Computerised Brain Tumours Classification using MRI Images
Keywords:
CNN, SVM, HOG, Glioma, Meningioma, Pituitary, Magnetic Resonance Imaging (MRI)Abstract
The categories of the brain tumours into four categories no tumour, glioma, meningioma, and pituitary are exploited in this study to propose a unique representation for magnetic resonance image analysis. MRI images are the input in this investigation. Radiologists manually interpret MRI scans to find abnormalities in the brain. Interpreting a large number of images by hand is difficult and time-consuming. However, because of the complexity of the MRI equipment, this undertaking is not easy. Particularly, it can be difficult and very subjective to differentiate between various tumour forms, such as gliomas, meningiomas, and pituitary tumours. Computer-based detection aids in the precise, quick, and accurate identification of the disease to address this issue. The suggested study employs CNN and SVM models. Using HOG characteristics, the SVM classifier categorises the brain MRI picture. Three convolutional layers were used in the CNN model's training, and the softmax classifier is used to categorise the image. The four forms of brain tumours identified by the SVM and CNN models are no tumour, glioma, meningioma, and pituitary. By comparing the outcomes, CNN estimates accuracy to be 97%, whereas SVM estimates accuracy to be 92%.
Downloads
References
Jaeyong Kang, ZahidUllah, JeonghwanGwak, “MRI – Based Tumor Classification Using Ensemble of Deep Features and Machine Learning”, Sensors, 2021.
RuqianHao, KhanhayarNamdar, Lin Liu, FarzadKhalvati, “ A Transfer Learning- Based Active Learning Framework for Brain Tumor Classificatoin”, Frontiers in Artificial Intelligence, 2021.
Neha Sharma, Mradul Kumar Jain, Nirvikar, Amit Kumar Agarwal, “Brain Tumor Classification Using CNN”, Advances and Applications in Mathematical Sciences, Volume 20, Issue 3, 2021.
S. Bauer, R. Wiest, L. P. Nolte and Reyes, “ A survey of MRI- Based Medical Image Analysis of Brain Tumor Studies, Physics in Medicine and Biology, Volume 58, Issue 13, 2013.
Tandel, Biswas G. S, Kakde. M, Tiwari. O. G, Suri, Turk. H.S, Laird. J. R, Ankrah. C. K, Khanna N. N, “A Review on a Deep Learning Perspective in Brain Cancer Classification”, Cancers, Volume 11, Issue 111, 2019.
Liu. J, Pan. Y, Li. M, Chen. Z, Tang. L, Lu. C, Wang. J, “Applications of Deep Learning to MRI Images: A Survey”, Big Data Min. Anal, Volume 1, pp 1- 18, 2018.
Mehrotra. R, Ansari. M. A, Agarwal. R, Anand. R. S, “A Transfer Learning Approach for AI-Based Classification of Brain Tumors”, Machine Learning, Volume 1, pp 1-18, 2018.
HimajiByale, Lingaraju G M and ShekarSivasubramanian, “Automatic Segmentation Segmentation and Classification of Brain Tumor using Machine Learning Techniques”, International Journal of Applied Engineering Research, Volume 14, pp. 11686-11692, 2018.
Mahmoud KhaledAbd-Ellah, Ali Ismail Awad, Ashraf A. M Khalaf and Hesam F. A Hamed, “Two-phase multi-model automatic brain tumors diagnosis system from magnetic resonance images using convolutional neural networks”, EURASIP Journal on Image and Video Processing, pp1-10, 2018.
Muhammad Sajjad, Slman Khan, Khan Muhammad, Wanqing Wu, Amin Ullah, Sung WookBaik, “Multi-Grade Brain Tumor Classification with Deep CNN with Extensive Data Augmentation” ,Journal of Computational Science, pp 1- 21, 2018.
Deepak. S, Ameer P. M, “ Brain Tumor Classification using deep CNN features via transfer learning”, Computers in Biology and Medicine, Volume 111, 2019.
He, K., Zhang, X., Ren, S., and Sun, J, ”Deep Residual Learning for Image Recognition”, Proceedings in IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778.
Li, Y., and Su, G. (2015), Simplified Histograms of Oriented Gradient Features Extraction Algorithm for the Hardware Implementation, International Conference on Computers, Communications, and Systems. pp. 192-195.
Mercier, G., and Lennon, M., (2003), Support vector machines for hyperspectral image classification with spectral-based kernels, Proceedings in IEEE International Geoscience and Remote Sensing Symposium, Vol. 1, pp. 288-290.
LeCun, Y., Bottou, L., and Bengio, Y., (2016), LeNet-5, Convolutional Neural Networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., and Chen, T., (2018), Recent Advances in Convolutional Neural Networks, Pattern Recognition, Vol. 77, pp. 354-377.
Springenberg, J. T., Dosovitskiy, A., Brox, T., and Riedmiller, M., (2014), Striving for simplicity: The all-convolutional net.
Sonoda, S., and Murata, N., (2017), Neural network with unbounded activation functions is universal approximator,Applied and Computational Harmonic Analysis, Vol. 43(2), pp. 233-268.
Chernov, V., Alander, J. and Bochko, V., (2015), Integer-based accurate conversion between RGB and HSV color spaces, Computers & Electrical Engineering, Vol. 46, pp.328-337.
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., and Chen, T., (2018), Recent Advances in Convolutional Neural Networks, Pattern Recognition, Vol. 77, pp. 354-377
Beemkumar, N., Gupta, S., Bhardwaj, S., Dhabliya, D., Rai, M., Pandey, J.K., Gupta, A. Activity recognition and IoT-based analysis using time series and CNN (2023) Handbook of Research on Machine Learning-Enabled IoT for Smart Applications Across Industries, pp. 350-364.
Rajiv, A., Saxena, A.K., Singh, D., Awasthi, A., Dhabliya, D., Yadav, R.K., Gupta, A. IoT and machine learning on smart home-based data and a perspective on fog computing implementation (2023) Handbook of Research on Machine Learning-Enabled IoT for Smart Applications Across Industries, pp. 336-349.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
