SavedAdd your journal

Journals / Türk Doğa ve Fen Dergisi / 2026 / Cilt: 15 Sayı: 2

Enhancing Reliability in Deep Learning Diagnosis of Brain Tumors Using Grad-CAM

Derin Öğrenme ile Beyin Tümörlerinin Teşhisinde Grad-CAM Kullanarak Güvenilirliğin Artırılması

Musab Coskun(BİNGÖL ÜNİVERSİTESİ, MÜHENDİSLİK-MİMARLIK FAKÜLTESİ, ELEKTRİK-ELEKTRONİK MÜHENDİSLİĞİ BÖLÜMÜ)0000-0001-8323-2330
Pages
39–48
Publication Date
2026-07-01
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This blend of interpretability offers a promising step toward creating more reliable and understandable tools for diagnosing brain tumors.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:While deep learning models in medical imaging have gained popularity as a means to enhance patient outcomes and diagnostic accuracy recently, one of their main issues is interpretability, which is essential to understanding and debugging the model.
📊
Key Findings & Data:We compare the effectiveness of ResNet50, DenseNet121, MobileNetV2 and ConvNeXtTiny architectures.
💡
Conclusion & Impact:This blend of interpretability offers a promising step toward creating more reliable and understandable tools for diagnosing brain tumors.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Tümör Teşhisi · Derin Öğrenme · Grad-CAM

Abstract

While deep learning models in medical imaging have gained popularity as a means to enhance patient outcomes and diagnostic accuracy recently, one of their main issues is interpretability, which is essential to understanding and debugging the model. Explainable Artificial Intelligence (XAI) is a recent rising research direction that aims to explain this black box part of the deep learning models. For quick identification, clinical evaluations and imaging methods such as Magnetic Resonance Imaging (MRI) scans, are frequently utilized; nevertheless, manual analysis has challenges such as subjectivity and delays. On the other hand, AI-based models convey a more rapid and reliable approach to classifying and detecting brain tumors. In this work, we present a transparent and explainable framework of pre-trained Convolutional Neural Network (CNN) models combined with Gradient Weighted Class Activation Mapping (Grad-CAM) for the classification of brain MRI images. We compare the effectiveness of ResNet50, DenseNet121, MobileNetV2 and ConvNeXtTiny architectures. We obtained a test accuracy of 100% and precision-recall scores above 99.90%, highlighting the model's effectiveness in identifying whether a tumor is present. The results illustrate how the models have enhanced localization skills by visualizing the regions of focus in the predictions through the application of the Grad-CAM method. This blend of interpretability offers a promising step toward creating more reliable and understandable tools for diagnosing brain tumors.

Özet

Tıbbi görüntülemede derin öğrenme modelleri, hasta sonuçlarını ve tanı doğruluğunu iyileştirmenin bir yolu olarak son zamanlarda popülerlik kazanmış olsa da, bu modellerin temel sorunlarından biri, modeli anlamak ve hata ayıklamak için gerekli olan yorumlanabilirliktir. Açıklanabilir Yapay Zeka (XAI), derin öğrenme modellerinin bu kara kutu kısmını açıklamayı amaçlayan, son zamanlarda yükselen bir araştırma yönüdür. Hızlı tanımlama için, manyetik rezonans görüntüleme (MRI) taramaları gibi klinik değerlendirmeler ve görüntüleme yöntemleri sıklıkla kullanılır; ancak manuel analiz, öznellik ve gecikmeler gibi zorluklar içerir. Öte yandan, yapay zeka tabanlı modeller, beyin tümörlerini sınıflandırma ve tespit etme konusunda daha hızlı ve güvenilir bir yaklaşım sunar. Bu çalışmada, beyin MRI görüntülerinin sınıflandırılması için önceden eğitilmiş Evrişimli Sinir Ağı (CNN) modellerinin Gradyen Ağırlıklı Sınıf Aktivasyon Haritalama (Grad-CAM) ile birleştirildiği şeffaf ve açıklanabilir bir çerçeve sunuyoruz. ResNet50, DenseNet121, MobileNetV2 ve ConvNeXtTiny mimarilerinin etkinliğini karşılaştırıyoruz. %100 test doğruluğu ve %99,90'ın üzerinde hassasiyet-geri çağırma puanları elde ettik, bu da modelin tümörün varlığını tespit etmedeki etkinliğini vurgulamaktadır. Sonuçlar, Grad-CAM yönteminin uygulanmasıyla tahminlerde odaklanılan bölgeleri görselleştirerek modellerin lokalizasyon becerilerini nasıl geliştirdiğini göstermektedir. Bu yorumlanabilirlik özelliği, beyin tümörlerini teşhis etmek için daha güvenilir ve anlaşılır araçlar oluşturma yolunda umut verici bir adımdır.

