{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:56:58Z","timestamp":1792000618517,"version":"4.4.0"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate segmentation of low-grade gliomas (LGGs) in FLAIR MRI remains challenging due to low-contrast tumor boundaries, irregular morphology, and extreme class imbalance. This work presents a lightweight hybrid segmentation framework that integrates three complementary components: (1) a fast graph-based region refinement step using GrabCut applied during training only to enhance tumor\u2013background contrast, (2) a compact U-Net architecture whose filter configuration is automatically selected using a small-scale genetic algorithm, and (3) an analytical evaluation of lightweight post-processing strategies studied separately from the final GA-optimized model. The method was evaluated on the LGG-MRI-Segmentation dataset using strict patient-level splits of 79 training, 19 validation, and 12 testing patients. The final model achieved strong slice-wise performance with a mean Dice of 0.9132 and a median Dice of 0.9855; the lower mean reflects the influence of more difficult, lower-performing slices and therefore provides a more conservative summary of overall performance across the evaluated test cases. Additional metrics include an IoU of 0.8851, sensitivity of 0.8954, precision of 0.9523, specificity of 0.9997, and an HD95 of 1.00 mm, indicating highly accurate boundary delineation. For contextual benchmarking, a 2D nnU-Net model was trained on the same dataset. nnU-Net achieved a mean validation Dice of 0.8450 and a best validation EMA Dice of 0.9134. Because these nnU-Net Dice values were obtained from its validation workflow rather than the exact slice-wise test procedure used for the proposed model, they are presented as contextual reference results rather than strictly matched test-set estimates. The proposed framework required substantially less training time under the evaluated implementations. Taken together, these findings demonstrate that a carefully coordinated combination of preprocessing, lightweight architectural optimization, and efficient post-processing can achieve strong segmentation performance on the evaluated dataset while remaining computationally efficient. These findings suggest that the proposed framework is promising for computationally constrained LGG segmentation workflows. However, broader clinical applicability requires validation on independent external cohorts before generalizability can be established.<\/jats:p>","DOI":"10.1371\/journal.pone.0338773","type":"journal-article","created":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:40:51Z","timestamp":1791999651000},"page":"e0338773","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Brain tumor segmentation using a combination of graph cut and optimized U-Net with genetic algorithm: An efficient hybrid framework for enhanced medical image analysis"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2341-0291","authenticated-orcid":true,"given":"Reem M.","family":"Mostafa","sequence":"first","affiliation":[{"name":"Faculty of Science Al-Azhar University","place":["Assiut, Asyut, Egypt"],"department":["Department of Mathematics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emad","family":"Mabrouk","sequence":"additional","affiliation":[{"name":"American University of the Middle East","place":["Egaila, Kuwait"],"department":["College of Engineering and Technology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed Saed","family":"Salim","sequence":"additional","affiliation":[{"name":"Faculty of Science Al-Azhar University","place":["Assiut, Asyut, Egypt"],"department":["Department of Mathematics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Ayman","sequence":"additional","affiliation":[{"name":"Faculty of Science Al-Azhar University","place":["Assiut, Asyut, Egypt"],"department":["Department of Mathematics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamdy Z.","family":"Zidan","sequence":"additional","affiliation":[{"name":"Faculty of Science Al-Azhar University","place":["Assiut, Asyut, Egypt"],"department":["Department of Mathematics"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,14]]},"reference":[{"issue":"9","key":"pone.0338773.ref001","doi-asserted-by":"crossref","first-page":"179","DOI":"10.3390\/jimaging7090179","article-title":"A survey of brain tumor segmentation and classification algorithms","volume":"7","author":"ES Biratu","year":"2021","journal-title":"J Imaging"},{"key":"pone.0338773.ref002","doi-asserted-by":"crossref","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","article-title":"U-Net and its variants for medical image segmentation: A review of theory and applications","volume":"9","author":"N Siddique","year":"2021","journal-title":"IEEE Access"},{"key":"pone.0338773.ref003","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.canlet.2020.02.025","article-title":"Imaging of intratumoral heterogeneity