also has a reduced number of parameters in comparison to Google’s Inception module which is more memory efficient. AlexNet takes more memory for training. The EfficientNet’s are based on inverted residual blocks of MobileNetV2 with addition to Squeeze and Excitation blocks which makes them highly efficient for feature extraction. Therefore, in this research study, the above stated pre-trained models are used in by retaining the ReLU as an activation function due to its unbounded nature which also helps the model from Vanishing Gradient problem. By hyper tuning the top layers of different pre-trained models by adding Global Average Pooling layer and Dropout layer along with Fully Connected layer with classifier as SoftMax increases the overall efficiency and also reduces overfitting. The proposed comparative study shows the working of different pre-trained DCNN models for classifying brain tumors. The proposed experimental study is performed on three different databases i.e., Kaggle, BraTS 2018, and Real time dataset acquired from PGIMER and comparison analysis. The comparison analysis with existing methods as well as statistical analysis is also performed. It is observed from the results that EfficientNetB0 has outperformed all the existing methods. The pre-trained EfficientNetB0 architecture by hyper tuning the parameters, the testing accuracy has increased by 2.14% on Kaggle and increased the classification accuracy by 3.98% on BraTS dataset. On Real time dataset comprising of Glioblastoma Multiforme and Oligodendroglioma, highest accuracy of 97.32% is achieved among all other models.
Similar content being viewed by others
Abbreviations
- AI:
-
Artificial intelligence
- CAD:
-
Computer aided diagnosis
- DCNN:
-
Deep convolutional neural network
- CNN:
-
Convolutional neural network
- WCNN:
-
Wavelet convolutional neural network
- MRI:
-
Magnetic resonance imaging
- CT:
-
Computed tomography
- NMR:
-
Nuclear magnetic resonance
- RF:
-
Radio frequency
- ML:
-
Machine learning
- ELM:
-
Extreme learning machine
- PSO:
-
Particle swarm optimization
- KSVM:
-
Kernel support vector machine
- PCA:
-
Principal component analysis
- DWT:
-
Discrete wavelet transformation
- CV:
-
Cross validation
- PPCA:
-
Probabilistic principal component analysis
- SHO:
-
Spotted hyena optimization
- ANN:
-
Artificial neural network
- SVM:
-
Support vector machine
- GA:
-
Genetic algorithm
- SCA:
-
Sine cosine algorithm
- HGG:
-
High grade Glioma
- LGG:
-
Low grade Glioma
- GBM:
-
Glioblastoma multiforme
- OGM:
-
Oligodendroglioma
- CE:
-
Categorical crossentropy
- GAP:
-
Global average pooling
- TPR:
-
True positive rate
- TNR:
-
True negative rate
- PPV:
-
Positive predicted value
- NPV:
-
Negative predicted value
- FPR:
-
False positive rate
- FNR:
-
False negative rate
- ACC:
-
Accuracy
- MCC:
-
Mathew’s correlation coefficient
- k:
-
Cohen’s Kappa coefficient
- MANet:
-
Multilevel attenuation network
- SENet:
-
Squeeze and excitation network
- SGDM:
-
Stochastic gradient descent with momentum
- NifTI:
-
Neuroimaging informatics technology initiative
- PGIMER:
-
Post-graduate Institute of Medical Education and Research
- ADBRF:
-
Adaboost random forest
- BSO:
-
Brain-storm optimization
- VG:
-
Vanishing gradient
- NADE:
-
Neural autoregressive distribution estimation
- PET:
-
Positron emission tomography
- ILSVRC:
-
ImageNet large scale visual recognition channel
- RBF:
-
Radial basis function
- Dolphin SCA:
-
Dolphin echolocation based sine cosine algorithm
References
Khazaei Z et al (2020) The association between incidence and mortality of brain cancer and human development index (HDI): an ecological study. BMC Public Health 20(1):1–7. https://doi.org/10.1186/s12889-020-09838-4
Rehman A, Naz S, Razzak MI, Akram F, Imran M (2020) “A deep learning-based framework for automatic brain tumors classification using transfer learning”, Circuits. Syst Signal Process 39(2):757–775. https://doi.org/10.1007/s00034-019-01246-3
