Authors:
Prem Nath,Naresh Kumar Trivedi,DOI NO:
https://doi.org/10.26782/jmcms.2026.04.00003Keywords:
Image Enhancement,Gibbs Ringing Artefact,Deep Learning,Medical Image Processing,Abstract
Accurate segmentation of brain tumours from magnetic resonance imaging (MRI) depends critically on the quality and consistency of acquired scans; however, MRI data are often affected by artefacts, intensity inhomogeneity, and inter-scanner variability, which degrade the performance of deep learning–based models. To address this, the present study proposes a denoising-guided enhancement pipeline designed to improve anatomical and geometric consistency before segmentation. The preprocessing framework integrates Gibbs ringing artefact suppression, N4ITK bias field correction, Z-score–based intensity normalisation, adaptive histogram equalisation, along with spatial alignment and resolution standardisation, applied in an empirically optimised sequence across multimodal MRI inputs (T1, T1c, T2, FLAIR). Tumour segmentation is performed using an Attention Residual U-Net (ARU-Net), enabling improved feature localisation and boundary delineation. Experimental evaluation on BraTS 2015 and BraTS 2018 datasets demonstrates enhanced performance, achieving Dice scores of 0.93 for whole tumour, 0.85 for tumour core, and 0.74 for enhancing tumour. Ablation analysis confirms that both the inclusion and ordering of preprocessing steps significantly influence segmentation accuracy, while statistical validation using corrected resampled t-tests establishes the robustness and significance of the observed improvements. The proposed pipeline is modular, reproducible, and suitable for integration into clinical imaging workflows, where denoising-guided preprocessing ensures early removal of acquisition-related artefacts without compromising fine anatomical details.Refference:
I. A., A. H. S. (2025). An automated detection of cerebral infarction in computed tomography (CT) brain images using a 3D U-Net model of convolutional neural networks (CNN). International Journal of Advanced Trends in Engineering and Management, vol. IV. 10.59544/rmju7664/ijatemv04i01p1.
II. Agraz, J. L., Grenko, C. M., Chen, A. A., Viaene, A. N., Nasrallah, M. D., Pati, S., Kurc, T., Saltz, J., Feldman, M. D., Akbari, H., Sharma, P., Shinohara, R. T., Bakas, S. (2022). Robust image population-based stain colour normalisation: how many reference slides are enough? IEEE Open Journal of Engineering in Medicine and Biology, vol. 3, pp. 218–226. 10.1109/ojemb.2023.3234443.
III. Angona, T. M., Mondal, M. R. H. (2025). An attention-based residual U-Net with Swin transformer for brain MRI segmentation. Array, vol. 25, article 100376. 10.1016/j.array.2025.100376.
IV. Becker, L. J., Fillinger, C., Waegaert, R., Journée, S. H., Hener, P., Ayazgok, B., Humo, M., Karatas, M., Thouaye, M., Gaikwad, M., Degiorgis, L., Santin, M. D. N., Mondino, M., Barrot, M., Ibrahim, E. C., Turecki, G., Belzeaux, R., Veinante, P., Harsan, L. A., Hugel, S., Lutz, P.-E., Yalcin, I. (2023). The basolateral amygdala–anterior cingulate pathway contributes to depression-like behaviours and comorbidity with chronic pain behaviors in male mice. Nature Communications, vol. 14. 10.1038/s41467-023-37878-y.
V. Bilgic, B., Costagli, M., Chan, K., Duyn, J., Langkammer, C., Lee, J., Li, X., Liu, C., Marques, J. P., Milovic, C., Robinson, S. D., Schweser, F., Shmueli, K., Spincemaille, P., Straub, S., Van Zijl, P., Wang, Y. (2024). Recommended implementation of quantitative susceptibility mapping for clinical research in the brain: a consensus of the ISMRM electro-magnetic tissue properties study group. Magnetic Resonance in Medicine, vol. 91, pp. 1834–1862. 10.1002/mrm.30006.
VI. Fei, N., Gao, Y., Lu, Z., Xiang, T. (2021). Z-score normalization, hubness, and few-shot learning. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 142–151. DOI: 10.1109/iccv48922.2021.00021.
VII. Ghaffari, S., Li, K. F., Capson, D. W. (2024). Combining SIFT and BRISK descriptors to improve image matching accuracy. Proceedings of the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, pp. 1–8. 10.1109/pacrim61180.2024.10690201.
VIII. Goto, M., Otsuka, Y., Hagiwara, A., Fujita, S., Hori, M., Kamagata, K., Aoki, S., Abe, O., Sakamoto, H., Sakano, Y., Kyogoku, S., Daida, H. (2023). Accuracy of skull stripping in a single-contrast convolutional neural network model using eight-contrast magnetic resonance images. Radiological Physics and Technology, vol. 16, pp. 373–383. 10.1007/s12194-023-00728-z.
IX. Hidayat, F. R., Sugiyanto, Rasyid. (2024). Convolutional neural network denoising technique on MRI examination using parallel imaging GRAPPA: a study on axial brain MRI T2 fat saturation FLAIR. International Journal of Radiology and Diagnostic Imaging, vol. 7, pp. 53–59. 10.33545/26644436.2024.v7.i2a.386.
X. Jackpersad, K., Gwetu, M. (2022). Brain MRI segmentation using autoencoders. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, pp. 74–93. 10.1007/978-3-030-93314-2_5.
XI. Kanakaraj, P., Yao, T., Cai, L. Y., Lee, H. H., Newlin, N. R., Kim, M. E., Gao, C., Pechman, K. R., Archer, D., Hohman, T., Jefferson, A., Beason-Held, L. L., Resnick, S. M., Garyfallidis, E., Anderson, A., Schilling, K. G., Landman, B. A., Moyer, D. (2023). DeepN4: learning N4ITK bias field correction for T1-weighted images. Research Square (Preprint). 10.21203/rs.3.rs-3585882/v1.