in high-grade glioma","volume":"477","author":"LS Hu","year":"2020","journal-title":"Cancer Lett"},{"issue":"12","key":"pone.0338773.ref004","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0144479","article-title":"Correction: Enhanced performance of brain tumor classification via tumor region augmentation and partition","volume":"10","author":"J Cheng","year":"2015","journal-title":"PLoS One"},{"key":"pone.0338773.ref005","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume-title":"Lecture Notes in Computer Science","author":"O Ronneberger","year":"2015"},{"key":"pone.0338773.ref006","first-page":"3","article-title":"Unet++: A nested u-net architecture for medical image segmentation.","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support","author":"Z Zongwei","year":"2018"},{"key":"pone.0338773.ref007","article-title":"Attention u-net based adversarial architectures for chest x-ray lung segmentation","volume":"2692","author":"G Ga\u00e1l","year":"2020","journal-title":"CEUR Workshop Proceedings"},{"key":"pone.0338773.ref008","article-title":"Residual attention u-net for automated multi-class segmentation of covid-19 chest ct images","author":"X Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0338773.ref009","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-Excitation Networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018. 7132\u201341. https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0338773.ref010","unstructured":"Pedano N, Flanders AE, Scarpace L, Mikkelsen T, Eschbacher JM, Hermes B, et al. The cancer genome atlas low grade glioma collection (tcga-lgg). 2016."},{"issue":"4","key":"pone.0338773.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447582","article-title":"A comprehensive survey of neural architecture search: Challenges and solutions","volume":"54","author":"P Ren","year":"2021","journal-title":"ACM Computing Surveys"},{"key":"pone.0338773.ref012","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnu-net: Self-configuring method for biomedical image segmentation","volume":"18","author":"F Isensee","year":"2021","journal-title":"Nature Methods"},{"key":"pone.0338773.ref013","doi-asserted-by":"crossref","unstructured":"Zhao Y-X, Zhang Y-M, Liu C-L. Bag of tricks for 3d mri brain tumor segmentation. In: BrainLes 2019, MICCAI, 2020. 210\u201320.","DOI":"10.1007\/978-3-030-46640-4_20"},{"key":"pone.0338773.ref014","first-page":"184","article-title":"3D Dilated Multi-fiber Network for Real-Time Brain Tumor Segmentation in MRI","volume-title":"Lecture Notes in Computer Science","author":"C Chen","year":"2019"},{"key":"pone.0338773.ref015","doi-asserted-by":"crossref","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. Swin-unet: Unet-like pure transformer for medical image segmentation. In European Conference on Computer Vision (ECCV) Workshops. Springer. 2022. p. 205\u201318.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"pone.0338773.ref016","first-page":"267","article-title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","volume-title":"Lecture Notes in Computer Science","author":"O Petit","year":"2021"},{"issue":"3","key":"pone.0338773.ref017","doi-asserted-by":"crossref","first-page":"362","DOI":"10.2174\/2213275912666181207152633","article-title":"Brain tumor detection from MR images employing fuzzy graph cut technique","volume":"13","author":"J Dogra","year":"2020","journal-title":"RACSC"},{"issue":"4","key":"pone.0338773.ref018","article-title":"Brain tumor segmentation based on \u03b1-expansion graph cut","volume":"34","author":"S Roaa","year":"2024","journal-title":"Int J Imaging Syst Technol"},{"key":"pone.0338773.ref019","doi-asserted-by":"crossref","unstructured":"Lambora A, Gupta K, Chopra K. Genetic Algorithm- A Literature Review. In: 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), 2019. 380\u20134. https:\/\/doi.org\/10.1109\/comitcon.2019.8862255","DOI":"10.1109\/COMITCon.2019.8862255"},{"key":"pone.0338773.ref020","volume-title":"Genetic Algorithms and Engineering Optimization","author":"M Gen","year":"2023"},{"issue":"4","key":"pone.0338773.ref021","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1002\/jemt.22994","article-title":"Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN)","volume":"81","author":"S Iqbal","year":"2018","journal-title":"Microsc Res Tech"},{"key":"pone.0338773.ref022","doi-asserted-by":"crossref","unstructured":"DSouza AM, Chen L, Wu Y, Abidin AZ, Xu C, Wism\u00fcller A. MRI tumor segmentation with densely connected 3D CNN. In: Medical Imaging 2018: Image Processing, 2018. 