Department of Electronics and Communication Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India.
Accurate analysis of complex imaging data is crucial in regenerative science, where precision is essential. However, challenges such as noise, anatomical variations, and low contrast regions hinder effective image interpretation. This paper introduces MATHSegNet, a Multi-Scale Adaptive Transformer-Enhanced Deep Neural Network, designed to enhance image analysis efficiency and accuracy. MATHSegNet integrates CNNs for fine-grained local feature extraction with Transformers to capture global dependencies and spatial relationships. Multi-scale feature extraction ensures precise representation at different spatial levels, while attention mechanisms highlight key regions for improved analysis. A hybrid loss function combining Dice Loss and Unified Focal Loss effectively addresses class imbalance, improving segmentation of smaller structures. Developed using PyTorch and TensorFlow, MATHSegNet offers fast training and adaptability. Experimental results demonstrate a 7–10% improvement over existing models, validated using metrics such as Dice Similarity Coefficient, IoU, Sensitivity, and Specificity, making MATHSegNet a scalable and interpretable solution for regenerative imaging tasks.
A. Atala, “Regenerative medicine and tissue engineering: Current developments and future prospects,” Nature Reviews Materials, vol.4, no.9, pp.610–622, (2019). https://doi.org/10.1038/s41578-019-0121-3
P. Kumar, & S. Lee, “Addressing anatomical heterogeneity in regenerative medicine through personalized imaging approaches,” Frontiers in Bioengineering and Biotechnology, 9, 678901, (2021). https://doi.org/10.3389/fbioe.2021.678901
Y. Wang, & R. Singh, “Overcoming noise and resolution challenges in CT imaging for regenerative therapies,” Medical Physics, vol.47, no.7, pp.3501–3512, (2020). https://doi.org/10.1002/mp.14256
M. Garcia, & R. Patel, “Multi-modal imaging in regenerative medicine: Integrating diverse data types for improved therapeutic outcomes,” Advanced Healthcare Materials, vol.9, no.18, Article 2000123, (2020). https://doi.org/10.1002/adhm.202000123
Y. Zhang, Q. Liu, & D. Shen, “Hybrid high-resolution and high-level feature learning framework for brain tumor segmentation,” IEEE Transactions on Medical Imaging, 38(6), 1446–1456, (2019). https://doi.org/10.1109/TMI.2019.2891605
N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-End Object Detection with Transformers,” Computer Vision – ECCV 2020, pp. 213–229, 2020, doi: 10.1007/978-3-030-58452-8_13.
Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 3–11, 2018, doi: 10.1007/978-3-030-00889-5_1.
O. Oktay, et al., Attention U-Net: Learning where to look for the pancreas, (2018). arXiv preprint. https://arxiv.org/abs/1804.03999
L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 834–848, Apr. 2018, doi: 10.1109/tpami.2017.2699184.
A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, N. Houlsby, “An image is worth 16x16 words: Transformers for image recognition at scale,” International Conference on Learning Representations (ICLR), (2021). https://arxiv.org/abs/2010.11929
Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pp. 9992–10002, Oct. 2021, doi: 10.1109/iccv48922.2021.00986.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, I. Polosukhin, “Attention is all you need,” Advances in Neural Information Processing Systems, 30, (2017). https://arxiv.org/abs/1706.03762
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2016, doi: 10.1109/cvpr.2016.90.
D. Benvenuto, D. P. Smith, M. Allen, Y. Wang, & L. Ying, “Multi-modal imaging techniques for regenerative medicine,” Journal of Biomedical Imaging, Article 123456, (2021). https://doi.org/10.1155/2021/123456
X. Zhang, Y. Zhao, & F. Chen, “STUNet: A hybrid UNet framework enhanced by Swin Transformers for medical image segmentation,” Artificial Intelligence in Medicine, 132, 102431, (2023). https://doi.org/10.1016/j.artmed.2023.102431
Y. Zhang, Z. Xu, & Y. Shi, “CRF-Net: Enhancing semantic segmentation using Conditional Random Fields and CNNs,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 3541-3550, (2023). https://github.com/daidshow/CRF-Net
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28.
C. H. Sudre, W. Li, T. Vercauteren, S. Ourselin, and M. Jorge Cardoso, “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, pp. 240–248, 2017, doi: 10.1007/978-3-319-67558-9_28.
