MR Görüntülerinden Beyin Tümörünün A-ESA Tabanlı Bir Yaklaşımla Otomatik Sınıflandırılması

Abstract

Beyin tümörleri dünya çapında önemli bir patolojik durumu temsil etmektedir. Be-yin içindeki dokunun anormal büyümesiyle karakterize edilen bu tümörler, sağlıklı beyin dokularını yerinden ederek ve kafa içi basıncını yükselterek ciddi bir tehdit oluşturmaktadır. Zamanında müdahale edilmediği takdirde bu durumun sonuçları ölümcül olabilir. Manyetik Rezonans Görüntüleme (MRG), özellikle yumuşak do-kuları incelemek için çok uygun olan güvenilir bir tanı yöntemi olarak öne çık-maktadır. Bu makale, Manyetik Rezonans (MR) görüntülerini kullanarak beyin kanserlerinin otomatik tespiti için yenilikçi bir derin öğrenme tabanlı yaklaşım sunmaktadır. Önerilen metodoloji, MR görüntülerinden derin özellikler çıkarmak için yeni bir Residual-ESA modelinin (A-ESA, yani Residual Convolutional Neural Network) sıfırdan eğitilmesini içermektedir. Önerilen yaklaşım, 2 sınıf (sağlıklı ve tümör) ve 4 sınıf (glioma tümörü, meningioma tümörü, hipofiz tümörü ve tümörsüz) veri setlerinden oluşan iki ayrı veri seti üzerinde değerlendirilmiştir. 2 sınıflı ve 4 sınıflı veri kümeleri için en iyi sınıflandırma doğruluğu sırasıyla %88.23 ve %77.14 idi.

Keywords

• beyin tümörü
• MRG
• derin öğrenme
• sınıflandırma

Automatic Classification of Brain Tumor from MR Images Using an A-ESA Based Approach

Abstract

Brain tumors represent a significant pathological condition globally. Characterized by the aberrant growth of tissue within the brain, they pose a severe threat by displacing healthy brain tissues and elevating intracranial pressure. Without timely intervention, the implications of this condition can be fatal. Magnetic Resonance Imaging (MRI) stands as a dependable diagnostic modality, particularly well-suited for examining soft tissues. This paper introduces an innovative deep learning-based approach for the automatic detection of brain cancers utilizing Magnetic Resonance (MR) images. The proposed methodology involves the training of a novel Residual-ESA model (A-ESA, i.e., Residual Convolutional Neural Network) from the ground up to extract profound features from MR images.The proposed approach was evaluated on two separate data sets consisting of 2 classes (healthy and tumor) and 4 classes (glioma tumor, menin-gioma tumor, pituitary tumor and tumor-free) data sets. The best classification ac-curacy for the 2-class and 4-class datasets was 88.23% and 77.14%, respectively.

Keywords

• brain tumor
• MRI
• deep learning
• classification

References

1. Havaei, M., vd. (2017). Brain tumor segmentation with Deep Neural Networks. Medical Image Analysis, 35, 18–31.
2. American Society of Clinical Oncology. (2021).
3. Petruzzi, A., Finocchiaro, C. Y., Lamperti, E., & Salmaggi, A. (2013). Living with a brain tumor. Supportive Care in Cancer, 21(4), 1105–1111.
4. Mohammed, M., Nalluru, S. S., Tadi, S., & Samineni, R. (2019). Brain tumor image classifica-tion using convolutional neural networks. International Journal of Advanced Science and Technology, 29(5), 928–934.
5. Islam, K., Ali, S., Miah, S., Rahman, M., Alam, S., & Hossain, M. A. (2021). Brain tumor detection in MR image using superpixels, principal component analysis and template-based K-means clustering algorithm. Machine Learning with Applications, 5, 100044.
6. Usman, K., & Rajpoot, K. (2017). Brain tumor classification from multi-modality MRI using wavelets and machine learning. Pattern Analysis and Applications, 20(3), 871–881.
7. Othman, M. F., & Basri, M. A. M. (2011). Probabilistic Neural Network for brain tumor classi-fication. Proceedings - 2011 2nd International Conference on Intelligent Systems, Modelling and Simulation, 136–138.
8. Toğaçar, M., Cömert, Z., & Ergen, B. (2021). Intelligent skin cancer detection applying auto-encoder, MobileNetV2 and spiking neural networks. Chaos, Solitons & Fractals, 144, 110714.

