Intelligent Brain Tumor Detection in Medical Images using Unsupervised Learning and Optimization Techniques

Subject Areas : Multimedia Processing, Communications Systems, Intelligent Systems

Mohammad Salemifar ¹ , Mohammad reza Mohammadrezaei ²

1 - MSc, Department of Computer Engineering, bardsir Branch, Islamic Azad University, bardsir, Iran,
2 - Assistant Professor, Department of Computer Engineering, Ramhormoz Branch, Islamic Azad University, Ramhormoz ,Iran

Received: 2024-04-30 Accepted : 2024-06-11 Published : 2024-08-18

Keywords: brain tumor detection, feature selection, som neural network, walrus optimizer algorithm,

Abstract :

Introduction: Early and accurate diagnosis of brain tumors, including precise location and size determination on MRI scans, is crucial for successful treatment planning. However, manual tumor detection is time-consuming. Recent advancements in machine learning and optimization algorithms have opened doors for automated medical image analysis. Neural networks, particularly deep networks with a large number of input images, have achieved high accuracy in image processing tasks.

Methodology: This paper proposes a novel approach for brain tumor diagnosis using a Self-Organizing Map (SOM) neural network and the Walrus Optimizer (WO) algorithm. The proposed method consists of four key steps: (1) Preprocessing: Input MRI images undergo preprocessing to enhance their quality. (2) Segmentation: SOM performs image segmentation, dividing the image into distinct regions. (3) Feature Extraction: Features are extracted from the segmented brain tissue to differentiate between healthy and tumorous regions. These features are then used to create a feature vector. (4) Feature Selection: Due to the high computational cost of evaluating all possible feature combinations, the WO algorithm is employed to select an optimal subset of the most discriminative features extracted in the previous step (e.g., using convolutional layers, wavelet transforms, or Gabor filters).

Results: The proposed method is implemented and evaluated using MATLAB software. Performance is measured using standard metrics like precision, accuracy, recall, and F1-score. The proposed approach utilizing SOM and WO achieves an accuracy of 92%, demonstrating a significant improvement of 16% compared to the baseline method with 76% accuracy. Additionally, it surpasses the accuracy of a method employing the Reptile Search Algorithm by 10%.

Discussion: The superior accuracy of the proposed method can be attributed to the combined strengths of the SOM neural network's ability to learn complex relationships in the data and the WO algorithm's effectiveness in selecting the most informative features for brain tumor classification.

References:

