Enhancing Brain Tumor Segmentation with Generative Adversarial Networks and Post-Processing Techniques

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 12

Year of Publication : 2025

Authors : Bashir Sheikh Abdullahi Jama, Mehmet Hacibeyoglu

10.14445/23488549/IJECE-V12I12P113

How to Cite?

Bashir Sheikh Abdullahi Jama, Mehmet Hacibeyoglu, "Enhancing Brain Tumor Segmentation with Generative Adversarial Networks and Post-Processing Techniques," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 12, pp. 154-163, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I12P113

Abstract:

Accurately and reliably segmenting brain tumors from Magnetic Resonance Imaging (MRI) poses a key challenge in medical image analysis because of the variability in shape, size, and intensity distributions of tumors. The present study introduces a hybrid segmentation framework that combines Generative Adversarial Networks (GANs) with a U-Net backbone and post-processing methods to improve tumor segmentation. The model was trained and evaluated on 500 heterogeneous MRI images preprocessed to a resolution of 512 × 512, and split into training (70%), validation (15%), and test (15%) sets. The model training occurred over 50 epochs, with a batch size of 16, and the Adam optimizer was used for training. The model was augmented with data augmentation strategies (e.g., flipping, cropping, scaling, contrast enhancement, etc.), and early stopping was applied to prevent overfitting. The generator employs both cross-entropy and adversarial loss, while the discriminator uses binary cross-entropy loss in its optimization. The experimental results reinforce the usefulness of the proposed framework, with a Dice Similarity Coefficient value of 0.89 ± 0.03, Intersection over Union value of 0.95 ± 0.04, recall value of 0.92 ± 0.03, and specificity value of 0.97 ± 0.02. Furthermore, the comparative evaluation with state-of-the-art methods confirms the superiority of the proposed method, resulting in a precision result of 99.12%, a recall result of 94.24%, an F-score result of 93.36%, and an IoU result of 94.87%, outpacing state-of-the-art models.

Keywords:

Brain Tumor, GANs, Image segmentation, Post-processing, U-net.

References:

