Özellik Seçimine Dayalı Güçlendirme Algoritmaları Kullanılarak Beyin Tümörünün Tespiti

Öz

Beyin tümörleri en yaygın ölüm nedenlerinden biridir. Beyin tümörlerinin erken ve doğru tanımlanması etkili tedavi için kritik öneme sahiptir. Beyin tümörü tespitinde geleneksel yöntemler yerine yapay zeka tabanlı yazılım programlarının kullanılması daha doğru sonuçlar sağlayabilir. Özellikle son zamanlarda tıbbi görüntülerin işlenmesine dayalı olarak hastalıkların tespitine yönelik birçok çalışma yapılmaktadır. Bu çalışmada, üç farklı özellik seçme algoritmasına (ki-kare testleri kullanılarak sınıflandırma için tek değişkenli özellik sıralaması (f-chi2), ReliefF algoritması kullanılarak özelliklerin önem sıralaması (f-Relief), sıralama özellikleri) dayalı yeni bir hibrit algoritma önerilmiştir. sınıflandırma için minimum artıklık maksimum alaka algoritması (f-mRMR) kullanılarak klasik ve topluluk öğrenme, sırasıyla farklı çekirdek yapılarına sahip destek vektör makinesine (SVM) ve güçlendirme yöntemleriyle topluluk öğrenmeye (EL) dayalı olarak beyni tespit etmek için gerçekleştirildi. Aşırı uyumu önlemek için manyetik rezonans görüntüleme (MRI) özelliklerini kullanan tümör. Analiz sonuçları, önerilen hibrit yöntemle beyin tümörlerinin tespitinde topluluk bazlı sınıflandırıcıda %100 doğruluk puanına ulaşıldığını göstermektedir. Tümörlerin tespitine yönelik yenilik olarak, karmaşık ağ problemlerinde boyutun azaltılmasına ve dolayısıyla karmaşıklığın azaltılmasına yardımcı olacak istatistik tabanlı özellik seçim yöntemleri önerilmektedir. Önerilen yöntem, gelecekteki çalışmalarda veri boyutunun azaltılmasına yardımcı olabilecek bir özellik seçim algoritması önermektedir.

Anahtar Kelimeler

• Tümör tespiti
• özellik seçimi
• destek vektör makinesi
• topluluk öğrenimi

Detection of Brain Tumor using Boosting Algorithms based on Feature Selection

Öz

Brain tumors are one of the most common causes of death. An early and correct identification of brain tumors is critical for effective therapy. Using artificial intelligence-based software programs instead of traditional methods can provide more accurate results in brain tumor detection. Especially recently, there have been many studies in the detection of diseases based on the processing of medical images. In this study, a novel hybrid algorithm was proposed based on three different feature selection algorithms (univariate feature ranking for classification using chi-square tests (f-chi2), rank the importance of features using ReliefF algorithm (f-Relief), rank features for classification using minimum redundancy maximum relevance algorithm (f-mRMR), and the classic and ensemble learning, respectively based on support vector machine (SVM) with different kernel structures and ensemble learning (EL) with boosting methods, were performed to detect the brain tumor using magnetic resonance imaging (MRI) features. K-fold is used to prevent overfitting. Analysis results show that a 100% accuracy score was achieved in the ensemble-based classifier in the detection of brain tumors with the proposed hybrid method. As a novelty for detecting the tumors, statistics-based feature selection methods are proposed, to help reduce the size and thus reduce complexity in complex network problems. The proposed method suggests a feature selection algorithm that can help reduce the data size in future studies.

Anahtar Kelimeler

• Tumor detection
• feature selection
• support vector machine
• ensemble learning

Kaynakça

1. [1] World Health Organization Report (WHO), 2022. https://www.who.int
2. [2] Doolittle, N.D., “State of the science in brain tumor classification. Paper presented at the Seminars in oncology nursing”, 2004.
3. [3] Vani, N., Sowmya, A., and Jayamma, N., “Brain Tumor Classification using Support Vector Machine. International Research Journal of Engineering and Technology (IRJET)”, 4(7), 792-796, 2017.
4. [4] Mohsen, H, El-Dahshan E.S.A., El-Horbaty E.S.M., and Salem A.B.M., “Classification using Deep Learning Neural Networks for Brain Tumors, Future Computing and Informatics Journal”, 3(1), 68-71, 2018.
5. [5] Shahzadi I, Tang T. B, Meriadeau F., and Quyyum, A., “CNN-LSTM: Cascaded framework for brain tumor classification. IEEE EMBS Conference on Biomedical Engineering and Sciences”, IECBES; 3-6 December, Sarawak, Malaysia: IEEE, 633-637, 2018.
6. [6] Swati, Z.N.K., Zhao, Q., Kabir, M., Ali, F., Ali, Z., Ahmed, S., and Lu, J., “Brain tumor classification for MR images using transfer learning and fine-tuning”, Computerized Medical Imaging and Graphics, 75, 34-46, 2019.
7. [7] Ghahfarrokhi, S.S., and Khodadadi, H., “Human brain tumor diagnosis using the combination of the complexity measures and texture features through magnetic resonance image”, Biomedical Signal Processing and Control, 61, 2020. https://doi.org/10.1016/j.bspc.2020.102025.
8. [8] Al-Saffar, Z.A., and Yildirim, T., “A hybrid approach based on multiple Eigenvalues selection (MES) for the automated grading of a brain tumor using MRI”, Computer Methods and Programs in Biomedicine, 2021, 201, 105945, ISSN 0169-2607, https://doi.org/10.1016/j.cmpb.2021.105945.

