Optimizing Brain Tumor Classification with Freeze-5 VGG16 and Dataset Fusion

Vicky; Ronsen Purba

doi:10.56741/jnest.v4i02.999

Optimizing Brain Tumor Classification with Freeze-5 VGG16 and Dataset Fusion

Authors

Vicky Mikroskil University
Ronsen Purba Universitas Mikroskil

DOI:

https://doi.org/10.56741/jnest.v4i02.999

Keywords:

Brain Tumor Classification, VGG16, Dataset Fusion, Fine-Tuning, Data Augmentation

Abstract

Magnetic resonance imaging (MRI)-based brain tumor classification is pivotal for early diagnosis and treatment planning. This study enhances the VGG16 pretrained model through freeze-5 fine-tuning (i.e., freezing the first five convolutional layers) and dataset fusion of two public repositories, yielding 5,023 training and 1,311 testing images. Preprocessing includes normalization and grayscale-to-RGB conversion, followed by moderate augmentation (rotation ≤ 15°, shift ≤ 0.1, zoom ≤ 0.1, brightness [0.9–1.1]). The base VGG16 (without top layers) is extended with GlobalAveragePooling2D, Dense (1024, ReLU), Dropout (0.5), and Dense (4, softmax) layers. The model is compiled with the Adam optimizer (lr=1e-4), EarlyStopping, and ReduceLROnPlateau callbacks. On the test set, the proposed configuration achieves peak accuracy of 99.16 % and macro-F1 of 0.99, outperforming prior hybrid approaches. An ablation study confirms that the freeze-5 strategy combined with data augmentation significantly boosts generalization without overfitting. These results underscore the critical role of optimal layer-freezing and dataset fusion in brain tumor classification. Future work will explore ensemble architecture and real-time clinical deployment.

Downloads

Download data is not yet available.

Author Biographies

Vicky, Mikroskil University

Vicky is a Master’s candidate in the Information Technology program at Universitas Mikroskil, Medan, Indonesia, where he is researching deep‐learning approaches for brain tumor classification (email: vicky@students.mikroskil.ac.id ).

Ronsen Purba, Universitas Mikroskil

Ronsen Purba is a Lecturer in Master of Information Technology (MTI) Program at Universitas Mikroskil, Medan, Indonesia (email: ronsen@mikroskil.ac.id).

References

R. Rudiansyah and A. Husein, “Klasifikasi Tumor Otak pada gambar Magnetic Resonance Images (MRI) dengan Pendekatan Pembelajaran Mendalam,” Data Sci. Indones., vol. 4, no. 1, pp. 62–68, Jul. 2024, doi: 10.47709/dsi.v4i1.4265. [Eng Trans: Classification of Brain Tumors on Magnetic Resonance Images (MRI) with Deep Learning Approach]. DOI: https://doi.org/10.47709/dsi.v4i1.4265

Y. Chen, “Comparative Analysis of Brain Tumor Classification and Models Based on VGG16,” in Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence, SCITEPRESS - Science and Technology Publications, pp. 652–658, 2024. doi: 10.5220/0012961300004508. DOI: https://doi.org/10.5220/0012961300004508

A. Muis, S. Sunardi, and A. Yudhana, “Medical Image Classification of Brain Tumor using Convolutional Neural Network Algorithm,” J. Infotel, vol. 15, no. 3, pp. 227–232, 2023, doi: 10.20895/infotel.v15i3.964. DOI: https://doi.org/10.20895/infotel.v15i3.964

C. B. Muddaraju, Shrinivasa, S. Narasimhamurthy, and V. Sontakke, “Automated Diagnosis of Brain Tumor Classification and Segmentation of Magnetic Resonance Imaging Images,” IAES Int. J. Artif. Intell., vol. 13, no. 4, pp. 4833–4842, 2024, doi: 10.11591/ijai.v13.i4.pp4833-4842. DOI: https://doi.org/10.11591/ijai.v13.i4.pp4833-4842

M. N. Musa, “MRI-Based Brain Tumor Classification using ResNet-50 and Optimized Softmax Regression,” J. Infotel, vol. 16, no. 3, Sep. 2024, doi: 10.20895/infotel.v16i3.1175. DOI: https://doi.org/10.20895/infotel.v16i3.1175

