WAMAS: A Multi-Agent System with Improved Watershed Segmentation for Brain MRI Analysis

Nedjoua Houda Kholladi, Okba Kazar, Abdelkader Hima, Kamal Bechkoum, Mounir Beggas, Meriem Hamoud

Abstract


Accurate segmentation of brain magnetic resonance imaging (MRI) scans is vital for early diagnosis and treatment planning of brain tumors. Classical methods such as the Watershed algorithm often suffer from over-segmentation, noise sensitivity, and limited adaptability. To address these issues, we propose a Watershed-based Multi-Agent System (WAMAS) that combines empirical thresholding, statistical similarity
measures, and agent-driven negotiation for robust tumor delineation. In preprocessing, edge features are extracted with Canny and Sobel operators, while region descriptors are obtained via Quadtree decomposition and refined through mean–variance analysis to adapt thresholds under noise. During processing, Region
Agents propose the proposed local watershed on its appropriate regions where seed candidate merges based on similarity scores, while Edge Agents validate boundaries using gradient consistency; conflicts are resolved through cooperative decision rules to prevent over-segmentation. Evaluations on BrainWeb and IBSR167 datasets under varying noise levels showed that WAMAS outperforms baseline Watershed and
advanced methods such as U-Net and B-UNet, and best results obtained are respectively 97.38% accuracy, 96.50% sensitivity, and 96.84% specificity. Paired t-tests (p < 0.01) confirmed significant improvements. These results demonstrate that WAMAS provides coherent boundaries and robust performance, making it
a promising tool for clinical neuroimaging.


Full Text:

PDF

References


Argun¸csah, Ali ¨Ozg¨ur, Ertunc Erdil, and Devrim ¨Unay. ”Applications of Computer Vision and Machine Learning in Bioimaging.” In Bioimaging Modalities in Bioengineering, pp. 585–626. Springer, 2025.

C¸ukur, Tolga, Salman UH Dar, Valiyeh Ansarian Nezhad, Yohan Jun, Tae Hyung Kim, Shohei Fujita, and Berkin Bilgic. ”A tutorial on MRI reconstruction: From modern methods to clinical implications.” arXiv preprint arXiv:2507.16715, 2025. DOI: 10.48550/arXiv.2507.16715

Cobbinah, Matthew, Henry Nunoo-Mensah, Prince Ebenezer Adjei, et al. ”Diversity in Stable GANs: A Systematic Review of Mode Collapse Mitigation Strategies.” Engineering Reports 7, no. 6 (2025): e70209. DOI: 10.1002/eng2.70209

Jin, Chengcheng, Theam Foo Ng, and Haidi Ibrahim. ”Advancements in Semi-Supervised Deep Learning for Brain Tumor Segmentation in MRI: A Literature Review.” AI 6, no. 7 (2025): 153. DOI: 10.3390/ai6070153

Tae, Woo-Suk, Byung-Joo Ham, Sung-Bom Pyun, and Byung-Jo Kim. ”Current Clinical Applications of Structural MRI in Neurological Disorders.” Journal of Clinical Neurology 21, no. 4 (2025): 277. DOI: 10.3988/jcn.2025.0185

Rong, Yi, Riley Tegtmeier, Edward L. Clouser Jr, et al. ”Advancements in radiation therapy treatment workflows for precision medicine: a review and forward looking.” Int J Radiat Oncol Biol Phys 122, no. 4 (2025):1022–1034. DOI: 10.1002/acm2.14612

Sujji, G. Evelin, YVS Lakshmi, and G. Wiselin Jiji. ”MRI brain image segmentation based on thresholding.” Int J Adv Comput Res 3, no. 1 (2013): 97. DOI: 10.5120/ijca2017914330

Hsieh, Thomas M., Yi-Min Liu, Chun-Chih Liao, et al. ”Automatic segmentation of meningioma from non-contrasted brain MRI integrating fuzzy clustering and region growing.” BMC Med Inform Decis Mak 11, no. 1 (2011): 54. DOI: 10.1186/1472-6947-11-54