🔖

Cite This Article

Coskun, M. (2026). Enhancing Reliability in Deep Learning Diagnosis of Brain Tumors Using Grad-CAM. Türk Doğa ve Fen Dergisi, Cilt: 15 Sayı: 2, 39–48. https://doi.org/10.46810/tdfd.1749282

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (30)

  1. H. ZainEldin et al., “Brain Tumor Detection and Classification Using Deep Learning and Sine-Cosine Fitness Grey Wolf Optimization,” Bioeng. Basel Switz., vol. 10, no. 1, p. 18, Dec. 2022, doi: 10.3390/bioengineering10010018.
  2. M. Zubair, I. A. Rana, Y. Islam, and S. A. Khan, “Variable Structure Based Control for the Chemotherapy of Brain Tumor,” IEEE Access, vol. 9, pp. 107333–107346, 2021, doi: 10.1109/ACCESS.2021.3091632.
  3. J. Amin, M. Sharif, A. Haldorai, M. Yasmin, and R. S. Nayak, “Brain tumor detection and classification using machine learning: a comprehensive survey,” Complex Intell. Syst., vol. 8, no. 4, pp. 3161–3183, Aug. 2022, doi: 10.1007/s40747-021-00563-y.
  4. S. Jayade, D. T. Ingole, and M. D. Ingole, “Review of Brain Tumor Detection Concept using MRI Images,” in 2019 International Conference on Innovative Trends and Advances in Engineering and Technology (ICITAET), Dec. 2019, pp. 206–209. doi: 10.1109/ICITAET47105.2019.9170144.
  5. W. Ayadi, W. Elhamzi, I. Charfi, and M. Atri, “Deep CNN for Brain Tumor Classification,” Neural Process. Lett., vol. 53, no. 1, pp. 671–700, Feb. 2021, doi: 10.1007/s11063-020-10398-2.
  6. M. Nazir, S. Shakil, and K. Khurshid, “Role of deep learning in brain tumor detection and classification (2015 to 2020): A review,” Comput. Med. Imaging Graph., vol. 91, p. 101940, Jul. 2021, doi: 10.1016/j.compmedimag.2021.101940.
  7. S. Saeedi, S. Rezayi, H. Keshavarz, and S. R. Niakan Kalhori, “MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques,” BMC Med. Inform. Decis. Mak., vol. 23, no. 1, p. 16, Jan. 2023, doi: 10.1186/s12911-023-02114-6.
  8. K. H. Jin, M. T. McCann, E. Froustey, and M. Unser, “Deep Convolutional Neural Network for Inverse Problems in Imaging,” IEEE Trans. Image Process., vol. 26, no. 9, pp. 4509–4522, Sep. 2017, doi: 10.1109/TIP.2017.2713099.
  9. N. K. E. Abbadi and N. E. Kadhim, “Brain Tumor Classification Based on Singular Value Decomposition,” IJARCCE, vol. 5, no. 8, pp. 553–557, Aug. 2016, doi: 10.17148/IJARCCE.2016.58116.
  10. M. Basthikodi, M. Chaithrashree, B. M. Ahamed Shafeeq, and A. P. Gurpur, “Enhancing multiclass brain tumor diagnosis using SVM and innovative feature extraction techniques,” Sci. Rep., vol. 14, no. 1, p. 26023, Oct. 2024, doi: 10.1038/s41598-024-77243-7.
  11. F. Citak-Er, Z. Firat, I. Kovanlikaya, U. Ture, and E. Ozturk-Isik, “Machine-learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3T,” Comput. Biol. Med., vol. 99, pp. 154–160, Aug. 2018, doi: 10.1016/j.compbiomed.2018.06.009.
  12. M. Pareek, C. K. Jha, and S. Mukherjee, “Brain Tumor Classification from MRI Images and Calculation of Tumor Area,” in Soft Computing: Theories and Applications, M. Pant, T. K. Sharma, O. P. Verma, R. Singla, and A. Sikander, Eds., Singapore: Springer, 2020, pp. 73–83. doi: 10.1007/978-981-15-0751-9_7.
  13. W. Ayadi, I. Charfi, W. Elhamzi, and M. Atri, “Brain tumor classification based on hybrid approach,” Vis. Comput., vol. 38, no. 1, pp. 107–117, Jan. 2022, doi: 10.1007/s00371-020-02005-1.
  14. R. S. Misu, “Brain Tumor Detection Using Deep Learning Approaches,” Sep. 21, 2023, arXiv: arXiv:2309.12193. doi: 10.48550/arXiv.2309.12193.