S. Y. Prasetyo and G. Z. Nabiilah, “Perbandingan Model Machine Learning pada Klasifikasi Tumor Otak Menggunakan Fitur Discrete Cosine Transform,” J. Teknol. Terpadu, vol. 9, no. 1, pp. 29–34, 2023. [Eng Trans: Comparison of Machine Learning Models for Brain Tumor Classification Using Discrete Cosine Transform Features]. DOI: https://doi.org/10.54914/jtt.v9i1.605

F. Citra R, F. Indriyani, and I. R. Rahadjeng, “Klasifikasi Tumor Otak Berbasis Magnetic Resonance Imaging menggunakan Algoritma Convolutional Neural Network,” Digit. Transform. Technol., vol. 3, no. 2, pp. 918–924, Jan. 2024, doi: 10.47709/digitech.v3i2.3469. [Eng Trans: Magnetic Resonance Imag-ing Based Brain Tumor Classification Using Convolutional Neural Network Algorithm]. DOI: https://doi.org/10.47709/digitech.v3i2.3469

A. Nurhidayat, W. A. Arrosyid, and R. Samsinar, “Prediksi Tumor Otak Menggunakan Metode Convolutional Neural Network (CNN) dan Algoritma Decision Tree,” Seminar Nasional Teknologi & Sains. Vol. 4. No. 1. 2025. 2025. [Eng Trans: Brain Tumor Prediction Using Convolutional Neural Network (CNN) Method and Decision Tree Algorithm].

B. Ulu, “Comparison of Deep Learning Methods in Brain Tumor Diagnosis: High-Performance Classification with MRI Data,” Commun. Fac. Sci. Univ. Ankara Ser. A2-A3 Phys. Sci. Eng., vol. 67, no. 1, pp. 59–73, Feb. 2025, doi: 10.33769/aupse.1619837. DOI: https://doi.org/10.33769/aupse.1619837

A. Biswas and M. S. Islam, “A Hybrid Deep CNN-SVM Approach for Brain Tumor Classification,” J. Inf. Syst. Eng. Bus. Intell., vol. 9, no. 1, pp. 1–15, 2023, doi: 10.20473/jisebi.9.1.1-15. DOI: https://doi.org/10.20473/jisebi.9.1.1-15

E. U. Haq, H. Jianjun, X. Huarong, K. Li, and L. Weng, “A Hybrid Approach Based on Deep CNN and Machine Learning Classifiers for the Tumor Segmentation and Classification in Brain MRI,” Comput. Math. Methods Med., vol. 2022, 2022, doi: 10.1155/2022/6446680. DOI: https://doi.org/10.1155/2022/6446680

M. A. Purnama Wibowo, Muhammad Bima Al Fayyadl, Yufis Azhar, and Zamah Sari, “Classification of Brain Tumors on MRI Images Using Convolutional Neural Network Model EfficientNet,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 4, pp. 538–547, Aug. 2022, doi: 10.29207/resti.v6i4.4119. DOI: https://doi.org/10.29207/resti.v6i4.4119

S. Aksoy, “Brain Tumor Detection and Classification via VGG16-Based Deep Learning on MRI Imaging,” Int. J. Multidiscip. Res., vol. 7, no. 2, Mar. 2025, doi: 10.36948/ijfmr.2025.v07i02.39435. DOI: https://doi.org/10.36948/ijfmr.2025.v07i02.39435

O. A. Supriadi, E. Utami, and D. Ariatmanto, “Deteksi Tumor Otak Melalui Gambar MRI Berdasarkan Vision Transformers dengan Tensorflow dan Keras,” J. Inform. Univ. Pamulang, vol. 8, no. 3, pp. 385–392, Sep. 2023, doi: 10.32493/informatika.v8i3.32707. [Eng Trans: Brain Tumor Detection Through MRI Images Based on Vi-sion Transformers with Tensorflow and Keras] DOI: https://doi.org/10.32493/informatika.v8i3.32707

