Conference Paper2026

A Morphology-Aware Preprocessing Pipeline for Improved Glioblastoma Segmentation in Brain MRI Using Hybrid Segformer

Atif Iqbal, Mohammed Raiyan Nur Hridoy, Ilma Hossain Mim, Riyadul Islam, Siam Tahsin Bhuiyan, Sefatul Wasi, Farhana Sarkar, Saadia Binte Alam

2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN)

IEEE, pp. 1-6

  • Good Health and Well-being — Relevance: 93%
DOI: 10.1109/qpain69676.2026.11546603URL

Abstract

Glioblastoma (GBM) is recognized as most aggressive and frequently diagnosed malignant brain tumor in the adult population. Its infiltrative pattern and rapid growth makes accurate identification and segmentation of tumor regions crucial for diagnosis and treatment planning. Magnetic resonance imaging (MRI) is a non-invasive medical imaging technique that plays a critical role in the diagnosis of glioblastoma. This study uses MRI scans to train models as they offer high-resolution images of soft tissues, aiding tumor detection. The Brain Tumor Progression Dataset was utilized, which contains the corresponding tumor mask as the ground truth. For the segmentation architecture, we utilized Segformer with the CNN-based models ResNet18, EfficientNet-B3, MobileNet-V2, and DenseNet201 as the encoder. We aimed to implement preprocessing on the annotated tumor masks in such a manner that CNN models can easily recognize the pattern of the tumor masks. It makes the segmentation task more precise during testing. Initially, to train the models, T1 post contrast MRI scans were used, and after training the model with various encoders, EfficientNet-B3 yielded the best results by achieving a precision of 65.85% along with a Recall of 61.68% and a Dice Score of 63.70%. Preprocessing steps were applied to the ground truth masks to remove noisy pixels, fill hollow regions, and reconnect broken portions with the main mask. The models were retrained using the preprocessed masks as ground truth. This led to a higher precision of 79.51% and the highest Dice score of 66.45%, achieved with EfficientNet-B3.

Keywords

  • Glioblastoma
  • brain tumor segmentation
  • SegFormer
  • EfficientNetB3
  • Magnetic resonance imaging
  • encoder comparison

CCDS Authors

Riyadul Islam
Riyadul Islam

Riyadul Islam

  • Intern, CCDS

Bachelors

Daffodil International University

Published at

Scientific Reports

Siam Tahsin Bhuiyan
Siam Tahsin Bhuiyan

Siam Tahsin Bhuiyan

  • Intern, CCDS

Bachelors

Independent University, Bangladesh

Published at

Scientific Reports

Saadia Binte Alam, PhD
Saadia Binte Alam, PhD

Saadia Binte Alam, PhD

  • Director, MIRA & WiSE Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

HCII, Scientific Reports, Cognitive Computation, Neural Computing and Applications

