Abstract
Accurate and timely diagnosis of brain tumors is vital for improving patient outcomes and guiding treatment. Traditional diagnostic methods can be subjective and inconsistent, making automated systems that use deep learning and machine learning technologies essential. This research develops a Python-based system using Matplotlib, Pandas, NumPy, TensorFlow, Keras, and OpenCV for brain tumor classification. OpenCV handles MRI image preprocessing tasks such as segmentation and normalization, which are crucial for accurate analysis. Convolutional Neural Networks (CNNs) implemented with TensorFlow and Keras offer precise tumor classification. NumPy supports data handling, pandas manages dataset organization, and Matplotlib produces visual representations of the results. The Brain Tumor Segmentation (BraTS 2021) dataset is used for training and testing. The performance is measured using accuracy, precision, recall, and F1-score. The CNN models like ResNet 50, Inception-V3, EfficientNetB3 and VGG16 is compared in the study to conclude with the optimal method to improve classification robustness. This study would enhances diagnostic tools in medical imaging by identifying an optimal algorithm for precision medicine, aiming for early diagnosis, improved treatment outcomes, reduced workload for healthcare professionals, and better public health.
References
- enze, B. H., et al. (2015). The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Transactions on Medical Imaging, 34(10), 1993-2024.
- Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
- He, K., et al. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770- 778.
- Abadi, Martín, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin et al. "{TensorFlow}: a system for {Large-Scale} machine learning." In 12th USENIX symposium on operating systems design and implementation (OSDI 16), pp. 265-283. 2016.
- Abiwinanda, Nyoman, Muhammad Hanif, S. Tafwida Hesaputra, Astri Handayani, and Tati Rajab Mengko. "Brain tumor classification using convolutional neural network." In World Congress on Medical Physics and Biomedical Engineering 2018: June 3-8, 2018, Prague, Czech Republic (Vol. 1), pp. 183-189. Springer Singapore, 2019.
- Mehrotra, Rajat, M. A. Ansari, Rajeev Agrawal, and R. S. Anand. "A transfer learning approach for AI-based classification of brain tumors." Machine Learning with Applications 2 (2020): 100003.
- Nagaraju, G., Rajiv Kumar Nath, P. Chinniah, K. Balasubramanian, S. Kirubakaran, and Balasubbareddy Mallala. "A Comparative analysis of Advanced Machine Learning Techniques for Enhancing Brain Tumor Detection." Journal of Electrical Systems 20, no. 2s (2024): 901-909.
- Borole, Vipin Y., Sunil S. Nimbhore, and Dr Seema S. Kawthekar. "Image processing techniques for brain tumor detection: A review." International Journal of Emerging Trends & Technology in Computer Science (IJETTCS) 4, no. 5 (2015): 2.
- Sharma, Neeraj, and Lalit M. Aggarwal. "Automated medical image segmentation techniques." Journal of medical physics 35, no. 1 (2010): 3-14.
- Amin, Javaria, Muhammad Sharif, Anandakumar Haldorai, Mussarat Yasmin, and Ramesh Sundar Nayak. "Brain tumor detection and classification using machine learning: a comprehensive survey." Complex & intelligent systems 8, no. 4 (2022): 3161-3183
- Qureshi, Shahzad Ahmad, Lal Hussain, Usama Ibrar, Eatedal Alabdulkreem, Mohamed K. Nour, Mohammed S. Alqahtani, Faisal Mohammed Nafie, Abdullah Mohamed, Gouse Pasha Mohammed, and Tim Q. Duong. "Radiogenomic classification for MGMT promoter methylation status using multi-omics fused feature space for least invasive diagnosis through mpMRI scans." Scientific reports 13, no. 1 (2023): 3291.