Silvoster, M. Leena, R. Mathusoothana, and S. Kumar. ”Watershed based algorithms for the segmentation of spine MRI.” Int J Inf Technol 14, no. 3 (2022): 1343–1353. DOI: 10.1007/s41870-021-00816-y

Vadmal, Vachan, Grant Junno, et al. ”MRI image analysis methods and applications: an algorithmic perspective using brain tumors as an exemplar.” Neuro Oncol Adv 2, no. 1 (2020): vdaa049. DOI: 10.1093/noajnl/vdaa049

Xu, Yan, Rixiang Quan, et al. ”Advances in medical image segmentation: A comprehensive review of traditional, deep learning and hybrid approaches.” Bioengineering 11, no. 10 (2024): 1034. DOI: 10.3390/bioengineering11101034

Xiao, Yating, Yan Chen, et al. ”Spine X-ray image segmentation based on deep learning and marker controlled watershed.” J Xray Sci Technol 33, no. 1 (2025): 109–119. DOI: 10.1177/08953996241299998

Aelgani, Vivekanand, Suneet Kumar Gupta, V. A. Narayana. ”A 2-level meta-heuristic aware adaptive watershed technique based optimized convolutional deep neural network for lung cancer segmentation and classification using explainable AI.” Biomed Signal Process Control 103 (2025): 107395. DOI: 10.1016/j.bspc.2025.107395

Abinav, S. ”Automated segmentation and classification of soft tissues in pathology images using deep learning and improved watershed algorithms.” [Unpublished manuscript].

Krishnapriya, Srigiri, and Yepuganti Karuna. ”A survey of deep learning for MRI brain tumor segmentation methods: Trends, challenges, and future directions.” Health Technol 13, no. 2 (2023): 181–201. DOI: 10.1186/s13755-023-00257-6

Latha, C., K. Perumal. ”Suppression of Over-Segmentation in Watershed Segmentation.” Int J Comput Appl 146, no. 1 (2016): 16-22. DOI: 10.5120/ijca2016910601

Lee, Jeong-A, et al. ”Automated Brain Image Segmentation from MR Using SVM and Watershed Transform.” PhD diss., Chosun University, 2020.

Yeghiazaryan, Varduhi, Yeva Gabrielyan, Irina Voiculescu. ”Parallel Watershed Partitioning: GPU-Based Hierarchical Image Segmentation.” J Parallel Distrib Comput 205 (2025): 105140. DOI: 10.1016/j.jpdc.2025.105140

Do, Thanh-Ha, Hoang Minh-Huong Dang, et al. ”Two-stage Pipeline for Automated Cell Segmentation.” APSIPA Trans Signal Inf Process 14, no.1 (2025).

Golkarieh, Alireza, Sajjad Rezvani Boroujeni, et al. ”Breakthroughs in brain tumor detection leveraging deep learning and transfer learning.” Comput Decision Making 2 (2025): 708–722. DOI: 10.59543/comdem.v2i.14243

Musthafa, Namya, Qurban A. Memon, et al. ”Advancing Brain Tumor Analysis: Current Trends, Key Challenges, Perspectives in Deep Learning-Based Brain MRI Tumor Diagnosis.” Eng 6, no. 5 (2025): 82. DOI: 10.1145/3673971.3674001

Birjais, Roshan. ”Challenges and Future Directions for Segmentation of Medical Images Using Deep Learning Models.” In Deep Learning Applications in Medical Image Segmentation, Wiley, 2025.

Rasool, Novsheena, Javaid Iqbal Bhat. ”A critical review on segmentation of glioma brain tumor and prediction of overall survival.” Arch Comput Methods Eng 32, no. 3 (2025): 1525–1569.

Mankki, Jussi-Jaakko, Klavdiia Bochenina. ”Vision Transformers in Brain Image Segmentation.” University of Helsinki, 2025.

