Brain Tumor Segmentation From MRI Images Using MLU-Net with Residual Connections

Eric Timothy Rompisa; Gede Putra Kusuma

doi:10.52436/1.jutif.2025.6.5.4742

Authors

Eric Timothy Rompisa BINUS Graduate Program Master of Computer Science, Bina Nusantara University, Indonesia
Gede Putra Kusuma BINUS Graduate Program Master of Computer Science, Bina Nusantara University, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2025.6.5.4742

Keywords:

Brain Tumor, CNN, Image Segmentation, Residual Connection, U-Net

Abstract

Brain tumor segmentation plays an important role in medical imaging in assisting diagnosis and treatment planning. Although advances in deep learning such as Unet already perform image segmentation, many challenges exist in segmenting brain tumors with tumor spread boundaries. This paper proposes a model that combines CNN and MLP (MLU-Net) techniques enhanced by the addition of residual connections to improve segmentation accuracy called ResMLU-Net. This architecture combines 2D covolution layers, block MLP and residual connections to process MRI images with the dataset used is BraTS 2021. The residaul connection helps reduce gradient degradation which ensures smooth information flow and better feature learning. The performance of ResMLU-Net will be evaluated using Dice and IoU metrics and will also be compared with several models such as Unet, ResUnet and MLU-Net. The experimental scores obtained from ResMLU-Net for segmenting brain tumors are 83.43% for IoU and 89.94% for Dice. These results show that adding residual connections can improve the accuracy in segmenting brain tumors which can be seen that there is an increase in the Dice and Iou scores. The proposed ResMLU-Net model is a valuable contribution to medical imaging and health informatics. With its provision of a standard and computationally viable solution to brain tumor segmentation, it offers incorporation into Computer-Aided Diagnosis (CAD) systems and support to clinical decision-making protocols.

Downloads

Download data is not yet available.

References

C. S. Muir, H. H. Storm, and A. Polednak, “Brain and other nervous system tumours,” Cancer Surveys. [Online]. Available: https://www.cancer.gov/types/brain

D. N. Louis et al., “The 2021 WHO classification of tumors of the central nervous system: A summary,” Neuro Oncol, vol. 23, no. 8, pp. 1231–1251, 2021, doi: 10.1093/neuonc/noab106.

I. B. L. M. Suta, R. S. Hartati, and Y. Divayana, “Diagnosa Tumor Otak Berdasarkan Citra MRI (Magnetic Resonance Imaging),” Majalah Ilmiah Teknologi Elektro, vol. 18, no. 2, 2019, doi: 10.24843/mite.2019.v18i02.p01.

P. Cranston, “Brain Tumor,” The journal of pastoral care & counseling : JPCC. [Online]. Available: https://www.mayoclinic.org/diseases-conditions/brain-tumor/symptoms-causes/syc-20350084

M. F. Safdar and S. S. Alkobaisi, “A comparative analysis of data augmentation approaches for magnetic resonance imaging (MRI) scan images of brain tumor,” Acta Informatica Medica, vol. 28, no. 1, pp. 29–36, 2020, doi: 10.5455/aim.2020.28.29-36.

B. K. Ahir, H. H. Engelhard, and S. S. Lakka, “Tumor development and angiogenesis in adult brain tumor: Glioblastoma,” Int J Mol Sci, vol. 21, no. 20, pp. 2461–2478, 2020, doi: 10.3390/ijms21204648.

Y. He et al., “Automatic left ventricle segmentation from cardiac magnetic resonance images using a capsule network,” J Xray Sci Technol, vol. 28, no. 3, pp. 541–553, 2020, doi: 10.3233/XST-190621.

T. Akan, A. G. Oskouei, and S. Alp, “Brain magnetic resonance image (MRI) segmentation using multimodal optimization,” Multimed Tools Appl, 2024, doi: 10.1007/s11042-024-19725-4.

U. Baid and others, “The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification,” arXiv preprint, 2021, [Online]. Available: http://arxiv.org/abs/2107.02314

A. Younis, L. Qiang, C. O. Nyatega, M. J. Adamu, and H. B. Kawuwa, “Brain tumor analysis using deep learning and VGG-16 ensembling learning approaches,” Applied Sciences, vol. 12, no. 2, pp. 1–14, 2022, doi: 10.3390/app12020689.