9. Loh, H. W., Ooi, C. P., Aydemir, E., Tuncer, T., Dogan, S., & Acharya, U. R. (2021). Decision support system for major depression detection using spectrogram and convolutional neural network with EEG signals. Expert Systems, e12773.
10. Karadal, C. H., Kaya, M. C., Tuncer, T., Dogan, S., & Acharya, U. R. (2021). Automated classification of remote sensing images using multileveled MobileNetV2 and DWT techniques. Expert Systems with Applications, 185, 115659.
11. Demir, F. (2021). DeepCoroNet: A deep LSTM approach for automated detection of COVID-19 cases from chest X-ray images. Applied Soft Computing, 103, 107160.
12. Demir, F. (2021). DeepBreastNet: A novel and robust approach for automated breast cancer detection from histopathological images. Biocybernetics and Biomedical Engineering, 41(3), 1123–1139.
13. Lu, S. Y., Wang, S. H., & Zhang, Y. D. (2020). A classification method for brain MRI via MobileNet and feedforward network with random weights. Pattern Recognition Letters, 140, 252–260.
14. Talo, M., Baloglu, U. B., Yildirim, O., & Acharya, U. R. (2019). Application of deep transfer learning for automated brain abnormality classification using MR images. Cognitive Systems Research, 54, 176–188.
15. Talo, M., Yildirim, O., Baloglu, U. B., Aydin, G., & Acharya, U. R. (2019). Convolutional neural networks for multi-class brain disease detection using MRI images. Computerized Medical Imaging and Graphics, 78, 101673.
16. Kumar, S., & Mankame, D. P. (2020). Optimization driven Deep Convolution Neural Network for brain tumor classification. Biocybernetics and Biomedical Engineering, 40(3), 1190–1204.
17. Raja, P. M. S., & Rani, A. V. (2020). Brain tumor classification using a hybrid deep autoencoder with Bayesian fuzzy clustering-based segmentation approach. Biocybernetics and Biomedical Engi-neering, 40(1), 440–453.
18. Devi, K. U., & Gomathi, R. (2020). Brain tumour classification using saliency driven nonlinear diffusion and deep learning with convolutional neural networks (CNN). Journal of Ambient Intelli-gence and Humanized Computing, 12(6), 6263–6273.
19. Alhassan, A. M., & Zainon, W. M. N. W. (2021). Brain tumor classification in magnetic reso-nance image using hard swish-based RELU activation function-convolutional neural network. Neural Computing and Applications, 33(15), 9075–9087.
20. Kumar, R. L., Kakarla, J., Isunuri, B. V., & Singh, M. (2021). Multi-class brain tumor classifi-cation using residual network and global average pooling. Multimedia Tools and Applications, 80(9), 13429–13438.
21. Kokkalla, S., Kakarla, J., Venkateswarlu, I. B., & Singh, M. (2021). Three-class brain tumor classification using deep dense inception residual network. Soft Computing, 25(13), 8721–8729.
22. Toğaçar, M., Cömert, Z., & Ergen, B. (2020). Classification of brain MRI using hyper column technique with convolutional neural network and feature selection method. Expert Systems with Ap-plications, 149, 113274.
23. Kang, J., Ullah, Z., & Gwak, J. (2021). MRI-based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors, 21(6), 2222.
24. Chakrabarty, N. Brain MRI images for brain tumor detection.
25. Bhuvaji, S., Kadam, A., Bhumkar, P., Dedge, S., & Kanchan, S. Brain Tumor Classification (MRI).
26. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep con-volutional neural networks. Advances in Neural Information Processing Systems, 1097–1105.
27. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv Preprint arXiv:1409.1556.