References

  1. 1.Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. (2016). Deep Residual Learning for Image Recognition. , 770–778[10.1109/cvpr.2016.90]
  2. 2.Olaf Ronneberger, Philipp Fischer, Thomas Brox. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Lecture notes in computer science, 234–241[10.1007/978-3-319-24574-4_28]
  3. 3.Gao Huang, Zhuang Liu, Laurens Van Der Maaten, Kilian Q. Weinberger. (2017). Densely Connected Convolutional Networks. , 2261–2269[10.1109/cvpr.2017.243]
  4. 4.Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. , 4510–4520[10.1109/cvpr.2018.00474]
  5. 5.Nahian Siddique, Sidike Paheding, Colin P. Elkin, Vijay Devabhaktuni. (2021). U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications. IEEE Access, 9, 82031–82057[10.1109/access.2021.3086020]
  6. 6.Zhihua Liu, Lei Tong, Long Chen, Zheheng Jiang, Feixiang Zhou, Qianni Zhang, Xiangrong Zhang, Yaochu Jin, Huiyu Zhou. (2022). Deep learning based brain tumor segmentation: a survey. Complex & Intelligent Systems, 9(1), 1001–1026[10.1007/s40747-022-00815-5]
  7. 7.Felix J. Dorfner, Jay B. Patel, Jayashree Kalpathy-Cramer, Elizabeth R. Gerstner, Christopher P. Bridge. (2025). A review of deep learning for brain tumor analysis in MRI. npj Precision Oncology, 9(1), 2[10.1038/s41698-024-00789-2]
  8. 8.Jason Walsh, Alice Othmani, Mayank Jain, Soumyabrata Dev. (2022). Using U-Net network for efficient brain tumor segmentation in MRI images. Healthcare Analytics, 2, 100098[10.1016/j.health.2022.100098]
  9. 9.Dinthisrang Daimary, Mayur Bhargab Bora, Khwairakpam Amitab, Debdatta Kandar. (2020). Brain Tumor Segmentation from MRI Images using Hybrid Convolutional Neural Networks. Procedia Computer Science, 167, 2419–2428[10.1016/j.procs.2020.03.295]
  10. 10.Shehan Perera, Pouyan Navard, Alper Yilmaz. (2024). SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation. , 4981–4988[10.1109/cvprw63382.2024.00503]
  11. 11.Necip Cinar, Alper Ozcan, Mehmet Kaya. (2022). A hybrid DenseNet121-UNet model for brain tumor segmentation from MR Images. Biomedical Signal Processing and Control, 76, 103647[10.1016/j.bspc.2022.103647]
  12. 12.Miri Kim, Erik Ladomersky, Andreas Mozny, Masha Kocherginsky, Kaitlyn O’Shea, Zachary Z Reinstein, Lijie Zhai, April Bell, Kristen L Lauing, Lakshmi Bollu, Erik Rabin, Karan Dixit, Priya Kumthekar, Leonidas C Platanias, Lifang Hou, Yinan Zheng, Jennifer Wu, Bin Zhang, Maya Hrachova, Sarah A Merrill, Maciej M Mrugala, Vikram C Prabhu, Craig Horbinski, Charles David James, Bakhtiar Yamini, Quinn T Ostrom, Margaret O Johnson, David A Reardon, Rimas V Lukas, Derek A Wainwright. (2021). Glioblastoma as an age-related neurological disorder in adults. Neuro-Oncology Advances, 3(1), vdab125[10.1093/noajnl/vdab125]
  13. 13.Preetha R, Jasmine Pemeena Priyadarsini M, Nisha J S. (2025). Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis. Scientific Reports, 15(1), 9914[10.1038/s41598-025-94267-9]
  14. 14.Ivana Jovčevska. (2018). Genetic secrets of long-term glioblastoma survivors. Bosnian Journal of Basic Medical Sciences, 19(2), 116–124[10.17305/bjbms.2018.3717]
  15. 15.Jeffrey Wong, Michael Baine, Sarah Wisnoskie, Nathan Bennion, Dechun Zheng, Dechun Zheng, Lei Yu, Vipin Dalal, Michael A. Hollingsworth, Chi Lin, Dandan Zheng, Dandan Zheng. (2021). Effects of interobserver and interdisciplinary segmentation variabilities on CT-based radiomics for pancreatic cancer. Scientific Reports, 11(1), 16328[10.1038/s41598-021-95152-x]