Russakovsky O et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211–252. https://doi.org/10.1007/s11263-015-0816-y
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the Inception Architecture for Computer Vision, Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. https://doi.org/10.1109/CVPR.2016.308
Chollet F (2017) Xception: deep learning with depthwise separable convolutions, Proc—30th IEEE Conf Comput Vis Pattern Recognition, CVPR, pp. 1800–1807. https://doi.org/10.1109/CVPR.2017.195
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks, Proc—30th IEEE Conf Comput Vis Pattern Recognition, CVPR 2017, pp. 2261–2269. https://doi.org/10.1109/CVPR.2017.243
Howard A et al. (2019) Searching for mobileNetV3, Proc IEEE Int Conf Comput Vis, pp. 1314–1324. https://doi.org/10.1109/ICCV.2019.00140
Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks, 36th Int. Conf. Mach. Learn. ICML 2019, pp. 10691–10700
Tan M, Le QV (2021) EfficientNetV2: smaller models and faster training, [Online]. http://arxiv.org/abs/2104.00298
Bhuvaji S, Kadam A, Bhumkar P, Dedge S, Kanchan S (2020) Brain tumor classification (MRI) Dataset https://www.kaggle.com/sartajbhuvaji/brain-tumor-classification-mri. https://doi.org/10.34740/kaggle/dsv/1183165
Menze BH et al (2015) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34(10):1993–2024. https://doi.org/10.1109/TMI.2014.2377694
Bakas S et al. (2018) Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge [Online]. http://arxiv.org/abs/1811.02629
Bakas S et al (2017) Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data 4:1–13. https://doi.org/10.1038/sdata.2017.117
O’Shea K, Nash R (2015) An introduction to convolutional neural networks [Online]. http://arxiv.org/abs/1511.08458
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift [Online]. http://arxiv.org/abs/1502.03167
Deepa AR, Sam Emmanuel WR (2019) An efficient detection of brain tumor using fused feature adaptive firefly backpropagation neural network. Multimed Tools Appl 78(9):11799–11814. https://doi.org/10.1007/s11042-018-6731-9
Kuraparthi S et al (2021) Brain tumor classification of MRI images using deep convolutional neural network. Trait du Signal 38(4):1171–1179. https://doi.org/10.18280/ts.380428
Badža MM, Barjaktarović MC (2020) Classification of brain tumors from MRI images using a convolutional neural network. Appl Sci. https://doi.org/10.3390/app10061999
Nagaraj P, Muneeswaran V, Veera Reddy L, Upendra P, Vishnu Vardhan Reddy M (2020) Programmed multi-classification of brain tumor images using deep neural network, Proc Int Conf Intell Comput Control Syst ICICCS 2020, pp. 865–870. https://doi.org/10.1109/ICICCS48265.2020.9121016.
Deepak S, Ameer PM (2019) Brain tumor classification using deep CNN features via transfer learning. Comput Biol Med 111:103345. https://doi.org/10.1016/j.compbiomed.2019.103345
Noreen N, Palaniappan S, Qayyum A, Ahmad I, Imran M, Shoaib M (2020) A deep learning model based on concatenation approach for the diagnosis of brain tumor. IEEE Access 8:55135–55144. https://doi.org/10.1109/ACCESS.2020.2978629
Kaur T, Gandhi TK (2020) Deep convolutional neural networks with transfer learning for automated brain image classification. Mach Vis Appl 31(3):1–16. https://doi.org/10.1007/s00138-020-01069-2
Sadad T et al (2021) Brain tumor detection and multi-classification using advanced deep learning techniques. Microsc Res Tech 84(6):1296–1308. https://doi.org/10.1002/jemt.23688
Chelghoum R, Ikhlef A, Hameurlaine A, Jacquir S (2020) Transfer learning using convolutional neural network architectures for brain tumor classification from MRI images, vol 583. IFIP. Springer International Publishing, Cham. https://doi.org/10.1007/978-3-030-49161-1_17
Sarhan AM (2020) Brain tumor classification in magnetic resonance images using deep learning and wavelet transform. J Biomed Sci Eng 13(06):102–112. https://doi.org/10.4236/jbise.2020.136010
