ANALYSIS OF BIOMEDICAL 3D DATA SEGMENTATION METHODS USING DEEP LEARNING

DOI: 10.31673/2786-8362.2025.017489

Abstract

This article provides a comprehensive review of modern approaches to the segmentation of
biomedical 3D scans using deep learning techniques. A comparative analysis of neural network
architectures is conducted, particularly convolutional neural networks (CNNs), Transformers, and the latest
Mamba-type models, which offer varying levels of computational complexity, accuracy, and generalization
capability. The advantages of hybrid architectures, multimodal approaches, and pretraining strategies –
including self-supervised learning and generative adversarial networks (GANs) – are described as methods
to improve performance under conditions of limited labeled data. The article highlights current
segmentation challenges related to the high complexity of biomedical images, variability in scanning
protocols, and resource constraints. Practical recommendations are offered for selecting the appropriate
architecture based on task requirements, dataset characteristics, and available computational resources.
Standard evaluation metrics (e.g., Dice coefficient, Hausdorff distance) and the use of publicly available
medical datasets (BraTS, LiTS, ACDC) for model benchmarking are also discussed.
Keywords: medical image segmentation, 3D biomedical data, deep learning, convolutional neural
networks, transformers, Mamba architecture, medical imaging, multimodal data, data augmentation, neural
models, computational efficiency, self-supervised learning, BraTS, LiTS, ACDC

References
1. Ronneberger, O., Fischer, P., & Brox, T. U-Net: Convolutional networks for biomedical image
segmentation. MICCAI, 234–241.
2. Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Xing, L. TransUNet: Transformers Make
Strong Encoders for Medical Image Segmentation. arXiv preprint arXiv:2102.04306.
3. Hatamizadeh, A., Nath, V., Liu, Y., Yin, Z., Kapp, D., & Tagare, H. Swin-Unet: Unet-like Pure
Transformer for Medical Image Segmentation. arXiv preprint arXiv:2205.05003.
4. Zhang, Y., Yang, J., & Wang, Q. GAN-based data augmentation for liver tumor segmentation
in CT scans. Medical Image Analysis, 78, 102401.
5. Zhou, Z., Seyedhosseini, M., & Tasdizen, T. Self-supervised learning for 3D medical image
segmentation. EEE Transactions on Medical Imaging, 42(3), 901–912.
6. Kim, H., Lee, J., & Park, J. Efficient3DNet: Lightweight 3D convolutional networks for fast
medical image segmentation. Computerized Medical Imaging and Graphics, 100, 102198.
7. S. Niyas, S.J. Pawan, M. Anand Kumar, Jeny Rajan. Medical image segmentation with 3D
convolutional neural networks: A survey. Neurocomputing, Volume 493,7 July 2022, Pages 397-413
https://doi.org/10.1016/j.neucom.2022.04.065.
8. Ali Hatamizadeh, Yucheng Tang, Vishwesh Nath, Dong Yang, Andriy Myronenko, Bennett
Landman, Holger R. Roth, Daguang Xu; Proceedings of the IEEE/CVF Winter Conference on
Applications of Computer Vision (WACV), 2022, pp. 574-584
9. Zhaohu Xing, Tian Ye, Yijun Yang, Guang Liu, Lei Zhu. SegMamba: Long-range Sequential
Modeling Mamba For 3D Medical Image Segmentation. (2024)
https://doi.org/10.48550/arXiv.2401.13560.
10. Md. Eshmam Rayed, S.M. Sajibul Islam, Sadia Islam Niha, Jamin Rahman Jim, Md Mohsin
Kabir, M.F. Mridha. Deep learning for medical image segmentation: State-of-the-art advancements
and challenges. ELSEVIER Volume 47, 2024,101504https://doi.org/10.1016/j.imu.2024.101504.