{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T15:25:33Z","timestamp":1773674733203,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T00:00:00Z","timestamp":1773532800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Precise segmentation of brain tumors from multimodal MRI scans is essential for accurate neuro-oncological diagnosis and treatment planning. To address this challenge, we propose a label-free optimization-driven segmentation framework based on the \u03b1-expansion graph cut algorithm, offering improved computational efficiency and interpretability compared to deep learning alternatives. The method relies on structured optimization and handcrafted features, including local intensity patches, entropy-based texture descriptors, and statistical moments, to compute voxel-wise unary potentials via gradient-boosted decision trees (XGBoost). These are integrated with spatially adaptive pairwise terms within a graph model optimized through \u03b1-expansion. Evaluation on 146 BraTS validation volumes demonstrates reliable whole-tumor overlap, with a mean Dice score of 0.855 \u00b1 0.184 and a 95% Hausdorff distance of 18.66 mm. Bootstrap analysis confirms the statistical stability of these results. The low computational overhead and modular design make the method particularly suitable for transparent and resource-constrained clinical deployment scenarios.<\/jats:p>","DOI":"10.3390\/computation14030070","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T13:32:07Z","timestamp":1773667927000},"page":"70","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimization-Driven Multimodal Brain Tumor Segmentation Using \u03b1-Expansion Graph Cuts"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0043-9892","authenticated-orcid":false,"given":"Roaa","family":"Soloh","sequence":"first","affiliation":[{"name":"Computer, Math and Sciences Department, College of Arts and Sciences, Rafik Hariri University, Damour-Chouf 2010, Lebanon"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4446-1891","authenticated-orcid":false,"given":"Bilal","family":"Nakhal","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Faculty of Science, Beirut Arab University, Beirut 1107 2809, Lebanon"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6859-033X","authenticated-orcid":false,"given":"Abdallah El","family":"Chakik","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Faculty of Science, Beirut Arab University, Beirut 1107 2809, Lebanon"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,15]]},"reference":[{"key":"ref_1","first-page":"251","article-title":"Cascaded Segmentation of Brain Tumors on Multi-Modality MR Images","volume":"11","author":"Ou","year":"2007","journal-title":"Med. Image Anal."},{"key":"ref_2","unstructured":"Bakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R.T., Berger, C., Ha, S.M., and Rozycki, M. (2018). Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)","volume":"34","author":"Menze","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Liu, X., Song, L., Liu, S., and Zhang, Y. (2021). A Review of Deep-Learning-Based Medical Image Segmentation Methods. Sustainability, 13.","DOI":"10.3390\/su13031224"},{"key":"ref_5","unstructured":"Boykov, Y., Veksler, O., and Zabih, R. (1998, January 23\u201325). Markov Random Fields with Efficient Approximations. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Santa Barbara, CA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1109\/34.969114","article-title":"Fast Approximate Energy Minimization via Graph Cuts","volume":"23","author":"Boykov","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/TPAMI.2004.1262177","article-title":"What Energy Functions Can Be Minimized via Graph Cuts?","volume":"26","author":"Kolmogorov","year":"2004","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","unstructured":"Delong, A., Osokin, A., Isack, H., and Boykov, Y. (2012, January 16\u201321). Fast Approximate Energy Minimization with Label Costs. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Mohammadi, S., and Allali, M. (2024). Advancing Brain Tumor Segmentation with Spectral\u2013Spatial Graph Neural Networks. Appl. Sci., 14.","DOI":"10.3390\/app14083424"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/42.906424","article-title":"Segmentation of Brain MR Images through a Hidden Markov Random Field Model and the Expectation\u2013Maximization Algorithm","volume":"20","author":"Zhang","year":"2001","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_11","first-page":"29","article-title":"Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features","volume":"75","author":"Zhao","year":"2019","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_12","first-page":"607","article-title":"A Comparison of Two Human Brain Tumor Segmentation Methods for MRI Data","volume":"6","author":"Egger","year":"2011","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102259","DOI":"10.1016\/j.media.2021.102259","article-title":"Relax and Focus on Brain Tumor Segmentation","volume":"75","author":"Wang","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_14","first-page":"102560","article-title":"Multi-Modal Tumor Segmentation Methods Based on Deep Learning: A Narrative Review","volume":"145","author":"Xue","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A Self-Configuring Method for Deep Learning-Based Biomedical Image Segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.cmpb.2018.01.003","article-title":"Supervised Learning-Based Multimodal MRI Brain Tumour Segmentation Using Texture Features from Supervoxels","volume":"157","author":"Soltaninejad","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_18","first-page":"393","article-title":"Conditional Adversarial Network for Semantic Segmentation of Brain Tumor","volume":"7","author":"Rezaei","year":"2017","journal-title":"J. Biomed. Phys. Eng."