Skip to main navigation menu Skip to main content Skip to site footer

August 21, 2026; Liverpool, UK
XI International Scientific and Theoretical Conference «Theoretical and practical scientific achievements: research and results of their implementation»

Papers indexed in Google Scholar

THE EVOLUTION OF THE BRATS DATASET AND COMPARATIVE ANALYSIS OF 3D SEGMENTATION ARCHITECTURES

Published 21.08.2026

  • Otabek Puladjonov
    •

Otabek Puladjonov
Sharda University, Uzbekistan

PDF

Abstract

Brain Tumor Segmentation (BraTS) challenges have significantly advanced research in brain tumor segmentation and related medical imaging tasks. Since its inception at MICCAI 2012, the BraTS initiative has driven the state-of-the-art in brain glioma image analysis by providing high-quality, multi-institutional annotated datasets and establishing rigorous benchmarks for algorithmic development. Over the years, these datasets have grown in size, complexity, and scope, incorporating refined pre-processing and annotation protocols to better reflect diverse clinical realities. This evolution has forced neural architectures to transition from foundational 3D convolutional networks to highly complex, globally contextualized vision transformers,. By synthesizing insights from recent challenge iterations, this section elucidates the progression of dataset curation and comprehensively evaluates the performance trajectories of three pivotal architectures: 3D U-Net, V-Net, and Swin UNETR. The trajectory of the BraTS datasets reflects a continuous push toward clinical precision and algorithmic robustness.

Author Biography

Otabek Puladjonov

Teaching Assistant; Faculty of Engineering and Technology

References

  1. Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H. R., & Xu, D. (2022). Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images. BrainLes@MICCAI.
  2. Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016). 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. Medical Image Computing and Computer-Assisted Intervention (MICCAI).
  3. Milletari, F., Navab, N., & Ahmadi, S. A. (2016). V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016, 565-571.
  4. MDPI (2025). Advancing Precision: A Comprehensive Review of MRI Segmentation Datasets from BraTS Challenges (2012–2025). Sensors, 25(6), 1838.
  5. Menze, B. H., et al. (2015). The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Transactions on Medical Imaging, 34(10), 1993-2024.
  6. Bakas, S., et al. (2018). Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge. arXiv preprint arXiv:1811.02629.
  7. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. MICCAI.
  8. Baid, U., et al. (2021). The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification. arXiv preprint arXiv:2107.02314.
  9. Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, 18(2), 203-211.
  10. Vaswani, A., et al. (2017). Attention is all you need. Advances in neural information processing systems, 30.
  11. Dosovitskiy, A., et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
  12. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. ICCV.
  13. Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H., & Xu, D. (2022). UNETR: Transformers for 3D Medical Image Segmentation. WACV.
  14. Jiang, Z., Capellán-Martín, D., Parida, A., Liu, X., Ledesma-Carbayo, M. J., Muhammad Anwar, S., & Linguraru, M. G. (2024). Enhancing Generalizability in Brain Tumor Segmentation: Model Ensemble with Adaptive Post - Processing. 2024 IEEE International Symposium on Biomedical Imaging (ISBI).
  15. Zhou, J., Ye, J., Liang, Y., Zhao, J., Wu, Y., Luo, S., Lai, X., & Wang, J. (2022). scSE-NL V-Net: A Brain Tumor Automatic Segmentation Method Based on Spatial and Channel "Squeeze-and-Excitation" Network With Non - local Block. Frontiers in Neuroscience, 16.
  16. Kazerooni, A. F., et al. (2024). The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs). arXiv preprint.
  17. Moawad, A. W., et al. (2023). The Brain Tumor Segmentation (BraTS) Challenge 2023: Local Health Challenges in Sub-Saharan Africa. arXiv preprint arXiv:2305.19277.
  18. Karimi, D., Dou, H., Warfield, S. K., & Gholipour, A. (2021). Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis. Medical Image Analysis, 65, 101759.

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.