  15. D. Lu, N. Polomac, I. Gacheva, E. Hattingen, and J. Triesch, “Human-Expert-Level Brain Tumor Detection Using Deep Learning with Data Distillation And Augmentation,” in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun. 2021, pp. 3975–3979. doi: 10.1109/ICASSP39728.2021.9415067.
  16. A. A. Dehkordi, M. Hashemi, M. Neshat, S. Mirjalili, and A. S. Sadiq, “Brain Tumor Detection and Classification Using a New Evolutionary Convolutional Neural Network,” Apr. 26, 2022, arXiv: arXiv:2204.12297. doi: 10.48550/arXiv.2204.12297.
  17. M. M. Zahoor et al., “A New Deep Hybrid Boosted and Ensemble Learning-Based Brain Tumor Analysis Using MRI,” Sensors, vol. 22, no. 7, p. 2726, Apr. 2022, doi: 10.3390/s22072726.
  18. Y. Zhang, S. Wang, H. Wu, K. Hu, and S. Ji, “Brain Tumors Classification for MR images based on Attention Guided Deep Learning Model,” in 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Nov. 2021, pp. 3233–3236. doi: 10.1109/EMBC46164.2021.9630571.
  19. M. Arabahmadi, R. Farahbakhsh, and J. Rezazadeh, “Deep Learning for Smart Healthcare—A Survey on Brain Tumor Detection from Medical Imaging,” Sensors, vol. 22, no. 5, Art. no. 5, Jan. 2022, doi: 10.3390/s22051960.
  20. M. K. Abd-Ellah, A. I. Awad, A. A. M. Khalaf, and H. F. A. Hamed, “A review on brain tumor diagnosis from MRI images: Practical implications, key achievements, and lessons learned,” Magn. Reson. Imaging, vol. 61, pp. 300–318, Sep. 2019, doi: 10.1016/j.mri.2019.05.028.
  21. A. Anil, A. Raj, H. Aravind Sarma, N. C. R, and D. P L, “Brain Tumor detection from brain MRI using Deep Learning,” Int. J. Innov. Res. Appl. Sci. Eng., vol. 3, no. 2, p. 458, Aug. 2019, doi: 10.29027/IJIRASE.v3.i2.2019.458-465.
  22. S. Gajula and V. Rajesh, “Deep Learning based Analysis of MRI Images for Brain Tumor Diagnosis,” Int. J. Adv. Comput. Sci. Appl. IJACSA, vol. 14, no. 2, Art. no. 2, Dec. 2023, doi: 10.14569/IJACSA.2023.0140234.
  23. C. Cao et al., “Deep Learning and Its Applications in Biomedicine,” Genomics Proteomics Bioinformatics, vol. 16, no. 1, pp. 17–32, Feb. 2018, doi: 10.1016/j.gpb.2017.07.003.
  24. M. W. Nadeem et al., “Brain Tumor Analysis Empowered with Deep Learning: A Review, Taxonomy, and Future Challenges,” Brain Sci., vol. 10, no. 2, p. 118, Feb. 2020, doi: 10.3390/brainsci10020118.
  25. D. R. Yerukalareddy and E. Pavlovskiy, “Brain Tumor Classification based on MR Images using GAN as a Pre-Trained Model,” in 2021 IEEE Ural-Siberian Conference on Computational Technologies in Cognitive Science, Genomics and Biomedicine (CSGB), May 2021, pp. 380–384. doi: 10.1109/CSGB53040.2021.9496036.
  26. Z. Liu et al., “Deep learning based brain tumor segmentation: a survey,” Complex Intell. Syst., vol. 9, no. 1, pp. 1001–1026, Feb. 2023, doi: 10.1007/s40747-022-00815-5.
  27. “Brian Tumor Dataset.” Accessed: Jun. 03, 2025. [Online]. Available: https://www.kaggle.com/datasets/preetviradiya/brian-tumor-dataset
  28. “Brain Tumor Classification (MRI).” Accessed: Jun. 03, 2025. [Online]. Available: https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri
  29. F. Doğan, M. Aktaş, ve M. İ. Gürsoy, “Classification of Skin Diseases with Different Deep Learning Models and Comparison of the Performances of the Models”, TDFD, c. 13, sy 3, ss. 117–123, Eyl. 2024, doi: 10.46810/tdfd.1502471.
  30. A. Gümüş, “Classification of Microscopic Fungi Images Using Vision Transformers for Enhanced Detection of Fungal Infections”, TDFD, c. 13, sy 1, ss. 152–160, Mar. 2024, doi: 10.46810/tdfd.1442556.