Wei, Yujia, Jaidip Manikrao Jagtap, et al. ”Comprehensive Segmentation of Gray Matter Structures on T1-Weighted Brain MRI.” Am J Neuroradiol 46, no. 4 (2025): 742–749. DOI: 10.3174/ajnr.A8544

Dihin, Rasha Ali, Nesreen Readh Hamza. ”Brain Tumor Classification in MRI Images Using VGG19 with Type2 Fuzzy Logic.” Informatica 49, no. 13 (2025). DOI: 10.31449/inf.v49i13.4782

Raghuramaiah, Bandla, Suresh Chittineni. ”BreastEnsemNet: Transformer and BiLSTM-Based Hybrid Ensemble Deep Learning for Mammogram Classification.” Informatica 49, no. 31 (2025). DOI: 10.31449/inf.v49i31.4871

Lu, Yuting, et al. ”An improved watershed segmentation algorithm of medical tumor image.” IOP Conf Ser Mater Sci Eng 677, no. 4 (2019). DOI: 10.1088/1757-899X/677/4/042042

Kornilov, Anton, Ilia Safonov, Ivan Yakimchuk. ”Review of watershed implementations for segmentation of volumetric images.” J Imaging 8, no. 5 (2022): 127. DOI: 10.3390/jimaging8050127

Roy, Bijoyeta, Mousumi Gupta, Bidyut Krishna Goswami. ”Colon histopathology glandular segmentation using ensemble and watershed.” Int J Imaging Syst Technol 34, no. 5 (2024): e23179. DOI: 10.1002/ima.23179

Xiao, Yating, et al. ”Spine X-ray image segmentation based on deep learning and marker controlled watershed.” J Xray Sci Technol 33, no. 1 (2025): 109-119. DOI: 10.1007/978-3-031-21014-3_32

Annavarapu, Ambika, Surekha Borra. ”Adaptive watershed segmentation based denoising using CNN.” Biomed Signal Process Control 93 (2024): 106119. DOI: 10.1016/j.bspc.2024.106119

Shen, Xiaoyan, et al. ”Lesion segmentation in breast ultrasound images using optimized marked watershed.” Biomed Eng Online 20, no. 1 (2021): 57. DOI: 10.1186/s12938-021-00890-y

Guo, Miao, Ating Yang, Min Dong. ”Breast Mass Segmentation via Enhanced U-Net++.” Informatica 49, no. 25 (2025). DOI: 10.31449/inf.v49i25.4855

Xu, Qi. ”Adaptive Semantic Perception Model for Deep Learning-Based Image Processing.” Informatica 49, no. 29 (2025). DOI: 10.31449/inf.v49i29.4861

Mezzoudj, Saliha, Meriem Khelifa, Yasmina Saadna. ”Leveraging Spark-TensorFlow Distributor for Distributed Deep CNNs: Accelerating COVID-19 Detection.” Informatica 49, no. 17 (2025): 173–188. DOI: 10.31449/inf.v49i17.4795

Tiwary, Pradeep Kumar, Prashant Johri, et al. ”Deep Learning-Based MRI Brain Tumor Segmentation with EfficientNet-Enhanced UNet.” IEEE Access (2025).

Tejashwini, P. S., J. Thriveni, K. R. Venugopal. ”Novel SLCA-UNet for MRI Brain Tumor Segmentation.” arXiv:2307.08048 (2023). DOI: 10.48550/arXiv.2307.08048

Bhatti, Uzair Aslam, Jinru Liu, et al. ”FF-UNet: Deep learning-powered enhanced brain tumor segmentation in MRI.” Image Vis Comput 122 (2025): 105635. DOI: 10.1016/j.imavis.2022.105635

Khaleel, Zahraa, Amir Lakizadeh. ”Early Diagnosis of Alzheimer’s Disease with Transfer Learning via ResNet50 and FSBi-LSTM.” Informatica 49, no. 11 (2025). DOI: 10.31449/inf.v49i11.4780

Allioui, Hanane, Mohamed Sadgal, Aziz Elfazziki. ”Intelligent environment for advanced brain imaging: multi-agent system for automated Alzheimer diagnosis.” Evol Intell 14, no. 4 (2021): 1523-1538. DOI: 10.1007/s12065-021-00579-0

Bennai, Mohamed Tahar, Zahia Guessoum, et al. ”Stochastic Multi-Agent Approach for Tumor Segmentation in Brain MR Images.” Artif Intell Med 110 (2020): 101980. DOI: 10.1016/j.artmed.2020.101980

