Yeni Bir Beyin Tümörü Tespiti Yaklaşımı: Derin Öğrenme ve Destek Vektör Makinelerinin Entegre Edilmesi

Yıl 2026, Cilt: 28 Sayı: 82, 157 - 162, 27.01.2026

Ezgi Özer

https://doi.org/10.21205/deufmd.2026288220

Öz

Beyin tümörleri insanlarda en sık görülen ölüm nedenleri arasındadır. Beyin kanserlerinin erken ve doğru tespiti etkili tedavi için kritik öneme sahiptir. Bilgisayarlı tomografi, manyetik rezonans görüntüleme, X-ışınları ve ultrason gibi görüntüleme teknikleri hastalık uzmanları tarafından ön referans olarak kullanılmaktadır. Hastalıkları erken teşhis etmek, uzmanların yoğunluğunu azaltmak ve teşhis hatalarını en aza indirmek için sağlık alanında farklı öğrenme stratejileri kullanılmaktadır. Beyin araştırmalarında görüntü işleme çalışmaları son yıllarda makine öğrenmesi ve derin öğrenme modellerinin geliştirilmesi sayesinde başarılı bulgular sağlamaya başlamıştır. Bu çalışmada literatürdeki çalışmalara bir yenilik olarak, önceden eğitilmiş CNN tabanlı özellikler çıkarımı yapılan, SVM tabanlı farklı çekirdeklerle sınıflandırma yapılan bir hibrit algoritma önerilmiştir. Sonuç olarak beyin tümörleri %98 sınıflandırma performansı ile tespit edilmiştir.

Anahtar Kelimeler

Tümör Tespiti , Özellik Çıkarımı , Önceden Eğitilmiş Model , Destek Vektör Makineleri

Proje Numarası

1059B141900679

A Novel Brain Tumor Detection Approach: Integrating Deep Learning and Support Vector Machines

Öz

Brain tumors are among the most common causes of death in humans. Early and accurate detection of brain cancers is critical for effective treatment. Imaging techniques such as computed tomography, magnetic resonance imaging, X-rays, and ultrasound are used as a preliminary reference by illness experts. Different learning strategies have been employed in the field of health to diagnose diseases early, reduce the intensity of experts, and minimize diagnostic errors. Image processing studies in brain research have begun to provide successful findings in recent years, thanks to the developed of machine learning and deep learning models. In this study, as a novelty to the studies in the literature, a hybrid algorithm is proposed that features were extracted with pre-trained based CNN, classification was made with SVM based different kernels. As a result, the brain tumors were detected with 98% classification performance.

Anahtar Kelimeler

Tumor Detection , Feature Extraction , Pre-Trained Models , Support Vector Machine

Proje Numarası

1059B141900679

Kaynakça

• Smith RA, Andrews KS, Brooks D, Fedewa SA, Manassaram-Baptiste D, Saslow D, et al. Cancer screening in the United States, 2017: A review of current American Cancer Society guidelines and current issues in cancer screening. CA Cancer J Clin 2017;67(2):100-21. doi:10.3322/caac.21392.
• Lu G, Fakurnejad S, Martin BA, van den Berg NS, van Keulen S, Nishio N, et al. Predicting Therapeutic Antibody Delivery into Human Head and Neck Cancers. Clin Cancer Res 2020;26(11):2582-94. doi:10.1158/1078-0432.
• WHO. World Health Organization Report. https://www.who.int/health-topics/cancer; 2022.
• Kidwell CS, Hsia AW. Imaging of the Brain and Cerebral Vasculature in Patients with Suspected Stroke: Advantages and Disadvantages of CT and MRI. Current Neurology and Neuroscience Reports 2006;6(1):9-16. doi:10.1007/s11910-996-0003-1.
• Vani N, Sowmya A, Jayamma N. Brain Tumor Classification using Support Vector Machine. International Research Journal of Engineering and Technology (IRJET) 2017;4(7):792-6.
• Mohsen HM, El-Dahshan EA, El-Horbaty EM, Salem AM. Classification using deep learning neural networks for brain tumors. Future Computing and Informatics Journal 2017;3(1):68-71. doi:10.1016/J.FCIJ.2017.12.001.
• Shahzadi I, Tang TB, Meriadeau F, Quyyum A. CNN-LSTM: Cascaded framework for brain tumour classification. IEEE EMBS Conference on Biomedical Engineering and Sciences 2018:633-7.
• Swati ZNK, Zhao Q, Kabir M, Ali F, Ali Z, Ahmed S, et al. Brain Tumor Classification for MR Images using Transfer Learning and Fine-Tuning. Computerized Medical Imaging and Graphics 2019;75:34-46. doi:10.1016/j.compmedimag.2019.05.001.
• Rammurthy D, Mahesh PK. Whale Harris Hawks Optimization based Deep Learning Classifier for Brain Tumor Detection using MRI images. Journal of King Saud University - Computer and Information Sciences 2022;34(6):3259-72. doi:10.1016/j.jksuci.2020.08.006.
• Nayak DR, Padhy N, Mallick PK, Singh A. A deep autoencoder approach for detection of brain tumor images. Computers and Electrical Engineering 2022;102(2).
• Jakhar SP, Nandal A, Dhaka A, Alhudhaif A, Polat K. Brain tumor detection with multi-scale fractal feature network and fractal residual learning. Applied Soft Computing 2024;153:1568-4946.
• Gupta BB, Gaurav A, Arya V. Deep CNN based brain tumor detection in intelligent systems. International Journal of Intelligent Networks 2024;5:30-7.
• Patterson J, Gibson A. Deep Learning A Practitioner’s Approach. 1st ed. O’Reilly; 2017.
• Bishop CM. Neural Network for Pattern Recognition. Microsoft Research Cambridge; 1995.
• Bishop CM. Pattern Recognition and Machine Learning. Springer; 2006.
• Bishop CM. Neural Networks for Pattern Recognition. Oxford University Press; 2010.
• Ozer E. Early Diagnosis of Epileptic Seizures over EEG Signals using Deep Learning Approach. PhD Thesis. Mimar Sinan Fine Arts University, Institute of Science and Technology; 2023.
• Cortes C, Vapnik V. Support-Vector Networks. Kluwer Academic Publishers; 1995.
• LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998;86(11):2278-324.
• Wei D, Anurag B, Jianing W. Deep Learning Essentials: Your Hands-on Guide to the Fundamentals of Deep Learning and Neural Network Modeling. Packt Publishing; 2018.
• Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning. Springer; 2009.
• He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA; 2016, p. 770-8.
• Dong Y, Zhang H, Wang C, Wang Y. Fine-Grained Ship Classification based on Deep Residual Learning for High-Resolution SAR Images. Remote Sens Lett 2019;10(11):1095-104.
• Özer E. Brain Tumor Detection using Deep CNNs and Ensemble Algorithms over MRI Images. Computer Science 2024;9(2):142-50. doi:10.53070/bbd.1455902.
• Van Rijsbergen CJ. Information Retrieval. London: Butterworths; 1979.
• Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters 2006;27(8):861-74. doi:10.1016/j.patrec.2005.10.010.
• Powers D. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. Journal of Machine Learning Technologies 2011;2(1):37-63. doi:10.48550/arXiv.2010.16061.
• Özer E. Detection of Brain Tumor using Boosting Algorithms based on Feature Selection. Researcher 2024;4(2):130-40.
• Nickparvar M. Brain Tumor MRI Dataset, Kaggle. https://doi.org/10.34740/KAGGLE/DSV/2645886; 2021.