An Intelligent Health Informatics Framework for Automated Brain Tissue Segmentation in MRI Using U-Net-Based Convolutional Neural Networks
DOI:
https://doi.org/10.54153/sjpas.2026.v8i1.1393Abstract
This study proposes an intelligent framework for automated brain tissue segmentation in MRI scans using U-Net-based convolutional neural networks, aiming to improve accuracy over existing methods. The methodology involves implementing both 2D and 3D U-Net architectures, trained and validated on public datasets (MRBrainS13, MRBrainS18, IBSR) with manual expert segmentations. Performance was compared against established tools (FSL, Dipy) using Dice Coefficient, Jaccard Index, AUC, and SSIM metrics. Results demonstrate the superiority of U-Net models, with Dice scores exceeding 0.9 for gray matter and showing high consistency, while 2D U-Net slightly outperformed the 3D variant in reducing false positives and negatives. The conclusion confirms that U-Net-based segmentation significantly enhances precision and reliability for distinguishing gray matter, white matter, and cerebrospinal fluid, offering a robust alternative to conventional techniques
References
[1]. Gaitanis J, Tarui T. Nervous System Malformations. Continuum (Minneap Minn). 2018;24(1, Child Neurology):72–95. doi:10.1212/CON.0000000000000561
[2]. Blinkouskaya Y, Weickenmeier J. Brain Shape Changes Associated With Cerebral Atrophy in Healthy Aging and Alzheimer’s Disease. Front Mech Eng. 2021;7:705653. doi:10.3389/fmech.2021.705653
[3]. Ineichen BV, Cananau C, Plattén M, Ouellette R, Moridi T, Frauenknecht KBM, et al. Dilated Virchow-Robin Spaces are a Marker for Arterial Disease in Multiple Sclerosis. bioRxiv [Preprint]. 2023 Feb 27:2023.02.24.529871. doi:10.1101/2023.02.24.529871
[4]. Gorgolewski K, Auer T, Calhoun V, et al. The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments. Sci Data. 2016;3:160044. doi:10.1038/sdata.2016.44
[5]. Yen C, Lin CL, Chiang MC. Exploring the Frontiers of Neuroimaging: A Review of Recent Advances in Understanding Brain Functioning and Disorders. Life (Basel). 2023;13(7):1472. doi:10.3390/life13071472
[6]. Narayana PA, Coronado I, Sujit SJ, Wolinsky JS. Deep learning-based neural tissue segmentation of MRI in multiple sclerosis: Effect of training set size. J Magn Reson Imaging. 2020;51(5):1487–1496
[7]. Ye Z, George A, Wu AT, Niu X, Lin J, Adusumilli G, et al. Deep learning with diffusion basis spectrum imaging for classification of multiple sclerosis lesions. Ann Clin Transl Neurol. 2020;7(5):695–706
[8]. Arab A, Chinda B, Medvedev G, et al. A fast and fully-automated deep-learning approach for accurate hemorrhage segmentation and volume quantification in non-contrast whole-head CT. Sci Rep. 2020;10:19389. doi:10.1038/s41598-020-76459-7
[9]. Guo S, Lu Y, Li Y. Richardson–Lucy Iterative Blind Deconvolution with Gaussian Total Variation Constraints for Space Extended Object Images. Photonics. 2024;11(6):576. doi:10.3390/photonics11060576
[10]. Dell'Acqua F, Tournier JD. Modelling white matter with spherical deconvolution: How and why? NMR Biomed. 2019;32(4):e3945. doi:10.1002/nbm.3945
[11]. Verma A, Shivhare SN, Singh SP, et al. Comprehensive Review on MRI-Based Brain Tumor Segmentation: A Comparative Study from 2017 Onwards. Arch Computat Methods Eng. 2024;31:4805–4851. doi:10.1007/s11831-024-10128-0
[12]. Ranjbarzadeh R, Bagherian Kasgari A, Jafarzadeh Ghoushchi S, et al. Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images. Sci Rep. 2021;11:10930. doi:10.1038/s41598-021-90428-8
[13]. Panić B, Klemenc J, Nagode M. Improved Initialization of the EM Algorithm for Mixture Model Parameter Estimation. Mathematics. 2020;8(3):373. doi:10.3390/math8030373
[14]. Billot B, Greve DN, Puonti O, Thielscher A, Van Leemput K, Fischl B, Dalca AV, Iglesias JE; ADNI. SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining. Med Image Anal. 2023;86:102789. doi:10.1016/j.media.2023.102789
[15]. Zhao L, Ma J, Shao Y, Jia C, Zhao J, Yuan H. MM-UNet: A multimodality brain tumor segmentation network in MRI images. Front Oncol. 2022;12:950706. doi:10.3389/fonc.2022.950706
[16]. Taye MM. Theoretical Understanding of Convolutional Neural Network: Concepts, Architectures, Applications, Future Directions. Computation. 2023;11(3):52. doi:10.3390/computation11030052
[17]. Zhao X, Wang L, Zhang Y, et al. A review of convolutional neural networks in computer vision. Artif Intell Rev. 2024;57:99. doi:10.1007/s10462-024-10721-6
[18]. Yao W, Bai J, Liao W, Chen Y, Liu M, Xie Y. From CNN to Transformer: A Review of Medical Image Segmentation Models. J Imaging Inform Med. 2024;37(4):1529–1547. doi:10.1007/s10278-024-00981-7
[19]. Yousefi T, Aktaş Ö. New hybrid segmentation algorithm: UNet-GOA. PeerJ Comput Sci. 2023;9:e1499. doi:10.7717/peerj-cs.1499
[20]. Akan T, Oskouei AG, Alp S, et al. Brain magnetic resonance image (MRI) segmentation using multimodal optimization. Multimed Tools Appl. 2025;84:16971–17020. doi:10.1007/s11042-024-19725-4
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright Notice
Authors retain copyright and grant the SJPAS journal right of first publication, with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in Samarra Journal of Pure and Applied Science.
The Samarra Journal of Pure and Applied Science permits and encourages authors to archive Pre-print and Post-print items submitted to the journal on personal websites or institutional repositories per the author's choice while providing bibliographic details that credit their submission, and publication in this journal. This includes the archiving of a submitted version, an accepted version, or a published version without any Risks.