Xia, Zhaoyue, Jun Du, et al. ”Multi-Agent Reinforcement Learning Aided Intelligent UAV Swarm for Target Tracking.” IEEE Trans Veh Technol (2021). DOI: 10.1109/TVT.2021.3138124

Saifullah, Shoffan, Rafał Drężewski, et al. ”Modified U-Net with attention gate for brain tumor segmentation.” Neural Comput Appl 37, no. 7 (2025): 5521–5558. DOI: 10.1007/s00521-024-08621-1

Ho, Hsing-Hao, Huai-Che Yang, et al. ”Deep learning for automated segmentation of radiation-induced changes in cerebral arteriovenous malformations following radiosurgery.” BMC Med Imaging 25, no. 1 (2025): 218. DOI: 10.1186/s12880-025-01796-w

Angona, Tazkia Mim, M. Rubaiyat Hossain Mondal. ”Attention based residual U-Net with swin transformer for brain MRI segmentation.” Array 25 (2025): 100376. DOI: 10.1016/j.array.2025.100376

Elkamouchi, Rahma, Abdelaziz Daaif, Kamal Elguemmat. ”Multi-Agents System in Healthcare: A Systematic Literature Review.” Springer Nature, 2024.

Montagna, Sara, et al. ”Agent-based systems in healthcare.” Comput Methods Programs Biomed 248 (2024): 108140. DOI: 10.1016/j.cmpb.2024.108140

Bennai, Mohamed T., et al. ”Multi-agent medical image segmentation: A survey.” Comput Methods Programs Biomed 232 (2023): 107444. DOI: 10.1016/j.cmpb.2023.107444

Radiopaedia. ”Watershed cerebral infarction.” Available at: radiopaedia.org/articles/watershed-cerebral-infarction

Cufi, X., Munoz, X., Freixenet, J., Marti, J. ”Review of image segmentation techniques integrating region and boundary information.” Adv Imaging Electron Phys 120 (2003): 1–39. DOI: 10.1016/S1076-5670(03)20001-2

Karma, I. G. M., Putra, I. K. G. D., Sudarma, M., Linawati, L. ”Image Segmentation Based on Color Dissimilarity.” Informatica 46, no. 5 (2022). DOI: 10.31449/inf.v46i5.4337

Jasim, H. M., Ghrabat, M. J. J., Abdulrahman, L. Q., et al. ”Provably efficient multi-cancer image segmentation based on multi-class fuzzy entropy.” Informatica 47, no. 8 (2023). DOI: 10.31449/inf.v47i8.5231

Al-Kharaz, A. A. ”Optimization of Brain Cancer Images with Some Noise Models.” Informatica 47, no. 9 (2023). DOI: 10.31449/inf.v47i9.5292

Rastogi, D., Johri, P., Donelli, M., et al. ”Deep learning-integrated MRI brain tumor analysis: feature extraction, segmentation, and survival prediction using replicator and volumetric networks.” Sci Rep 15, no. 1 (2025): 1437. DOI: 10.1038/s41598-025-15858-2

Möller, H., Graf, R., Schmitt, J., et al. ”SPINEPS—automatic whole spine segmentation of T2-weighted MR images using a two-phase approach to multi-class semantic and instance segmentation.” Eur Radiol 35, no. 3 (2025):1178–1189. DOI: 10.1007/s00330-024-09157-9

Aruna, V. S., Vijayashree, J. ”A Critical Analysis of Brain Tumor MRI Segmentation and Classification Utilizing Machine Learning and Deep Learning Methods.” Informatica 49, no. 24 (2025). DOI: 10.31449/inf.v49i24.4842

Al-Fakih, Abdulkhalek, et al. ”FLAIR MRI sequence synthesis using squeeze attention generative model for reliable brain tumor segmentation.” Alexandria Eng J 99 (2024): 108–123. DOI: 10.1016/j.aej.2024.01.012

Aljahdali, Sadeem, et al. ”Effectiveness of radiology modalities in diagnosing and characterizing brain disorders.” Neurosciences J 29, no. 1 (2024): 37–43. DOI: 10.17712/nsj.2024.1.20230032