50. http:\/\/dx.doi.org\/10.1117\/12.2293394","DOI":"10.1117\/12.2293394"},{"issue":"7","key":"pone.0338773.ref023","first-page":"1082","article-title":"Brain tumor segmentation in fluid-attenuated inversion recovery mri scans using a residual u-net architecture","volume":"14","author":"N Mahyoub","year":"2023","journal-title":"Int J Adv Comp Sci Appl"},{"key":"pone.0338773.ref024","doi-asserted-by":"crossref","first-page":"1449982","DOI":"10.3389\/fonc.2024.1449982","article-title":"Vasari 2.0: A new updated mri vasari lexicon to predict grading and idh status in brain glioma","volume":"14","author":"A Negro","year":"2024","journal-title":"Front Oncol"},{"key":"pone.0338773.ref025","doi-asserted-by":"crossref","unstructured":"Ayman A, Mabrouk E, Elnomery Z. Adaptation of Region Growing thresholds using Memetic Programming algorithm. In: 2013 IEEE\/ACIS 12th International Conference on Computer and Information Science (ICIS), 2013. 29\u201334. http:\/\/dx.doi.org\/10.1109\/icis.2013.6607812","DOI":"10.1109\/ICIS.2013.6607812"},{"key":"pone.0338773.ref026","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.jocs.2019.01.002","article-title":"Immune system programming for medical image segmentation","volume":"31","author":"E Mabrouk","year":"2019","journal-title":"J Comput Sci"},{"issue":"4","key":"pone.0338773.ref027","doi-asserted-by":"crossref","first-page":"256","DOI":"10.3390\/a19040256","article-title":"Genetic programming algorithm evolving robust unary costs for efficient graph cut segmentation","volume":"19","author":"RM Mostafa","year":"2026","journal-title":"Algorithms"},{"issue":"1","key":"pone.0338773.ref028","doi-asserted-by":"crossref","first-page":"300","DOI":"10.21037\/qims-20-783","article-title":"Evaluation of magnetic resonance image segmentation in brain low-grade gliomas using support vector machine and convolutional neural network","volume":"11","author":"Q Yang","year":"2021","journal-title":"Quant Imaging Med Surg"},{"key":"pone.0338773.ref029","article-title":"Enhancing brain tumor segmentation using channel attention and transfer learning","author":"M Behzadpour","year":"2025","journal-title":"arXiv preprint"},{"key":"pone.0338773.ref030","article-title":"Evolutionary neural architecture search for retinal vessel segmentation","author":"M Baldeon-Calisto","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0338773.ref031","doi-asserted-by":"crossref","unstructured":"Addula SR, Sekhar Sajja G. Automated Machine Learning to Streamline Data-Driven Industrial Application Development. In: 2024 Second International Conference Computational and Characterization Techniques in Engineering & Sciences (IC3TES), 2024. 1\u20134. http:\/\/dx.doi.org\/10.1109\/ic3tes62412.2024.10877481","DOI":"10.1109\/IC3TES62412.2024.10877481"},{"issue":"6","key":"pone.0338773.ref032","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): Maintaining and operating a public information repository","volume":"26","author":"K Clark","year":"2013","journal-title":"J Digit Imaging"},{"key":"pone.0338773.ref033","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","article-title":"Grabcut: Interactive foreground extraction using iterated graph cuts","volume":"23","author":"C Rother","year":"2004","journal-title":"ACM Transactions on Graphics"},{"key":"pone.0338773.ref034","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S-A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), 2016. 565\u201371. http:\/\/dx.doi.org\/10.1109\/3dv.2016.79","DOI":"10.1109\/3DV.2016.79"},{"key":"pone.0338773.ref035","doi-asserted-by":"crossref","unstructured":"Setiawan AGW. Image segmentation metrics in skin lesion: Accuracy, sensitivity, specificity, dice coefficient, jaccard index, and matthews correlation coefficient. 2020;97\u2013102.","DOI":"10.1109\/CENIM51130.2020.9297970"},{"key":"pone.0338773.ref036","doi-asserted-by":"crossref","unstructured":"Sudre C, Li W, et al. Generalised dice overlap as a deep learning loss function. In: DLMIA and ML-CDS, MICCAI, 2017. 240\u20138.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"pone.0338773.ref037","unstructured":"Reinke A, Maier-Hein L, Delphi consortium on metrics. Common limitations of performance metrics in biomedical image analysis. In: Medical Imaging with Deep Learning (MIDL), 2021."},{"key":"pone.0338773.ref038","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/978-1-4612-4380-9_16","article-title":"Individual comparisons by ranking methods","volume-title":"Breakthroughs in Statistics","author":"F Wilcoxon","year":"1992"},{"key":"pone.0338773.ref039","doi-asserted-by":"crossref","DOI":"10.4135\/9781412984997","volume-title":"Meta-analytic procedures for social research","author":"R Rosenthal","year":"1991"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0338773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:41:01Z","timestamp":1791999661000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0338773"}},"subtitle":[],"editor":[{"given":"Mario","family":"Tortora","sequence":"first","affiliation":[{"name":"Universit\u00e0 degli Studi di Napoli Federico II: Universita degli Studi di Napoli Federico II","place":["ITALY"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,14]]},"references-count":39,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0338773","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,14]]}}}