28. Demir, F., Abdullah, D. A., & Sengur, A. (2020). A new deep CNN model for environmental sound classification. IEEE Access, 8, 66529–66537.
29. Petmezas, G., vd. (2021). Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets. Biomedical Signal Processing and Control, 63, 102194.
30. Kucharski, A., & Fabijańska, A. (2021). CNN-watershed: A watershed transform with predicted markers for corneal endothelium image segmentation. Biomedical Signal Processing and Control, 68, 102805.
31. Hashemzehi, R., Mahdavi, S. J. S., Kheirabadi, M., & Kamel, S. R. (2020). Detection of brain tumors from MRI images base on deep learning using hybrid model CNN and NADE. Biocybernetics and Biomedical Engineering, 40(3), 1225–1232.
32. Shahabi, M. S., Shalbaf, A., & Maghsoudi, A. (2021). Prediction of drug response in major depressive disorder using ensemble of transfer learning with convolutional neural network based on EEG. Biocybernetics and Biomedical Engineering, 41(3), 946–959.
33. Li, T., Qing, C., & Tian, X. (2018). Classification of heart sounds based on convolutional neural network. Communications in Computer and Information Science, 819, 252–259.
34. Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. 32nd International Conference on Machine Learning (ICML), 1, 448–456.
35. Demir, F., Ismael, A. M., & Sengur, A. (2020). Classification of lung sounds with CNN model using parallel pooling structure. IEEE Access, 8, 105376–105383.
36. Demir, F., Demir, K., & Sengur, A. (2022). DeepCov19Net: Automated COVID-19 disease detection with a robust and effective technique deep learning approach. New Generation Computing, 1–23.
37. Demir, F., Akbulut, Y., Taşcı, B., & Demir, K. (2023). Improving brain tumor classification performance with an effective approach based on new deep learning model named 3ACL from 3D MRI data. Biomedical Signal Processing and Control, 81, 104424.
38. Demir, F., Siddique, K., Alswaitti, M., Demir, K., & Sengur, A. (2022). A simple and effective approach based on a multi-level feature selection for automated Parkinson’s disease detection. Journal of Personalized Medicine, 12(1), 55.
39. Demir, K., Berna, A. R. I., & Demir, F. (2020). Detection of brain tumor with a pre-trained deep learning model based on feature selection using MR images. Fırat University Journal of Experimental and Computational Engineering, 2(1), 23–31.
40. Demir, K., Ay, M., Cavas, M., & Demir, F. (2023). Automated steel surface defect detection and classification using a new deep learning-based approach. Neural Computing and Applications, 35(11), 8389–8406.
41. Toğaçar, M., Cömert, Z., & Ergen, B. (2020). Classification of brain MRI using hyper column technique with convolutional neural network and feature selection method. Expert Systems with Ap-plications, 149, 113274.
42. Demir, F., & Akbulut, Y. (2022). A new deep technique using R-CNN model and L1NSR feature selection for brain MRI classification. Biomedical Signal Processing and Control, 75, 103625.
43. Kang, J., Ullah, Z., & Gwak, J. (2021). MRI-based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors, 21(6), 2222.
44. Reyes, D., & Sánchez, J. (2024). Performance of convolutional neural networks for the classi-fication of brain tumors using magnetic resonance imaging. Heliyon, 10(3).
45. Sharif, M. I., Li, J. P., Khan, M. A., Kadry, S., & Tariq, U. (2024). M3BTCNet: Multi-model brain tumor classification using metaheuristic deep neural network features optimization. Neural Computing and Applications, 36(1), 95–110.