9. [9] Nayak, D.R., Padhy, N., Mallick, P.K., and, Singh. A., “A deep autoencoder approach for detection of brain tumor images, Computers and Electrical Engineering”, 2022, 102, 108238, ISSN 0045-7906, https://doi.org/10.1016/j.compeleceng.2022.108238.
10. [10] Isunuri, V.B., and Kakarla, J., “EfficientNet and multi-path convolution with multi-head attention network for brain tumor grade classification, Computers and Electrical Engineering”, 2023, 108, 108700, ISSN 0045-7906, https://doi.org/10.1016/j.compeleceng.2023.108700.
11. [11] D. Rammurthy, P. Mahesh, “Whale Harris Hawks optimization based deep learning classifier for brain tumor detection using MRI images,” Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 6, pp. 3259-3272, 2020.
12. [12] Pendela Kanchanamala, Revathi K.G., M. “Belsam Jeba Ananth, Optimization-enabled hybrid deep learning for brain tumor detection and classification from MRI”, Biomedical Signal Processing and Control, Volume 84, 2023, 104955, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2023.104955.
13. [13] Hastie, T., Tibshirani, R., and Friedman, J., “The Elements of Statistical Learning Data Mining”, Inference, and Prediction, 2007, Second Edition, Springer.
14. [14] Hardle, W.K., and Simar, L., Applied Multivariate Statistical Analysis, Fourth Edition, 2015, Springer.
15. [15] Kononenko, I., Šimec, E., and Robnik-Šikonja, M., “Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF”, Applied Intelligence 7, 1997, 39-55. https://doi.org/10.1023/A:1008280620621.
16. [16] Robnik-Šikonja, M., and Kononenko, I,. “Theoretical and Empirical Analysis of ReliefF and RReliefF. Machine Learning”, 2003, 53, 23-69. https://doi.org/10.1023/A:1025667309714
17. [17] Blum, A.L., and Langley. P., “Selection of Relevant Features and Examples in Machine Learning Artificial Intelligence”, 1997, 97 (1), 245-271.
18. [18] Liu H., and Motoda, H. (Ed.)., Computational Methods of Feature Selection, Chapman and Hall/CRC Data Mining and Knowledge Discovery Series, Kononenko, I and Sikonja, M., 2008, Chapter 9- Non-Myopic Feature Quality Evaluation with (R) ReliefF, New York.
19. [19] Urbanowicz, R.J., Meeker, M., La Cava, W., Olson, R.S., Moore, J.H., “Relief-based feature selection: Introduction and review, Journal of Biomedical Informatics”, 2018, 85, 189-203, ISSN 1532-0464, https://doi.org/10.1016/j.jbi.2018.07.014.
20. [20] Peng, H., Long, F., and Ding, C., "Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy," in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8), 1226-1238, doi: 10.1109/TPAMI.2005.159.
21. [21] EL-Manzalawy, Y., Hsieh, T.Y., and Shivakumar, M., “Min-Redundancy and Max-Relevance Multi-View Feature Selection for Predicting Ovarian Cancer Survival using Multi-Omics Data”, BMC Med Genomics, 2018, 11(3). doi.org/10.1186/s12920-018-0388-0
22. [22] Polikar, R., Ensemble learning. Ensemble machine learning, 2012, 10th ed. Boston, Springer, 1-34.
23. [23] Ozer, E., “Early Diagnosis of Epileptic Seizures over EEG Signals using Deep Learning Approach”, Mimar Sinan Fine Arts University, 2023, Institute of Science and Technology, PhD Thesis.
24. [24] Cortes, C., and Vapnik, V., Support-Vector Networks. Kluwer Academic Publishers, 1995.
25. [25] Van Rijsbergen, C.J., Information Retrieval, London: Butterworths, 1979
26. [26] Fawcett, T., “An introduction to ROC analysis”, Pattern Recognition Letters, 2006, 27(8), 861-874.
27. [27] Hastie, T., Tibshirani, R., and Friedman, J., The Elements of Statistical Learning, Springer, 2009.
28. [28] Powers, D.M., “Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation”, Journal of Machine Learning Technologies, 2011, 2(1), 37-63.
29. [29] Bohaju, J., Brain Tumor Data set, Kaggle, 2020. doi.org/10.34740/KAGGLE/DSV/1370629