L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,” Computer Vision – ECCV 2018, pp. 833–851, 2018, doi: 10.1007/978-3-030-01234-2_49.
H. Tang, X. Liu, W. Yan, X. Peng, & W. Sun, “Enhancing boundary precision in medical image segmentation using GAN-based postprocessing,” Medical Image Analysis, 81, 102512, (2022). https://doi.org/10.1016/j.media.2022.102512
Q. Huang, S. Zhou, L. Wang, & T. Zhang, “HMDA: Hybrid multi-scale deformable attention for robust medical image segmentation,” IEEE Transactions on Medical Imaging, 41(12), 3456–3468, (2022). https://doi.org/10.1109/TMI.2022.3187652
Y. Jiang, S. Wang, & J. Wu, “Hybrid U-Net-transformer model for improved anatomical feature segmentation,” Neural Networks, 154, 121–133, (2022). https://doi.org/10.1016/j.neunet.2022.03.001
D. Luo, H. Xu, & G. Tang, “Graph-based neural networks with transformers for medical image segmentation of irregular anatomical structures,” Journal of Biomedical Informatics, 139, 104295, (2023). https://doi.org/10.1016/j.jbi.2023.104295
C. Wang, Q. Yang, & J. Li, “H2Former: Hierarchical hybrid transformers for segmentation in multi-modal medical imaging. Medical Image Analysis, 87, 102748, (2023). https://doi.org/10.1016/j.media.2023.102748
F. Li, R. Zhang, & X. Meng, “Domain-specific transformer-based model for fluorescence microscopy image segmentation,” Computers in Biology and Medicine, 151, 106576, (2024). https://doi.org/10.1016/j.compbiomed.2024.106576
Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger, “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation,” Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, pp. 424–432, 2016, doi: 10.1007/978-3-319-46723-8_49.
J. Guo, F. Han, & S. Wang, “Transformer-based architectures for medical image segmentation: A review,” Medical Image Analysis, 77, 102360, (2022). https://doi.org/10.1016/j.media.2021.102360
S. Liu, & H. Zhang, “Enhancing regenerative therapy monitoring through advanced MRI techniques,” Journal of Medical Imaging, 10(2), 112–130, (2023). https://doi.org/10.1117/1.JMI.10.2.112
J. Smith, & A. Lee, “A study on the effectiveness of Dice loss in binary segmentation tasks,” Journal of Medical Imaging, 15(4), 123-135, (2020).
M. Zhang, & H. Wang, “Unified Focal Loss for improved segmentation in imbalanced datasets,” International Journal of Computer Vision, 39(2), 98-110, (2021).
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Mallikka R, Suresh Kumar D, Divya Rohatgi, Badugu Suresh, David Neels Ponkumar Devadhas and Thota Radha Rajesh;
Methodology: Mallikka R, Suresh Kumar D and Divya Rohatgi;
Software: Badugu Suresh, David Neels Ponkumar Devadhas and Thota Radha Rajesh;
Data Curation: Mallikka R, Suresh Kumar D and Divya Rohatgi;
Writing- Original Draft Preparation: Mallikka R, Suresh Kumar D, Divya Rohatgi, Badugu Suresh, David Neels Ponkumar Devadhas and Thota Radha Rajesh;
Validation: Badugu Suresh, David Neels Ponkumar Devadhas and Thota Radha Rajesh;
Writing- Reviewing and Editing: Mallikka R, Suresh Kumar D, Divya Rohatgi, Badugu Suresh, David Neels Ponkumar Devadhas and Thota Radha Rajesh;
All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
We would like to thank Reviewers for taking the time and effort necessary to review the manuscript. We sincerely appreciate all valuable comments and suggestions, which helped us to improve the quality of the manuscript.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Mallikka R
Department of Computer Science and Engineering, SRM Institute of Science and Technology, SRM Deemed University, Tiruchirappalli, Tamil Nadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Mallikka R, Suresh Kumar D, Divya Rohatgi, Badugu Suresh, David Neels Ponkumar Devadhas and Thota Radha Rajesh, “Multi-Scale Adaptive Transformer Enhanced Deep Neural Network for Advanced Image Analysis in Regenerative Science”, Journal of Machine and Computing, pp. 1032-1047, April 2025, doi: 10.53759/7669/jmc202505082.
