CNN-based Binary and Categorical Model to Detect Tumor from MR Images
Keywords:
CNN, Neural Network, Global Average Pooling, MRI, Batch Normalization, Max Pooling, Dropout, Dense layerAbstract
Detecting Brain tumors through human eye inspection has a probability of errors in analysis and a higher number of MRI reports cannot be inspected in a feasible amount of time. Thus, we need an easier automated approach towards this, that can be easily used and can give accurate results in Tumor detection. In this paper, we have implemented a Machine Learning Model based on Convolutional Neural Network, with the help of Global Average Pooling to fulfill this goal. Here we have two models, where one can do a binary classification of the images to detect if they have a trace of tumor in the MR Images or not, and another model that can detect the type of Tumor categorically among 3 types which are Glioma, Meningioma, and Pituitary. This model has acquired an accuracy score of 96.02% and 99.46% in the Binary and Categorical Models respectively.
References
[1] SS. Phaye , A. Sikka, A. Dhall , A. Bathula and D. Bathula, “Dense and Diverse Capsule Networks: Making the Capsules Learn Better”, Asian Conference on Computer Vision, May10, 2018. https://doi.org/10.48550/arXiv.1805.04001.
[2] M. Siar and M. Teshnehlab, "Brain Tumor Detection Using Deep Neural Network and Machine Learning Algorithm," 2019 9th International Conference on Computer and Knowledge Engineering (ICCKE), pp.363-368, 2019. www.doi.org/10.1109/ICCKE48569.2019.8964846.
[3] L. Gaur, M. Bhandari, T. Razdan, S. Mallik, Z. Zhao. “Explanation-Driven Deep Learning Model for Prediction of Brain Tumor Status Using MRI Image Data.” FrontGenet,Mar 14, 2022.
www.doi.org/10.3389/fgene.2022.822666.
[4] E. Av?ar, Salçin K. “Detection and classification of brain tumors from MRI images using faster R-CNN ". Tehni?ki glasnik. 2019;13(4): pp.337–342. 2019. https://doi.org/10.31803/tg-20190712095507.
[5] M.O. Khairandish, M. Sharma, V. Jain, J.M. Chatterjee, N.Z. Jhanjhi, A Hybrid CNN-SVM Threshold Segmentation Approach for Tumor Detection and Classification of MRI Brain Images, IRBM, Volume 43, Issue 4, 2022, Pages 290-299,ISSN1959-0318, https://doi.org/10.1016/j.irbm.2021.06.003.
[6] A. Gumaei, M. M. Hassan, M. R. Hassan, A. Alelaiwi and G. Fortino, "A Hybrid Feature Extraction Method with Regularized Extreme Learning Machine for Brain Tumor Classification," in IEEE Access, vol.7, pp.36266-36273, 2019. www.doi.org/10.1109/ACCESS.2019.2904145.
[7] ARI, AL? and HANBAY, DAVUT "Deep learning-based brain tumor classification and detection system," Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 26: No. 5, Article 9, 2018. https://doi.org/10.3906/elk-1801-8.
[8] J Cheng , W Huang, S Cao , R Yang , W Yang , Z Yun “Enhanced Performance of Brain Tumor Classification via Tumor Region Augmentation and Partition”, PLOS ONE, October8,2015. https://doi.org/10.1371/journal.pone.0140381.
[9] X. W. Gao and R. Hui, "A deep learning based approach to classification of CT brain images," 2016 SAI Computing Conference (SAI), London, UK, pp.28-31, 2016. www.doi.org/10.1109/SAI.2016.7555958.
[10] Y. Xu, Z. Jia, Y. Ai, F. Zhang, M. Lai and E. I. -C. Chang, "Deep convolutional activation features for large scale Brain Tumor histopathology image classification and segmentation," 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, QLD, Australia, pp. 947-951, 2015. www.doi.org/10.1109/ICASSP.2015.7178109.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
