{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T16:48:40Z","timestamp":1782751720834,"version":"3.54.5"},"reference-count":40,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Accurate, automated delineation of adult diffuse gliomas from multi-parametric magnetic resonance imaging (mpMRI) is central to quantitative neuro-oncology. Volumetric 3D networks dominate the BraTS leaderboard but require expensive GPUs, long training cycles, and provide diminishing returns relative to their compute budget. Slice-wise 2D models, by contrast, discard inter-slice context that is informative for thin tumor rims and small enhancing foci. We introduce GDNet, a 2.5D multimodal MRI segmentation framework for adult glioma evaluated on the BraTS 2024 cohort. GDNet consumes a stack of three adjacent axial slices from the four standard BraTS modalities (T1, T1ce, T2, FLAIR) as a 12-channel input to a compact U-shaped encoder\u2013decoder with Group Normalization and predicts whole tumor (WT), tumor core (TC), and enhancing tumor (ET) masks for the central slice. The training pipeline pairs the 2.5D backbone with: (i) Exponential Moving Average (EMA) of model weights with decay 0.999, (ii) mixed tumor-aware slice sampling (p_tumor = 0.50), (iii) a compound Cross-Entropy + Soft-Dice loss, and (iv) AdamW with warm-up plus cosine annealing under Automatic Mixed Precision. We performed a systematic, step-by-step ablation covering a 2D baseline, EMA + mixed sampling, tumor-centered crop fine-tuning, a GDNet-inspired architectural integration, a region-aware loss, 3-slice and 5-slice 2.5D inputs, and connected-component post-processing, and we report multi-seed results to quantify reproducibility. On the held-out BraTS 2024 test partition, the final 3-slice 2.5D GDNet achieved positive-only Dice scores of 0.791 \u00b1 0.000 (WT), 0.736 \u00b1 0.003 (TC), 0.654 \u00b1 0.004 (ET), and a mean foreground positive-only Dice of 0.820 \u00b1 0.000 across seeds; the all-slice mean foreground Dice exceeded 0.927 \u00b1 0.000. Validation positive-only scores were 0.805 \u00b1 0.002 (WT), 0.757 \u00b1 0.004 (TC), 0.683 \u00b1 0.009 (ET). The inter-seed standard deviation was small for every region (\u22640.01 Dice points), indicating low inter-seed variance across the two seeds evaluated; with only two seeds, we regard this as preliminary evidence of training stability rather than a strong reproducibility claim. The ablation isolated EMA + mixed tumor sampling and the 2.5D context window as the dominant sources of improvement; notably, a GDNet-style architectural integration with a region-aware loss did not outperform the simpler 2.5D U-Net on positive-only WT\/TC\/ET, and light post-processing improved only all-slice Dice. A failure-mode audit found that the residual catastrophic predictions are concentrated on a small minority of diffuse, infiltrative tumors with mass effect. Conclusions: Carefully engineered training strategies, tumor-aware sampling, EMA stabilization, and a modest 2.5D context window recover a substantial fraction of the accuracy of much heavier 3D networks at a fraction of the compute, are reproducible across seeds, and outperform a heavier GDNet-inspired architectural variant on the same data. GDNet is therefore a practical and, pending external validation, potentially clinically deployable framework for multimodal glioma segmentation on workstation-class GPU hardware.<\/jats:p>","DOI":"10.3390\/jimaging12070288","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T15:27:37Z","timestamp":1782746857000},"page":"288","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GDNet: A Robust 2.5D Multimodal MRI Brain Tumor Segmentation Framework with EMA Stabilization and Tumor-Aware Sampling"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7118-0382","authenticated-orcid":false,"given":"Behnam","family":"Kiani Kalejahi","sequence":"first","affiliation":[{"name":"Department of Computer Science, School of Engineering, Central Asian University, Tashkent 111211, Uzbekistan"},{"name":"Faculty of Data Science and Information Technology, INTI International University, Nilai 71800, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sajid","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Engineering, Central Asian University, Tashkent 111211, Uzbekistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad Javad","family":"Rajabi","sequence":"additional","affiliation":[{"name":"Faculty of Data Science and Information Technology, INTI International University, Nilai 71800, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1093\/neuonc\/noab106","article-title":"The 2021 WHO Classification of Tumors of the Central Nervous System: A summary","volume":"23","author":"Louis","year":"2021","journal-title":"Neuro-Oncology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"iii1","DOI":"10.1093\/neuonc\/noab200","article-title":"CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2014\u20132018","volume":"23","author":"Ostrom","year":"2021","journal-title":"Neuro-Oncology"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.artmed.2018.08.008","article-title":"Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: A review","volume":"95","author":"Bernal","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"vdac081","DOI":"10.1093\/noajnl\/vdac081","article-title":"Automated brain tumor identification using magnetic resonance imaging: A systematic review and meta-analysis","volume":"4","author":"Kouli","year":"2022","journal-title":"Neuro-Oncol. Adv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1038\/s41698-024-00789-2","article-title":"A review of deep learning for brain tumor analysis in MRI","volume":"9","author":"Dorfner","year":"2025","journal-title":"npj Precis. Oncol."},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"170117","DOI":"10.1038\/sdata.2017.117","article-title":"Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Sci. Data"},{"key":"ref_8","unstructured":"Baid, U., Ghodasara, S., Mohan, S., Bilello, M., Calabrese, E., Colak, E., Farahani, K., Kalpathy-Cramer, J., Kitamura, F.C., and Pati, S. (2021). The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv."},{"key":"ref_9","unstructured":"de Verdier, M.C., Saluja, R., Gagnon, L., LaBella, D., Baid, U., Tahon, N.H., Foltyn-Dumitru, M., Zhang, J., Alafif, M., and Baig, S. (2024). The 2024 Brain Tumor Segmentation (BraTS) Challenge: Glioma Segmentation on Post-treatment MRI. arXiv."