},{"key":"ref_19","first-page":"102957","article-title":"Cross-Modality Guidance-Aided Multi-Modal Learning with Dual Attention for MRI Brain Tumor Grading","volume":"88","author":"Xu","year":"2024","journal-title":"Med. Image Anal."},{"key":"ref_20","first-page":"102813","article-title":"Brain Tumor Segmentation Based on Deep Learning, Attention Mechanisms, and Energy-Based Uncertainty Prediction","volume":"87","author":"Schwehr","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_21","unstructured":"Wu, J., Fu, R., Fang, H., Zhang, Y., Yang, Y., Xiong, H., Liu, H., and Xu, Y. (2022). MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102475","DOI":"10.1016\/j.media.2022.102475","article-title":"Unsupervised Brain Imaging 3D Anomaly Detection and Segmentation with Transformers","volume":"79","author":"Pinaya","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"101706","DOI":"10.1016\/j.imu.2025.101706","article-title":"TransUNetB: An Advanced Transformer\u2013UNet Framework for Efficient and Explainable Brain Tumor Segmentation","volume":"59","author":"Khushubu","year":"2025","journal-title":"Inform. Med. Unlocked"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102776","DOI":"10.1016\/j.artmed.2024.102776","article-title":"A deep convolutional neural network for the automatic segmentation of glioblastoma brain tumor: Joint spatial pyramid module and attention mechanism network","volume":"148","author":"Liu","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104324","DOI":"10.1016\/j.cviu.2025.104324","article-title":"Brain tumor image segmentation based on shuffle transformer-dynamic convolution and inception dilated convolution","volume":"254","author":"Zhou","year":"2025","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"102788","DOI":"10.1016\/j.artmed.2024.102788","article-title":"Scalable Swin Transformer Network for Brain Tumor Segmentation from Incomplete MRI Modalities","volume":"149","author":"Zhang","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/JPROC.2021.3054390","article-title":"A Review of Deep Learning in Medical Imaging","volume":"109","author":"Zhou","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Soloh, R., El Batish, M., and Abou Orm, L. (2025, January 29\u201330). A Lightweight Adversarial and Graph-Cut Hybrid Framework for Accurate and Fast Brain Tumor Segmentation in FLAIR MRI. Proceedings of the 2025 IEEE International Conference on Emerging Trends in Engineering and Computing (ETECOM), Riffa, Bahrain.","DOI":"10.1109\/ETECOM66111.2025.11319072"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41597-024-03073-x","article-title":"Brain Tumor Segmentation Using Synthetic MR Images\u2014A Comparison of GANs and Diffusion Models","volume":"11","author":"Akbar","year":"2024","journal-title":"Sci. Data"},{"key":"ref_30","first-page":"119592","article-title":"Multi-Class Brain Tumor Segmentation Using Graph Attention Network","volume":"219","author":"Patel","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Soloh, R., Abou Orm, L., and El Batish, M. (2025, January 9\u201310). Enhanced Patch-Wise Brain Tumor Segmentation Using U-Net and \u03b1-Expansion-Based Graph Cut Refinement. Proceedings of the 2025 Eighth International Conference on Advances in Biomedical Engineering (ICABME), Debbieh, Lebanon.","DOI":"10.1109\/ICABME66883.2025.11211673"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e23132","DOI":"10.1002\/ima.23132","article-title":"Brain Tumor Segmentation Based on \u03b1-Expansion Graph Cut","volume":"34","author":"Soloh","year":"2024","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref_33","unstructured":"(2025, September 08). Multimodal Brain Tumor Segmentation Challenge 2019: Data. Available online: https:\/\/www.med.upenn.edu\/cbica\/brats2019\/data.html."},{"key":"ref_34","unstructured":"Lombaert, H., Sun, Y., Grady, L., and Xu, C. (2005, January 17\u201320). A Multilevel Banded Graph Cuts Method for Fast Image Segmentation. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Beijing, China."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Byeon, H., Al-Kubaisi, M., Dutta, A.K., Alghayadh, F., Soni, M., Bhende, M., Chunduri, V., Suresh Babu, K., and Jeet, R. (2024). Brain tumor segmentation using neuro-technology enabled intelligence-cascaded U-Net model. Front. Comput. Neurosci., 18.","DOI":"10.3389\/fncom.2024.1391025"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s44196-025-00787-7","article-title":"MSegNet: A Multi-View Coupled Cross-Modal Attention Model for Enhanced MRI Brain Tumor Segmentation","volume":"18","author":"Wang","year":"2025","journal-title":"Int. J. Comput. Intell. Syst."}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/3\/70\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T13:59:16Z","timestamp":1773669556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-3197\/14\/3\/70"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,15]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["computation14030070"],"URL":"https:\/\/doi.org\/10.3390\/computation14030070","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,15]]}}}