O. Ronneberger and T. Fischer, P., & Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” ArXiv, vol. arXiv:1505, 2015, [Online]. Available: https://arxiv.org/abs/1505.04597

R. Budi, R. A. Harianto, and E. Setyati, “Segmentasi citra area tumpukan sampah dengan memanfaatkan Mask R-CNN,” Journal of Intelligent System and Computation, vol. 5, no. 1, pp. 58–64, 2023, doi: 10.52985/insyst.v5i1.305.

Y. Xie, J. Zhang, and C. Shen, “CoTr: Efficiently bridging CNN and transformer for medical image segmentation,” arXiv preprint, 2021.

H. Huang and others, “UNet 3+: A full-scale connected UNet for medical image segmentation,” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 1055–1059. doi: 10.1109/ICASSP40776.2020.9053405.

R. Azad, M. Asadi-Aghbolaghi, M. Fathy, and S. Escalera, “Medical image segmentation review: The success of U-Net,” Pattern Recognit, vol. 128, pp. 1–38, 2022, doi: 10.1016/j.patcog.2022.108675.

M. K. Anbudevi and K. Suganthi, “Review of semantic segmentation of medical images using modified architectures of UNET,” J Healthc Eng, vol. 2022, pp. 1–11, 2022, doi: 10.1155/2022/8423073.

Y. Deng, Y. Hou, J. Yan, and D. Zeng, “ELU-Net: An efficient and lightweight U-Net for medical image segmentation,” IEEE Access, vol. 10, pp. 35932–35941, 2022, doi: 10.1109/ACCESS.2022.3163711.

D. Liu and others, “SGEResU-Net for brain tumor segmentation,” Mathematical Biosciences and Engineering, vol. 19, no. 6, pp. 5576–5590, 2022, doi: 10.3934/mbe.2022261.

X. Li and others, “TransU2-Net: An effective medical image segmentation framework based on transformer and U2-Net,” IEEE J Transl Eng Health Med, vol. 11, pp. 441–450, 2023, doi: 10.1109/JTEHM.2023.32899990.

L. Feng and others, “MLU-Net: A multi-level lightweight U-Net for medical image segmentation integrating frequency representation and MLP-based methods,” IEEE Access, vol. 12, pp. 20734–20751, 2024, doi: 10.1109/ACCESS.2024.3360889.

F. I. Diakogiannis, F. Waldner, P. Caccetta, and C. Wu, “ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 162, pp. 94–114, 2020, doi: 10.1016/j.isprsjprs.2020.01.013.

D. Zhang and others, “Cross-modality deep feature learning for brain tumor segmentation,” Pattern Recognit, vol. 110, pp. 1–10, 2021, doi: 10.1016/j.patcog.2020.107562.

P. Wang and A. C. S. Chung, “Relax and focus on brain tumor segmentation,” Med Image Anal, vol. 75, p. 102259, 2021, doi: 10.1016/j.media.2021.102259.

Y. Zhang and others, “mmFormer: Multimodal medical transformer for incomplete multimodal learning of brain tumor segmentation,” in Lecture Notes in Computer Science, vol. 13435, 2022, pp. 107–117. doi: 10.1007/978-3-031-16443-9_11.

Z. Xing and others, “NestedFormer: Nested modality-aware transformer for brain tumor segmentation,” in Lecture Notes in Computer Science, vol. 13435, 2022, pp. 140–150. doi: 10.1007/978-3-031-16443-9_14.

Y. Jiang and others, “SwinBTS: A method for 3D multimodal brain tumor segmentation using Swin Transformer,” Brain Sci, vol. 12, no. 6, pp. 1–15, 2022, doi: 10.3390/brainsci12060797.

F. Ullah and others, “Brain tumor segmentation from MRI images using handcrafted convolutional neural network,” Diagnostics, vol. 13, no. 16, pp. 1–15, 2023, doi: 10.3390/diagnostics13162650.

M. Vatanpour and J. Haddadnia, “TransDoubleU-Net: Dual scale Swin Transformer with dual level decoder for 3D multimodal brain tumor segmentation,” IEEE Access, vol. 11, pp. 125511–125518, 2023, doi: 10.1109/ACCESS.2023.3330958.

J. Lin and others, “CKD-TransBTS: Clinical knowledge-driven hybrid transformer with modality-correlated cross-attention for brain tumor segmentation,” IEEE Trans Med Imaging, vol. 42, no. 8, pp. 2451–2461, 2023, doi: 10.1109/TMI.2023.3250474.

T. Magadza and S. Viriri, “Efficient nnU-Net for brain tumor segmentation,” IEEE Access, vol. 11, pp. 126386–126397, 2023, doi: 10.1109/ACCESS.2023.3329517.