Collins, D. L., Zijdenbos, A. P., Kollokian, V., et al. ”Design and construction of a realistic digital brain phantom.” IEEE Trans Med Imaging 17, no. 3 (1998): 463–468. DOI: 10.1109/42.712135

Chatterjee, Pubali, Kaushik Das Sharma, Amlan Chakrabarti. ”A stochastic approach for automated brain MRI segmentation.” IET Image Process 15, no. 3 (2021): 735–745. DOI: 10.1049/ipr2.12047

Chen, Hsian-Min, et al. ”Comparison of Multispectral Image-Processing Methods for Brain Tissue Classification in BrainWeb Synthetic Data and Real MR Images.” Biomed Res Int 2021 (2021): 9820145. DOI: 10.1155/2021/9820145

BrainWeb dataset. Available: http://brainweb.bic.mni.mcgill.ca/brainweb/

IBSR dataset. Available: https://www.nitrc.org/projects/ibsr/

DICOM dataset. Available: https://www.osirix-viewer.com/resources/dicom-image-library/

Rutherford, M., Mun, S. K., Levine, B., et al. ”A DICOM dataset for evaluation of medical image deidentification.” Sci Data 8, no. 1 (2021):183. DOI: 10.1038/s41597-021-00896-8

Pandora: Agent-Based Modelling framework for large-scale distributed simulations. Available: https://github.com/xrubio/pandora

Wilensky, Uri. NetLogo Version 6.4.0. Northwestern University, 2021. Available: https://ccl.northwestern.edu/netlogo

Halder, A., Talukdar, N. A. ”Brain tissue segmentation using improved kernelized rough-fuzzy C-means with spatio-contextual information from MRI.” Magn Reson Imaging 62 (2019): 129–151. DOI: 10.1016/j.mri.2019.06.015

Hall, L. O., Bensaid, A. M., Clarke, L. P., et al. ”A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain.” IEEE Trans Neural Netw 3, no. 5 (1992): 672–682. DOI: 10.1109/72.159326

Li, C., Goldgof, D. B., Hall, L. O. ”Knowledge-based classification and tissue labeling of MR images of human brain.” IEEE Trans Med Imaging 12, no. 4 (1993): 740–750. DOI: 10.1109/42.242709

Maji, P., Pal, S. K. ”Rough-fuzzy pattern recognition: applications in bioinformatics and medical imaging.” Wiley, 2012.

Maji, P., Pal, S. K. ”RFCM: a hybrid clustering algorithm using rough and fuzzy sets.” Fundam Inform 80, no. 4 (2007): 475–496. DOI: 10.3233/EFI-2007-80403

Ahmed, M. N., Yamany, S. M., Mohamed, N., et al. ”A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data.” IEEE Trans Med Imaging 21, no. 3 (2002): 193–199. DOI: 10.1109/42.996759

Halder, A. ”Kernel based rough fuzzy c-means clustering optimized using particle swarm optimization.” In: ISACC 2015. IEEE; 2015. DOI: 10.1109/ISACC.2015.44

Chen, S., Zhang, D. ”Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure.” IEEE Trans Syst Man Cybern B Cybern 34, no. 4 (2004): 1907–1916. DOI: 10.1109/TSMCB.2004.831296

Chen, L., Zou, J., Chen, C. L. P. ”Kernel Spatial Shadowed C-Means for Image Segmentation.” Int J Fuzzy Syst 16, no. 1 (2014). DOI: 10.1007/s40815-014-0013-5

Tavares, S. ”White Matter, Gray Matter and Cerebrospinal Fluid Segmentation from Brain Magnetic Resonance Imaging using Adaptive U-Net and Local Convolutional Neural Network.”

Müller, D., Soto-Rey, I., Kramer, F. ”Towards a guideline for evaluation metrics in medical image segmentation.” BMC Res Notes 15, no. 1 (2022): 210. DOI: 10.1186/s13104-022-06195-x




DOI: https://doi.org/10.31449/inf.v49i23.11386

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.