]1[ حریری، مهدی ، (1402)، تشخیص چهره در تصویر با استفاده از روش ویولا-جونز و تحلیل بافت تصویر، سامانه‌های پردازشی و ارتباطی چندرسانه‌ای هوشمند .
]2[ موسوی، زینب ، کرمی، الهه ، غلامی، کبری ، (1402)، استفاده از شبکه های عصبی ژانگ با زمان گسسته برای بهینه سازی غیرخطی متغیر با زمان، سامانه‌های پردازشی و ارتباطی چندرسانه‌ای هوشمند.
[3] Sangeeta, D. N. H. (2023). Brain tumor detection and classification with feature extraction and reduction using DWT and PCA. Journal of Survey in Fisheries Sciences, 10(2S), 948-963.
[4] Kandimalla, S. Y., Vamsi, D. M., Bhavani, S., & VM, M. (2023). Recent Methods and Challenges in Brain Tumor Detection Using Medical Image Processing. Recent Patents on Engineering, 17(5), 8-23.
[5] Kumar, A. (2023). Study and analysis of different segmentation methods for brain tumor MRI application. Multimedia Tools and Applications, 82(5), 7117-7139.
[6] Zhu, Z., He, X., Qi, G., Li, Y., Cong, B., & Liu, Y. (2023). Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI. Information Fusion, 91, 376-387.
[7] Qin, C., Li, B., & Han, B. (2023). Fast brain tumor detection using adaptive stochastic gradient descent on shared-memory parallel environment. Engineering Applications of Artificial Intelligence, 120, 105816.
[8] Purni, J. T., Vedhapriyavadhana, R., Jayalakshmi, S. L., & Girija, R. (2023). High Performance Classifier for Brain Tumor Detection Using Capsule Neural Network. In Computer Vision and Machine Intelligence Paradigms for SDGs: Select Proceedings of ICRTAC-CVMIP 2021 (pp. 151-164). Singapore: Springer Nature Singapore.
[9] Baji, F. S., Abdullah, S. B., & Abdulsattar, F. S. (2023). K-mean clustering and local binary pattern techniques for automatic brain tumor detection. Bulletin of Electrical Engineering and Informatics, 12(3), 1586-1594.
[10] Panigrahi, A., & Subasi, A. (2023). Magnetic resonance imagining-based automated brain tumor detection using deep learning techniques. In Applications of Artificial Intelligence in Medical Imaging (pp. 75-107). Academic Press.
[11] Bashkandi, A. H., Sadoughi, K., Aflaki, F., Alkhazaleh, H. A., Mohammadi, H., & Jimenez, G. (2023). Combination of political optimizer, particle swarm optimizer, and convolutional neural network for brain tumor detection. Biomedical Signal Processing and Control, 81, 104434.
[12] Han, M., Du, Z., Yuen, K. F., Zhu, H., Li, Y., & Yuan, Q. (2024). Walrus optimizer: A novel nature-inspired metaheuristic algorithm. Expert Systems with Applications, 239, 122413.
[13] Bedi, K. P., & Jadon, J. S. (2024, January). Comparison of Deep Learning Methods for Detecting Brain Tumor. In 2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence) (pp. 897-901). IEEE.
[14] Curci, A., & Esposito, A. (2024). Detecting Brain Tumors through Multimodal Neural Networks. arXiv preprint arXiv:2402.00038.
[15] Yang, Y., & Razmjooy, N. (2024). Early detection of brain tumors: Harnessing the power of GRU networks and hybrid dwarf mongoose optimization algorithm. Biomedical Signal Processing and Control, 91, 106093.
[16] Bhimavarapu, U., Chintalapudi, N., & Battineni, G. (2024). Brain Tumor Detection and Categorization with Segmentation of Improved Unsupervised Clustering Approach and Machine Learning Classifier. Bioengineering, 11(3), 266.
[17] Joshi, A. A., & Aziz, R. M. (2024). Deep learning approach for brain tumor classification using metaheuristic optimization with gene expression data. International Journal of Imaging Systems and Technology, 34(2), e23007.
[18] Mandle, A. K., Sahu, S. P., & Gupta, G. P. (2024). WSSOA: whale social spider optimization algorithm for brain tumor classification using deep learning technique. International Journal of Information Technology, 1-17.
[19] Neetha, K. S., & Narayan, D. L. (2024). Feature selection using adaptive manta ray foraging optimization for brain tumor classification. Pattern Analysis and Applications, 27(2), 29.
[20] Mohammed, N. A., Khedr, O. E., El-Rabaie, E. S. M., & Khalaf, A. A. (2023). Early detection of brain cancers biomedical sensor with low losses and high sensitivity in the terahertz regime based on photonic crystal fiber technology. Optical and Quantum Electronics, 55(3), 1-21.
[21] Khan, M. A., Khan, A., Alhaisoni, M., Alqahtani, A., Alsubai, S., Alharbi, M., ... & Damaševičius, R. (2023). Multimodal brain tumor detection and classification using deep saliency map and improved dragonfly optimization algorithm. International Journal of Imaging Systems and Technology, 33(2), 572-587.
[22] Pedada, K. R., Rao, B., Patro, K. K., Allam, J. P., Jamjoom, M. M., & Samee, N. A. (2023). A novel approach for brain tumour detection using deep learning based technique. Biomedical Signal Processing and Control, 82, 104549.
[23] Ramtekkar, P. K., Pandey, A., & Pawar, M. K. (2023). Innovative brain tumor detection using optimized deep learning techniques. International Journal of System Assurance Engineering and Management, 1-15.
[24] Harahap, M., Husein, A. M., Deol, S. S., Singh, S., Situmorang, S. D., & Saputra, J. (2022, October). Comparative Analysis of Deep Learning Approach for Detection and Segmentation of Brain Tumor. In 2022 IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM) (pp. 01-05). IEEE.
[25] Raiyan, T., Anonna, H. H., Mondal, S. K., & Khan, M. M. (2022, October). Brain Tumor Detection using Smart Deep Learning. In 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 0186-0190). IEEE.
[26] Mathew, J., & Srinivasan, N. (2022). Deep Convolutional Neural Network with Transfer Learning for Automatic Brain Tumor Detection from MRI. In 2022 International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS) (pp. 1-6). IEEE.
[27] Vankdothu, R., Hameed, M. A., & Fatima, H. (2022). A brain tumor identification and classification using deep learning based on CNN-LSTM method. Computers and Electrical Engineering, 101, 107960.
[28] Abualigah, L., Abd Elaziz, M., Sumari, P., Geem, Z. W., & Gandomi, A. H. (2022). Reptile Search Algorithm (RSA): A nature-inspired meta-heuristic optimizer. Expert Systems with Applications, 191, 116158.
[29] Suresha, D., Jagadisha, N., Shrisha, H. S., & Kaushik, K. S. (2020). Detection of brain tumor using image processing. In 2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC) (pp. 844-848). IEEE.