},{"key":"ref_10","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"MICCAI 2015"},{"key":"ref_11","first-page":"424","article-title":"3D U-Net: Learning dense volumetric segmentation from sparse annotation","volume":"Volume 9901","author":"Abdulkadir","year":"2016","journal-title":"MICCAI 2016"},{"key":"ref_12","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_13","first-page":"109","article-title":"TransBTS: Multimodal brain tumor segmentation using transformer","volume":"Volume 12901","author":"Wang","year":"2021","journal-title":"MICCAI 2021"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., and Xu, D. (2022). UNETR: Transformers for 3D medical image segmentation. 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE.","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"ref_15","first-page":"272","article-title":"Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images","volume":"Volume 12962","author":"Hatamizadeh","year":"2022","journal-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (MICCAI BrainLes 2021)"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_17","first-page":"178","article-title":"Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks","volume":"Volume 10670","author":"Wang","year":"2018","journal-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (MICCAI BrainLes 2017)"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Avesta, A., Hossain, S., Lin, M., Aboian, M., Krumholz, H.M., and Aneja, S. (2023). Comparing 3D, 2.5D, and 2D approaches to brain image auto-segmentation. Bioengineering, 10.","DOI":"10.3390\/bioengineering10020181"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ottesen, J.A., Yi, D., Tong, E., Iv, M., Latysheva, A., Saxhaug, C., Jacobsen, K.D., Helland, \u00c5., Emblem, K.E., and Rubin, D.L. (2023). 2.5D and 3D segmentation of brain metastases with deep learning on multinational MRI data. Front. Neuroinform., 16.","DOI":"10.3389\/fninf.2022.1056068"},{"key":"ref_20","first-page":"1748","article-title":"Enhanced brain stroke lesion segmentation in MRI using a 2.5D transformer backbone U-Net model","volume":"14","author":"Liu","year":"2024","journal-title":"Diagnostics"},{"key":"ref_21","first-page":"49","article-title":"Brain tumor segmentation methods based on MRI images: Review paper","volume":"5","author":"Guluzade","year":"2021","journal-title":"Khazar J. Sci. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., and Ahmadi, S.-A. (2016, January 25\u201328). V-Net: Fully convolutional neural networks for volumetric medical image segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, USA.","DOI":"10.1109\/3DV.2016.79"},{"key":"ref_23","first-page":"118","article-title":"nnU-Net for brain tumor segmentation","volume":"Volume 12659","author":"Isensee","year":"2020","journal-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (MICCAI BrainLes 2020)"},{"key":"ref_24","first-page":"311","article-title":"3D MRI brain tumor segmentation using autoencoder regularization","volume":"Volume 11384","author":"Myronenko","year":"2018","journal-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries (MICCAI BrainLes 2018)"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ferreira, A., Solak, N., Li, J., Dammann, P., Kleesiek, J., Alves, V., and Egger, J. (2024). How we won BraTS 2023 adult glioma challenge? Just faking it! Enhanced synthetic data augmentation and model ensemble for brain tumour segmentation. arXiv.","DOI":"10.1007\/978-3-031-76163-8_8"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1007\/s11760-023-02555-6","article-title":"Brain tumor segmentation by auxiliary classifier generative adversarial network","volume":"17","author":"Meshgini","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kiani Kalejahi, B., Meshgini, S., and Danishvar, S. (2023). Segmentation of brain tumor using a 3D generative adversarial network. Diagnostics, 13.","DOI":"10.3390\/diagnostics13213344"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Vafaeezadeh, M., Behnam, H., and Gifani, P. (2024). Ultrasound image analysis with vision transformers, review. Diagnostics, 14.","DOI":"10.20944\/preprints202401.0309.v1"},{"key":"ref_29","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_30","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, G., Elsen, E., Garcia, D., Ginsburg, B., Houston, M., Kuchaiev, O., and Venkatesh, G. (2018). Mixed precision training. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Wu, Y., and He, K. (2018). Group normalization. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref_32","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_33","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). SGDR: Stochastic gradient descent with warm restarts. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_34","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled weight decay regularization. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., and Cardoso, M.J. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (MICCAI DLMIA), Springer.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Kiani Kalejahi, B., Danishvar, S., and Rajabi, M.J. (2026). GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models. Biomimetics, 11.","DOI":"10.3390\/biomimetics11030175"},{"key":"ref_38","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_39","unstructured":"Adewole, M., Rudie, J.D., Gbdamosi, A., Toyobo, O., Raymond, C., Zhang, D., Omidiji, O., Akinola, R., Suwaid, M.A., and Emegoakor, A. (2023). The Brain Tumor Segmentation (BraTS) Challenge 2023: Glioma Segmentation in Sub-Saharan Africa Patient Population (BraTS-Africa). arXiv."},{"key":"ref_40","unstructured":"Fathi Kazerooni, A., Khalili, N., Liu, X., Gandhi, D., Jiang, Z., Anwar, S.M., Albrecht, J., Adewole, M., Anazodo, U., and Anderson, H. (2024). The Brain Tumor Segmentation in Pediatrics (BraTS-PEDs) Challenge: Focus on Pediatrics. arXiv."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/7\/288\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T16:40:17Z","timestamp":1782751217000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/7\/288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":40,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["jimaging12070288"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12070288","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]}}}