Objective: This review delineates the evolution of attention architectures in automated tumor segmentation across three pivotal paradigms: classic Pre-Transformer attention, dominant Transformer-based self-attention, and emerging Mamba-based state space models.
Methods: We synthesize their functional roles—from channel enhancement to long-range dependency modelingand critically assess hybrid structures designed for multimodal clinical oncology scenarios.
Findings/Results: The review establishes attention mechanisms as a foundational pillar for the next generation of intelligent segmentation tools, highlighting their potential in feature enhancement and localization.
Conclusion: Interrogating current challenges and charting future trajectories, these mechanisms are poised to profoundly impact the landscape of precision medicine.
| [1] |
Withey DJ, Koles ZJ. A review of medical image segmentation: methods and available software. Int J Bioelectromagn. 2008;10(3):125-148.
|
| [2] |
Liu X, Song L, Liu S, et al. A review of deep-learning-based medical image segmentation methods. Sustainability. 2021;13(3):1224.
|
| [3] |
Ronneberger O, Fischer P, Brox T, U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer international publishing; 2015:234-241.
|
| [4] |
Li Z, Zhang H, Li Z, et al. Residual-attention UNet++: a nested residual-attention U-net for medical image segmentation. Appl Sci. 2022;12(14):7149.
|
| [5] |
Wang R, Lei T, Cui R, et al. Medical image segmentation using deep learning: a survey. IET Image Proc. 2022;16(5):1243-1267.
|
| [6] |
Azad R, Aghdam EK, Rauland A, et al. Medical image segmentation review: the success of U-Net. IEEE Trans Pattern Anal Mach Intell. 2024;46(12):10076-10095.
|
| [7] |
Zhang J, Chen X, Yang B, et al. Advances in attention mechanisms for medical image segmentation. Comp Sci Rev. 2025;56:100721.
|
| [8] |
Xiao H, Li L, Liu Q, et al. Transformers in medical image segmentation: a review. Biomed Signal Process Control. 2023;84:104791.
|
| [9] |
Papanastasiou G, Dikaios N, Huang J, et al. Is attention all you need in medical image analysis? A review. IEEE J Biomed Health Inf. 2023;28(3):1398-1411.
|
| [10] |
Qi X, Zhi M. A review of attention mechanisms in image processing. J Front Comp Sci Technol. 2024;18(2):345-362.
|
| [11] |
Liu W, Lu X. Research Progress of Transformer Based on Computer Vision. Comp Eng Applications. 2022;58(6):1-16.
|
| [12] |
Jin Q, Meng Z, Sun C, et al. RA-UNet: a hybrid deep attention-aware network to extract liver and tumour in CT scans. Front Bioeng Biotechnol. 2020;8:605132.
|
| [13] |
Chen Y, Zheng C, Yi Z, et al. A Survey of Liver and Tumour Image Segmentation Methods. Application Res Comp. 2022;39(3):641-650.
|
| [14] |
Wang Z, Zou Y, Liu PX. Hybrid dilation and attention residual U-Net for medical image segmentation. Comput Biol Med. 2021;134:104449.
|
| [15] |
Pang S, Du A, Orgun MA, et al. Tumour attention networks: better feature selection, better tumour segmentation. Neural Netw. 2021;140:203-222.
|
| [16] |
Zhang Q, Liang Y, Zhang Y, et al. A comparative study of attention mechanism based deep learning methods for bladder tumour segmentation. Int J Med Informatics. 2023;171:104984.
|
| [17] |
Gu R, Wang G, Song T, et al. CA-Net: comprehensive attention convolutional neural networks for explainable medical image segmentation. IEEE Trans Med Imaging. 2020;40(2):699-711.
|
| [18] |
Safarpour H, Sadeghi S, Zarbakhsh P, et al. Explainable deep learning framework for brain tumour segmentation using vision transformer and conditional random fields. Multimedia Syst. 2026;32(1):19.
|
| [19] |
Li B, Liu Y. Dual-path brain tumour segmentation based on Mamba spatial attention and channel interaction attention modules. Application Res Comp. 2025:1-8. Online].
|
| [20] |
Prasanna G, Ernest JR, Lalitha G, et al. Squeeze excitation embedded attention U-Net for brain tumour segmentation. In: International conference on emerging electronics and automation. Springer Nature Singapore; 2022:107-117.