Khan MA et al (2020) Multimodal brain tumor classification using deep learning and robust feature selection: a machine learning application for radiologists. Diagnostics 10(8):1–19. https://doi.org/10.3390/diagnostics10080565
Zhang Y, Wang S, Ji G, Dong Z (2013) An MR brain images classifier system via particle swarm optimization and kernel support vector machine. Sci World J. https://doi.org/10.1155/2013/130134
Nayak DR, Dash R, Majhi B (2016) Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests. Neurocomputing 177:188–197. https://doi.org/10.1016/j.neucom.2015.11.034
Afshar P, Plataniotis KN, Mohammadi A (2019) Capsule networks for brain tumor classification based on MRI images and coarse tumor boundaries, ICASSP, IEEE Int Conf Acoust Speech Signal Process—Proc, pp. 1368–1372. https://doi.org/10.1109/ICASSP.2019.8683759
Gaur L, Bhandari M, Razdan T, Mallik S, Zhao Z (2022) Explanation-driven deep learning model for prediction of brain tumor status using MRI image data. Front Genet 13(March):1–9. https://doi.org/10.3389/fgene.2022.822666
Rath P, Mallick PK, Siddavatam R, Chae GS (2021) An empirical development of hyper-tuned CNN using spotted hyena optimizer for bio-medical image classification. J Nat Sc Biol Med 12:300–316. https://doi.org/10.4103/jnsbm.JNSBM_12_3_5
Alanazi MF et al (2022) Brain tumor/mass classification framework using magnetic-resonance-imaging-based isolated and developed transfer deep-learning model. Sensors. https://doi.org/10.3390/s22010372
Narmatha C, Eljack SM, Tuka AARM, Manimurugan S, Mustafa M (2020) A hybrid fuzzy brain-storm optimization algorithm for the classification of brain tumor MRI images. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-02470-5
Kumar S, Mankame DP (2020) Optimization driven deep convolution neural network for brain tumor classification. Biocybern Biomed Eng 40(3):1190–1204. https://doi.org/10.1016/j.bbe.2020.05.009
Shaik NS, Cherukuri TK (2022) Multi-level attention network: application to brain tumor classification. Signal Image Video Process 16(3):817–824. https://doi.org/10.1007/s11760-021-02022-0
Sachdeva J, Kumar V, Gupta I, Khandelwal N, Ahuja CK (2016) A package-SFERCB-“Segmentation, feature extraction, reduction and classification analysis by both SVM and ANN for brain tumors.” Appl Soft Comput J 47:151–167. https://doi.org/10.1016/j.asoc.2016.05.020
Sachdeva J, Kumar V, Gupta I, Khandelwal N, Ahuja CK (2013) Segmentation, feature extraction, and multiclass brain tumor classification. J Digit Imaging 26(6):1141–1150. https://doi.org/10.1007/s10278-013-9600-0
Abd-Ellah MK, Awad AI, Khalaf AAM, Hamed HFA (2016) Design and implementation of a computer-aided diagnosis system for brain tumor classification, Proc Int Conf Microelectron. https://doi.org/10.1109/ICM.2016.7847911
Tiwari P, Sachdeva J, Ahuja CK, Khandelwal N (2017) Computer aided diagnosis system—a decision support system for clinical diagnosis of brain tumors. Int J Comput Intell Syst 10(1):104–119. https://doi.org/10.2991/ijcis.2017.10.1.8
El-Dahshan EAS, Mohsen HM, Revett K, Salem ABM (2014) Computer-aided diagnosis of human brain tumor through MRI: a survey and a new algorithm. Expert Syst Appl 41(11):5526–5545. https://doi.org/10.1016/j.eswa.2014.01.021
Bahadure NB, Ray AK, Thethi HP (2018) Comparative approach of MRI-based brain tumor segmentation and classification using genetic algorithm. J Digit Imaging 31(4):477–489. https://doi.org/10.1007/s10278-018-0050-6
Zöllner FG, Emblem KE, Schad LR (2012) SVM-based Glioma grading: optimization by feature reduction analysis. Z Med Phys 22(3):205–214. https://doi.org/10.1016/j.zemedi.2012.03.007
Alfonse M, Salem A-BM (2016) An automatic classification of brain tumors through MRI using support vector machine. Egypt Comput Sci J 40(03):1110–2586
Soltaninejad M, Ye X, Yang G, Allinson N, Lambrou T (2014) Brain tumour grading in different MRI protocols using SVM on statistical features, Med Image Underst Anal, 2014