XII. Komenchuk, O. (2024). Adaptive pre-processing methods for increasing the accuracy of segmentation of dental X-ray images. Innovative Technologies and Scientific Solutions for Industries, pp. 29–38. 10.30837/2522-9818.2024.3.029.
XIII. Kumar, R., Gupta, M., Agarwal, A., Nayyar, A. (2024). CBAR-UNet: a novel methodology for segmentation of cardiac magnetic resonance images using block attention-based deep residual neural network. Multimedia Tools and Applications, vol. 83, pp. 85047–85063. 10.1007/s11042-024-19432-0.
XIV. Laajava, J., Korja, M. (2023). Peritumoral T2/FLAIR hyperintense MRI findings of meningiomas are not necessarily edema and may persist permanently: a systematic review. Neurosurgical Review, vol. 46, article 193. 10.1007/s10143-023-02094-1.
XV. Lee, H., Novikov, D. S., Fieremans, E. (2021). Removal of partial Fourier-induced Gibbs (RPG) ringing artifacts in MRI. Magnetic Resonance in Medicine, vol. 86, pp. 2733–2750. 10.1002/mrm.28830.
XVI. Lee, H.-B., Jung, M.-H., Kim, Y.-H., Park, E.-B., Jang, W.-S., Kim, S.-J., Choi, K.-J., Park, J.-Y., Hwang, K.-B., Shim, J.-H., Yoon, S., Kim, Y.-M. (2023). Deep learning image segmentation for the reliable porosity measurement of high-capacity Ni-based oxide cathode secondary particles. Journal of Analytical Science and Technology, vol. 14. 10.1186/s40543-023-00407-z.
XVII. Li, X., Jiang, Y., Li, M., Zhang, J., Yin, S., Luo, H. (2022). MSFR-Net: multi-modality and single-modality feature recalibration network for brain tumor segmentation. Medical Physics, vol. 50, pp. 2249–2262. 10.1002/mp.15933.
XVIII. Li, Y., Zhang, L., Liang, Y., Xu, C., Liu, T. (2024). Improvements in brain tumor segmentation methods based on convolutional neural networks. ICST Transactions on e-Education and e-Learning, vol. 11. 10.4108/eetel.6080.
XIX. Liu, H.-Y., Tsai, S., Tsai, M.-L., Chiang, K.-W. (2022). An initial alignment method of inertial navigation system for the static state. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLIII-B1, pp. 227–233. DOI: 10.5194/isprs-archives-xliii-b1-2022-227-2022.
XX. Petitjean, C., Lian, J., Wang, L., Trullo, R., Shen, D., Nie, D., Wang, Q., Ruan, S. (2024). Medical image synthesis with deep convolutional adversarial networks. UNC Libraries (Preprint). 10.17615/yy4y-3×54.
XXI. Ramamoorthy, M., Qamar, S., Manikandan, R., Jhanjhi, N. Z., Masud, M., AlZain, M. A. (2022). Earlier detection of brain tumor by pre-processing based on histogram equalization with neural network. Healthcare, vol. 10, article 1218. 10.3390/healthcare10071218.
XXII. Rempe, M., Mentzel, F., Pomykala, K. L., Haubold, J., Nensa, F., Kroeninger, K., Egger, J., Kleesiek, J. (2023). k-strip: a novel segmentation algorithm in k-space for the application of skull stripping. Computer Methods and Programs in Biomedicine, vol. 243, article 107912. 10.1016/j.cmpb.2023.107912.
XXIII. Shakya, K. S., Alavi, A., Porteous, J., K., P., Laddi, A., Jaiswal, M. (2024). A critical analysis of deep semi-supervised learning approaches for enhanced medical image classification. Information, vol. 15, article 246. 10.3390/info15050246.
XXIV. Singh, R., Singh, N., Kaur, L. (2024). Deep learning methods for 3D magnetic resonance image denoising, bias field and motion artifact correction: a comprehensive review. Physics in Medicine and Biology, vol. 69, article 23TR01. 10.1088/1361-6560/ad94c7.
XXV. Sun, H., Yang, S., Chen, L., Liao, P., Liu, X., Liu, Y., Wang, N. (2023). Brain tumor image segmentation based on improved FPN. BMC Medical Imaging, vol. 23, article 172. 10.1186/s12880-023-01131-1.
XXVI. Tuta, L., Nicolaescu, M., Rosu, G., Grivei, A., Barbulescu, B. (2020). A robust adaptive filtering method based on independent component analysis (ICA). Proceedings of the IEEE Communications Conference, pp. 59–64. 10.1109/comm48946.2020.9141995.
XXVII. Wang, H., Hu, K., Guo, X., Li, H., Tao, C. (2026). A gift from the integration of discriminative and diffusion-based generative learning: boundary refinement remote sensing semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1–18. 10.1109/tpami.2026.3654243.
XXVIII. Yang, W., Li, Z., Du, C., Chow, S. K. K. (2025). HLNet: high-level attention mechanism U-Net for brain tumor segmentation in MRI. Applied Intelligence, vol. 55. 10.1007/s10489-025-06568-1.
XXIX. Yao, L., Zhang, Z., Bagci, U. (2023). Ensemble learning with residual transformer for brain tumor segmentation. Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI), pp. 1–5. 10.1109/isbi53787.2023.10230404.
XXX. ZongRen, L., Silamu, W., Yuzhen, W., Zhe, W. (2023). DenseTrans: multimodal brain tumor segmentation using Swin transformer. IEEE Access, vol. 11, pp. 42895–42908. 10.1109/access.2023.3272055.