[1] P. Purwono et al., “Understanding Generative Adversarial Networks (GANs): A Review,” Control Systems and Optimization Letters, vol. 3, no. 1, pp. 1-10, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Lan Lan et al., “Generative Adversarial Networks and Its Applications in Biomedical Informatics,” Frontiers in Public Health, vol. 8, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] A. Gunasekaran, “Generative Adversarial Networks: A Brief History and Overview,” Journal of Student Research, vol. 12, no. 1, pp. 1 12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Zhaoqing Pan et al., “Recent Progress on Generative Adversarial Networks (GANs): A Survey,” IEEE Access, vol. 7, pp. 36322-36333, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Qiang Wu, and Kenneth R. Castleman, Chapter Seven - Image Segmentation, Microscope Image Processing (Second Edition), pp. 119 152, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jiss Kuruvilla et al., “A Review on Image Processing and Image Segmentation,” 2016 International Conference on Data Mining and Advanced Computing (SAPIENCE), Ernakulam, India, pp. 198-203, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Yue Zhang et al., “Unsupervised X-Ray Image Segmentation with Task Driven Generative Adversarial Networks,” Medical Image Analysis, vol. 62, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Jianning Li et al., “Medical Image Segmentation in Oral-Maxillofacial Surgery,” Computer-Aided Oral and Maxillofacial Surgery Developments, Applications, and Future Perspectives, pp. 1-27, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] David T. Gering et al., “An Integrated Visualization System for Surgical Planning and Guidance Using Image Fusion and an Open MR,” Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, vol. 13, no. 6, pp. 967-975, 2001.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Rahulsinh B. Chauhan et al., “An Overview of Image Processing for Dental Diagnosis,” Innovation and Emerging Technologies, vol. 10, pp. 1-26, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Sara Altun Güven, and Muhammed Fatih Talu, “Brain MRI High Resolution Image Creation and Segmentation with the New GAN Method,” Biomedical Signal Processing and Control, vol. 80, no. 1, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Kambham Pratap Joshi et al., “VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification,” Big Data and Cognitive Computing, vol. 9, no. 2, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Yudong Zhang, and Zhengchao Dong, “Medical Imaging and Image Processing,” Technologies, vol. 11, no. 2, pp. 1-4, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Digvijay Reddy et al., “Brain Tumor Detection Using Image Segmentation Techniques,” 2018 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, pp. 18-22, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Nurul Huda, and Ku Ruhana Ku-Mahamud, “CNN-Based Image Segmentation Approach in Brain Tumor Classification: A Review,” Engineering Proceedings, vol. 84, no. 1, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Eman Abdel-Maksoud, Mohammed Elmogy, and Rashid Al-Awadi, “Brain Tumor Segmentation based on a Hybrid Clustering Technique,” Egyptian Informatics Journal, vol. 16, no. 1, pp. 71-81, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Keiller Nogueira et al., “An Introduction to Deep Morphological Networks.” IEEE Access, vol. 9, pp, 114308-114324, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Sérgio Pereira et al., “Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images,” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1240-1251, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Mohammad Havaei et al., “Brain Tumor Segmentation with Deep Neural Networks,” Medical Image Analysis, vol. 35, pp. 18-31, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Xiaosheng Wu et al., “Diff‐CFFBNet: Diffusion‐Embedded Cross‐Layer Feature Fusion Bridge Network for Brain Tumor Segmentation,” International Journal of Imaging Systems and Technology, vol. 35, no. 3, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Yu Wang et al., “Multimodal Brain Tumor Image Segmentation using WRN-PPNet,” Computerized Medical Imaging and Graphics, vol. 75, pp. 56-65, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Konstantinos Kamnitsas et al., “DeepMedic for Brain Tumor Segmentation,” International Workshop on Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp. 138-149, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Xiaomei Zhao et al., “A Deep Learning Model Integrating FCNNs and CRFs for Brain Tumor Segmentation,” Medical Image Analysis, vol. 43, pp. 98-111, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Sabri Koçer et al., “A Comparative Study for Evaluating the Performance of Various Classification Techniques on Brain Tumour,” Five Zero, vol. 2, no. 1, pp. 1-12, 2022.
[Google Scholar] [Publisher Link]
[25] Shuangting Liu et al., “Pixel Level Data Augmentation for Semantic Image Segmentation Using Generative Adversarial Networks,” ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, pp. 1902 1906, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Ziping Gao et al., “Generative Adversarial Networks for Road Crack Image Segmentation,” 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, pp. 1-8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Vayangi Vishmi Vishara Ganepola, and Torin Wirasingha, “A Novel Framework for Semantic Image Segmentation using Generative Adversarial Networks and Neural Architecture Search,” 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS), Negambo, Sri Lanka, pp. 252-257, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Alankrita Aggarwal, Mamta Mittal, and Gopi Battineni, “Generative Adversarial Network: An Overview of Theory and Applications,” International Journal of Information Management Data Insights, vol. 1, no. 1, pp. 1-9, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Ramy A. Zeineldin et al., “Multimodal CNN Networks for Brain Tumor Segmentation in MRI: A BraTS 2022 Challenge Solution,” Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp. 127-137, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Spyridon Bakas et al., “Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge,” arXiv Preprint, pp. 1-49, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Spyridon Bakas et al., “Advancing The Cancer Genome Atlas Glioma MRI Collections with Expert Segmentation Labels and Radiomic Features,” Scientific Data, vol. 4, pp. 1-13, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Biting Yu et al., “SA-LuT-Nets: Learning Sample-Adaptive Intensity Lookup Tables for Brain Tumor Segmentation,” IEEE Transactions on Medical Imaging, vol. 40, no. 5, pp. 1417-1427, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[33] S. Raghavendra et al., “Multilayer Stacked Probabilistic Belief Network - Based Brain Tumor Segmentation and Classification,” International Journal of Foundations of Computer Science, vol. 33, no. 06n07, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Jinglin Yuan, “Brain Tumor Image Segmentation Method using Hybrid Attention Module and Improved Mask RCNN,” Scientific Reports, vol. 14, pp. 1-13, 2024.
[CrossRef] [Google Scholar] [Publisher Link]