Machhale K, Nandpuru HB, Kapur V, Kosta L (2015) MRI brain cancer classification using hybrid classifier (SVM-KNN), 2015 Int Conf Ind Instrum Control ICIC. https://doi.org/10.1109/IIC.2015.7150592
Cinarer G, Emiroglu BG (2019) Classificatin of brain tumors by machine learning algorithms, 3rd Int Symp Multidiscip Stud Innov Technol. ISMSIT 2019—Proc. https://doi.org/10.1109/ISMSIT.2019.8932878
Kang J, Ullah Z, Gwak J (2021) MRI based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors 21(6):1–21. https://doi.org/10.3390/s21062222
Anitha R, Siva Sundhara Raja D (2018) Development of computer-aided approach for brain tumor detection using random forest classifier. Int J Imaging Syst Technol 28(1):48–53. https://doi.org/10.1002/ima.22255
Zhou X et al (2015) Detection of pathological brain in MRI scanning based on wavelet-entropy and naive bayes classifier. Lect Notes Comput Sci. https://doi.org/10.1007/978-3-319-16483-0_20
Lahmiri S (2017) Glioma detection based on multi-fractal features of segmented brain MRI by particle swarm optimization techniques. Biomed Signal Process Control 31:148–155. https://doi.org/10.1016/j.bspc.2016.07.008
Chen T, Xiao F, Yu Z, Yuan M, Xu H, Lu L (2021) Detection and grading of gliomas using a novel two-phase machine learning method based on MRI images. Front Neurosci 15(May):1–10. https://doi.org/10.3389/fnins.2021.650629
Zacharaki EI et al (2009) Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 62(6):1609–1618. https://doi.org/10.1002/mrm.22147
Krishna TG, Sunitha KVN, Mishra S (2018) Detection and classification of brain tumor from MRI medical image using wavelet transform and PSO based LLRBFNN algorithm. Int J Comput Sci Eng 6(1):18–23. https://doi.org/10.26438/ijcse/v6i1.1823
Gumaei A, Hassan MM, Hassan MR, Alelaiwi A, Fortino G (2019) A hybrid feature extraction method with regularized extreme learning machine for brain tumor classification. IEEE Access 7:36266–36273. https://doi.org/10.1109/ACCESS.2019.2904145
Kharrat A, Ben Halima M, Ben Ayed M (2016) MRI brain tumor classification using Support Vector Machines and meta-heuristic method. Int Conf Intell Syst Des Appl. https://doi.org/10.1109/ISDA.2015.7489271
Hashemzehi R, Mahdavi SJS, Kheirabadi M, Kamel SR (2020) Detection of brain tumors from MRI images base on deep learning using hybrid model CNN and NADE. Biocybern Biomed Eng 40(3):1225–1232. https://doi.org/10.1016/j.bbe.2020.06.001
Minarno AE, HazmiCokroMandiri M, Munarko Y, Hariyady H (2021) Convolutional neural network with hyperparameter tuning for brain tumor classification. Kinet Game Technol Inf Syst Comput Network Comput Electron Control. https://doi.org/10.22219/kinetik.v6i2.1219
Kingma DP, Ba JL, Adam: a method for stochastic optimization, 3rd Int. Conf. Learn. Represent. ICLR 2015—Conf Track Proc, pp. 1–15, 2015
Zhu Q, He Z, Zhang T, Cui W (2020) Improving classification performance of softmax loss function based on scalable batch-normalization. Appl Sci (Switzerland). https://doi.org/10.3390/APP10082950
Nwankpa C, Ijomah W, Gachagan A, Marshall S (2018) Activation functions: comparison of trends in practice and research for deep learning [Online]. http://arxiv.org/abs/1811.03378
Chicco D, Tötsch N, Jurman G (2021) The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation. BioData Min 14:1–22. https://doi.org/10.1186/s13040-021-00244-z
Funding
The authors gratefully acknowledge financial support from Indian Council of Medical Research: (ICMR)/ISRM (12)46/2019.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All the authors declare that they have no conflict of interest or competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sachdeva, J., Sharma, D. & Ahuja, C.K. Comparative Analysis of Different Deep Convolutional Neural Network Architectures for Classification of Brain Tumor on Magnetic Resonance Images. Arch Computat Methods Eng 31, 1959–1978 (2024). https://doi.org/10.1007/s11831-023-10041-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11831-023-10041-y