B. Babu Vimala, S. Srinivasan, S. K. Mathivanan, Mahalakshmi, P. Jayagopal, and G. T. Dalu, “Detection and Classification of Brain Tumor using Hybrid Deep Learning Models,” Sci. Rep., vol. 13, no. 1, pp. 1–18, 2023, doi: 10.1038/s41598-023-50505-6. DOI: https://doi.org/10.1038/s41598-023-50505-6

D. S. Wankhede, C. J.shelke, V. K. Shrivastava, R. Achary, and S. N. Mohanty, “Brain Tumor Detection and Classification Using Adjusted InceptionV3, AlexNet, VGG16, VGG19 with ResNet50-152 CNN Model,” EAI Endorsed Trans. Pervasive Heal. Technol., vol. 10, 2024, doi: 10.4108/eetpht.10.6377. DOI: https://doi.org/10.4108/eetpht.10.6377

S. Li, “Classification of Brain Tumors Based on Magnetic Resonance Imaging (MRI) using Deep Learning Models,” Appl. Comput. Eng., vol. 40, no. 1, pp. 247–254, Feb. 2024, doi: 10.54254/2755-2721/40/20230660. DOI: https://doi.org/10.54254/2755-2721/40/20230660

Maria Nadeem, “Brain Tumor MRI Image Classification:ResNet50,” Kaggle. [Online]. Available: https://www.kaggle.com/code/marianadeem755/brain-tumor-mri-image-classification-resnet50/input

Awsaf, “Brain Tumor Segmentation (BraTS2020),” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/awsaf49/brats2020-training-data

Z. Li and X. Zhou, “A Global-Local Parallel Dual-Branch Deep Learning Model with Attention-Enhanced Feature Fusion for Brain Tumor MRI Classification,” Comput. Mater. Contin., vol. 83, no. 1, pp. 739–760, 2025, doi: 10.32604/cmc.2025.059807. DOI: https://doi.org/10.32604/cmc.2025.059807

B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, J. Kirby, et al. "The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)", IEEE Transactions on Medical Imaging 34(10), 1993-2024 (2015) DOI: 10.1109/TMI.2014.2377694 DOI: https://doi.org/10.1109/TMI.2014.2377694

S. Bakas, H. Akbari, A. Sotiras, M. Bilello, M. Rozycki, J.S. Kirby, et al., "Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features", Nature Scientific Data, 4:170117, 2017, DOI: 10.1038/sdata.2017.117 DOI: https://doi.org/10.1038/sdata.2017.117

S. Bakas, M. Reyes, A. Jakab, S. Bauer, M. Rempfler, A. Crimi, et al., "Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge", arXiv preprint arXiv:1811.02629, 2018.

A. Çinar and M. Yıldırım, “Detection of Tumors on Brain MRI Images Using the Hybrid Convolutional Neural Network Architecture,” Medical Hypotheses, vol. 139, article 109684, 2020. DOI: https://doi.org/10.1016/j.mehy.2020.109684

Díaz-Pernas, F. J., Martínez-Zarzuela, M., Antón-Rodríguez, M. & González-Ortega, D. A Deep Learning Approach for Brain Tumor Classifcation and Segmentation Using a Multiscale Convolutional Neural Network. Feature Papers Artif. Intell. Med. Vol 9, No.2, pp. 1–14, 2021. doi: 10.3390/healthcare9020153. DOI: https://doi.org/10.3390/healthcare9020153

M. S. Majib, M. D. M. Rahman, T. M. S. Sazzad, N. I. Khan, and S. K. Dey, “VGG-SCNet: A VGG Net-Based Deep Learning Framework for Brain Tumor Detection on MRI Images,” IEEE Access, vol. 9, pp. 116942–116952, 2021, doi: 10.1109/ACCESS.2021.3105874. DOI: https://doi.org/10.1109/ACCESS.2021.3105874

Sarkar, A., Maniruzzaman, M. A. & Alahe, M. A. An Efective and Novel Approach for Brain Tumor Classifcation using Alexnet CNN Feature Extractor and Multiple Eminent Machine Learning Classifers in MRIs. J. Sensors Hindawi 1224619, 1–19 (2023). DOI: https://doi.org/10.1155/2023/1224619