  16. 16.Masih Sabouri, Aref Famili Dogonchi, Mehdi Shafiei, Donya Sheibani Tehrani. (2024). Survival rate of patient with glioblastoma: a population-based study. The Egyptian Journal of Neurosurgery : the official publication of the Egyptian Society of Neurological Surgeons/Egyptian journal of neurosurgery, 39(1)[10.1186/s41984-024-00294-5]
  17. 17.Adalberto M. Filho, Ariana Znaor, Ceren Sunguc, Mariam Zahwe, Rafael Marcos-Gragera, Jonine D. Figueroa, Freddie Bray. (2025). Cancers of the brain and central nervous system: global patterns and trends in incidence. Journal of Neuro-Oncology, 172(3), 567–578[10.1007/s11060-025-04944-y]
  18. 18.Su Wu, Ziheng Wang, Chang Liu, Chenming Zhu, Shaozhi Wu, Kai Xiao. (2019). Automatical Segmentation of Pelvic Organs After Hysterectomy by using Dilated Convolution U-Net++. , 362–367[10.1109/qrs-c.2019.00074]
  19. 19.Haseeb Sultan, Muhammad Owais, Se Hyun Nam, Adnan Haider, Rehan Akram, Muhammad Usman, Kang Ryoung Park. (2023). MDFU-Net: Multiscale dilated features up-sampling network for accurate segmentation of tumor from heterogeneous brain data. Journal of King Saud University - Computer and Information Sciences, 35(5), 101560[10.1016/j.jksuci.2023.101560]
  20. 20.Nisreen Haydar, Khatoun Alyousef, Usama Alanan, Rana Issa, Fawaz Baddour, Zuheir Al-shehabi, Moatasem Hussein Al-janabi. (2022). Role of Magnetic Resonance Imaging (MRI) in grading gliomas comparable with pathology: A cross-sectional study from Syria. Annals of Medicine and Surgery, 82, 104679[10.1016/j.amsu.2022.104679]
  21. 21.Mushtaq Mahyoob Saleh, Musab Elkheir Salih, Mohamed A. A. Ahmed, Altahir Mohamed Hussein. (2025). From Traditional Methods to 3D U-Net: A Comprehensive Review of Brain Tumour Segmentation Techniques. Journal of Biomedical Science and Engineering, 18(01), 1–32[10.4236/jbise.2025.181001]
  22. 22.K. Hemalatha, P. R. Vishnu Vardhan, Alfred Dharmaraj Aravindraj, S. Hari Hara Sudhan. (2025). Masked and Noise-Masked Multimodal Brain Tumor Image Segmentation Using SegFormer and Shared Encoder Framework. IEEE Access, 13, 142759–142775[10.1109/access.2025.3596643]
  23. 23.Seref Sagiroglu, Ramazan Terzi, Emrah Celtikci, Alp Özgün Börcek, Yilmaz Atay, Bilgehan Arslan, Mustafa Caglar Sahin, Kerem Nernekli, Umut Demirezen, Okan Bilge Ozdemir, Kevser Özdem Karaca, Nuh Azgınoğlu. (2025). A novel brain tumor magnetic resonance imaging dataset (Gazi Brains 2020): initial benchmark results and comprehensive analysis. PeerJ Computer Science, 11, e2920[10.7717/peerj-cs.2920]
  24. 24.Danai Chourmouzi, Elissabet Papadopoulou, Kostantinos Marias, Antonios Drevelegas. (2014). Imaging of Brain Tumors. Surgical Oncology Clinics of North America, 23(4), 629–684[10.1016/j.soc.2014.07.004]
  25. 25.Roushanak Rahmat, Khadijeh Saednia, Mohammad Reza Haji Hosseini Khani, Mohamad Rahmati, Raj Jena, Stephen J. Price. (2020). Multi-scale segmentation in GBM treatment using diffusion tensor imaging. Computers in Biology and Medicine, 123, 103815[10.1016/j.compbiomed.2020.103815]
  26. 26.Run Su, Jinhuai Liu, Deyun Zhang, Chuandong Cheng, Mingquan Ye. (2020). Multimodal Glioma Image Segmentation Using Dual Encoder Structure and Channel Spatial Attention Block. Frontiers in Neuroscience, 14, 586197[10.3389/fnins.2020.586197]
  27. 27.C. Gunasundari, K. Selva Bhuvaneswari. (2025). Machine learning fusion for glioma tumor detection. Scientific Reports, 15(1), 11236[10.1038/s41598-025-89911-3]
← All publications