Abstract
Brain Tumors can be lethal if not diagnosed or misdiagnosed. Seeing the mortality because of this is high there’s a need to find a solution to detect, classify and diagnose this problem effectively and help medical professionals save precious lives. Brain MRI [1] images help in detection of these tumors. Though there are classification techniques the most common limitation is low accuracy. In this paper we use Deep Learning Architectures to perform these tasks. Architectures like VGG19, ResNet50 [2], DenseNet201 [4] and Xception [5] which are Convolutional Neural Networks [6] are analysed and compared and a novel model is built. We used the BraTS2020 [3] dataset which consists of images of four types Pituitary tumor, Meningioma tumor, Glioma tumor and no tumor we next performed resizing, re-scaling, preprocessing techniques on them. Following which we deployed the architecture to obtain our first set of results i.e, VGG19 gave accuracy of 70%, ResNet gave 72%, Xception gave 75% and DensetNet201 gave 76%. To make our accuracies better we performed image enhancement. [7]the process where adjusting of digital images takes place to ensure that the results are more suitable to display or for doing further image analysis is called image enhancement. Three types of Image enhancement techniques have been used: Adaptive Thresholding [8], Brightening [9], Contrasting [10] and we found that with contrasting we got the best results and VGG19 architecture gave highest accuracy of 83% proving the importance of image enhancement.
KLE Technological University Hubballi, India.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Grover, V.P., Tognarelli, J.M., Crossey, M.M., Cox, I.J., Taylor-Robinson, S.D., McPhail, M.J.: Magnetic resonance imaging: principles and techniques: lessons for clinicians. J. Clin. Exp. Hepatol. 5(3), 246–255 (2015). https://doi.org/10.1016/j.jceh.2015.08.001
Mo, N., Yan, L., Zhu, R., Xie, H.: Class-specific anchor based and context-guided multi-class object detection in high resolution remote sensing imagery with a convolutional neural network. Remote Sens. 11, 272 (2019). https://doi.org/10.3390/rs11030272
Wang, S., Zhang, Y.-D.: DenseNet-201-based deep neural network with composite learning factor and precomputation for multiple sclerosis classification. ACM Trans. Multimedia Comput. Commun. Appl. 16, 1–19 (2020). https://doi.org/10.1145/3341095
arXiv:1610.02357 [cs.CV]
Albawi, S., Mohammed, T.A., Al-Zawi, S.: Understanding of a convolutional neural network. Int. Conf. Eng. Technol. (ICET) 2017, 1–6 (2017). https://doi.org/10.1109/ICEngTechnol.2017.8308186
Roy, P., Dutta, S., Dey, N., Dey, G., Chakraborty, S., Ray, R.: Adaptive thresholding: a comparative study. In: 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT), pp. 1182–1186 (2014). https://doi.org/10.1109/ICCICCT.2014.6993140
Maurya, L., Lohchab, V., Kumar Mahapatra, P., Abonyi, J.: Contrast and brightness balance in image enhancement using Cuckoo Search-optimized image fusion. J. King Saud Univ. Comput. Inf. Sci. 34(9), pp. 7247–7258 (2022)
Roomi, M., Maragatham, G.G.: A review of image contrast enhancement methods and techniques. Res. J. Appl. Sci. Eng. Technol. 9, 309–326 (2015). https://doi.org/10.19026/rjaset.9.1409
Patel, A.: Benign vs Malignant tumors. JAMA Oncol. 6(9), 1488 (2020). https://doi.org/10.1001/jamaoncol.2020.2592
McAuliffe, M.J., Lalonde, F.M., McGarry, D., Gandler, W., Csaky, K., Trus, B.L.: medical image processing, analysis and visualization in clinical research. In: Proceedings 14th IEEE Symposium on Computer-Based Medical Systems. CBMS 2001, pp. 381–386 (2001). https://doi.org/10.1109/CBMS.2001.941749
Rawat, W., Wang, Z.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput. 29, 1–98 (2017). https://doi.org/10.1162/NECO_a_00990
Thalagala, S., Chamila, W.: Application of AlexNet convolutional neural network architecture-based transfer learning for automated recognition of casting surface defects. pp. 129–136 (2021). https://doi.org/10.1109/SCSE53661.2021.9568315
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Boustani, A., Aatila, M., El Bachari, E., Ahmed, E.O.: MRI brain images classification using convolutional neural networks, pp. 308–320 (2020)
Sallam, W., Seddik, A., Ali, H.: A review on brain MRI image segmentation (2013)
Qi, Y., et al.: A comprehensive overview of image enhancement techniques. Archives of Computational Methods in Engineering (2021)
Thirumaran, J., Shylaja, S.: Medical image processing-an introduction. Comput. Graph. Image Process. 4, 5–611 (2014)
Padmavathy, V.S., Priya, R.: Image contrast enhancement techniques-a survey. Int. J. Eng. Technol. (UAE) 7, 466–469 (2018)
Dubey, R.: A review on MRI image segmentation techniques (2015)
Agarwal, V.: Research on data preprocessing and categorization technique for smartphone review analysis. Int. J. Comput. Appl. 131, 30–36 (2015). https://doi.org/10.5120/ijca2015907309
Tejas, P., Akshay, K., Rishi, S., Rushi, B.: UNDERSTANDING INCEPTION NETWORK ARCHITECTURE FOR IMAGE CLASSIFICATION (2020). https://doi.org/10.13140/RG.2.2.16212.35204
Ying, X.: An overview of overfitting and its solutions. J. Phys. Conf. Ser. 1168, 022022 (2019). https://doi.org/10.1088/1742-6596/1168/2/022022
Binghui, C., Weihong, D., Junping, D.: Noisy Softmax: improving the generalization ability of DCNN via Postponing the Early Softmax Saturation (2017). https://doi.org/10.1109/CVPR.2017.428
Zhou, T., Ye, X., Lu, H., Zheng, X., Qiu, S., Liu, Y.: Dense convolutional network and its application in medical image analysis. Biomed. Res. Int. 2022, 2384830 (2022). https://doi.org/10.1155/2022/2384830
Zhao, L., Jia, K.: Multiscale CNNs for brain tumor segmentation and diagnosis. Comput. Math. Methods Med. 2016, 1–7 (2016). https://doi.org/10.1155/2016/8356294
Sobhaninia, Z., Rezaei, S., Karimi, N., Emami, A., Samavi, S.: Brain tumor segmentation by cascaded deep neural networks using multiple image scales. In: 2020 28th Iranian Conference on Electrical Engineering (ICEE), pp. 1–4 (2020). https://doi.org/10.1109/ICEE50131.2020.9260876
Wahlang, I., Maji, A.K., Saha, G., et al.: Brain magnetic resonance imaging classification using deep learning architectures with gender and age. Sensors (Basel). 22(5), 1766 (2022). https://doi.org/10.3390/s22051766
Tamilarasi, R., Gopinathan, S.: Journal of Physics: Conference Series. 1964, 072022 (2021). https://doi.org/10.1088/1742-6596/1964/7/072022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Meti, A., Rao, A., Jha, P. (2023). Brain MRI Image Classification Using Deep Learning. In: Jabbar, M.A., Ortiz-Rodríguez, F., Tiwari, S., Siarry, P. (eds) Applied Machine Learning and Data Analytics. AMLDA 2022. Communications in Computer and Information Science, vol 1818. Springer, Cham. https://doi.org/10.1007/978-3-031-34222-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-34222-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34221-9
Online ISBN: 978-3-031-34222-6
eBook Packages: Computer ScienceComputer Science (R0)