|
| [21] |
Ji Q, Wang J, Ding C, et al. DMAGNet: dual-path multi-scale attention guided network for medical image segmentation. IET Image Proc. 2023;17(13):3631-3644.
|
| [22] |
Sinha A, Dolz J. Multi-scale self-guided attention for medical image segmentation. IEEE J Biomed Health Inf. 2020;25(1):121-130.
|
| [23] |
Cheng J, Tian S, Yu L, et al. ResGANet: residual group attention network for medical image classification and segmentation. Med Image Anal. 2022;76:102313.
|
| [24] |
Hatamizadeh A, Nath V, Tang Y, et al. Swin UNETR: Swin transformers for semantic segmentation of brain tumors in MRI images. In: International MICCAI brainlesion workshop. Springer International Publishing; 2021:272-284.
|
| [25] |
Wu J, Wu Y. Brain tumour segmentation based on residual mixed attention and adaptive feature fusion. Application Res Comp. 2025;42(8):2525–2531.
|
| [26] |
Moodi F, Shoushtari FK, Valizadeh G, et al. Attention Xception UNet (AXUNet): a novel combination of CNN and self-attention for brain tumour segmentation. arXiv preprint arXiv:2503.20446; 2025.
|
| [27] |
He W, Gopalakrishnan AK. A Hybrid UNet model incorporating attention mechanism for adaptive brain tumour magnetic resonance segmentation. In: 2024 IEEE 7th information technology, networking, electronic and automation control conference (ITNEC). IEEE. 2024;7:1302-1308.
|
| [28] |
Yang J, Qiu K. An improved segmentation algorithm of CT image based on U-Net network and attention mechanism. Multimedia Tools Applications. 2022;81(25):35983-36006.
|
| [29] |
Wang K, Zhang X, Zhang X, et al. EANet: iterative edge attention network for medical image segmentation. Pattern Recognit. 2022;127:108636.
|
| [30] |
Zhan B, Song E, Liu H, et al. CFNet: a medical image segmentation method using the multi-view attention mechanism and adaptive fusion strategy. Biomed Signal Process Control. 2023;79:104112.
|
| [31] |
Shao H, Zeng Q, Hou Q, et al. Mcanet: medical image segmentation with multi-scale cross-axis attention. Mach Intell Res. 2025;22(3):437-451.
|
| [32] |
Ranjbarzadeh R, Keles A, Crane M, et al. Comparative analysis of real-clinical MRI and BraTS datasets for brain tumour segmentation. In: IET conference proceedings CP887. The Institution of Engineering and Technology. 2024;2024(10):39-46.
|
| [33] |
Azad R, Niggemeier L, Hüttemann M, et al. Beyond self-attention: deformable large kernel attention for medical image segmentation. Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2024:1287-1297.
|
| [34] |
Li Y, Liang M, Wei M, et al. Mechanisms and applications of attention in medical image segmentation: a review. Acad J Sci Technol. 2023;5(3):237-243.
|
| [35] |
Xie Y, Yang B, Guan Q, et al. Attention mechanisms in medical image segmentation: A survey. arXiv preprint arXiv:2305.17937; 2023.
|
| [36] |
Gonçalves T, Rio-Torto I, Teixeira LF, et al. A survey on attention mechanisms for medical applications: are we moving toward better algorithms? IEEE Access. 2022;10:98909-98935.
|
| [37] |
Ren H, Wang X. Overview of attention mechanisms. Comp Applications. 2021;41(S1):1-6.
|
| [38] |
Siddique N, Sidike P, Elkin C, et al. U-Net and its variants for medical image segmentation: theory and applications. arXiv preprint arXiv:2011.01118; 2020.
|
| [39] |
Kamsari M, Sadeghi S, de Oliveira G G, et al. The role of data augmentation and attention mechanisms in UNet and ConvNeXt architectures for optimizing breast tumour segmentation. Sci Rep. 2025;15:45268.
|
| [40] |
Peng J, Luo H, Zhao G, et al. A survey of medical image segmentation algorithms based on deep learning. Comp Eng Applications. 2021;57(3):44-57.
|
| [41] |
Pan P, Chen H, Li Y, et al. Tumour segmentation in automated whole breast ultrasound using bidirectional LSTM neural network and attention mechanism. Ultrasonics. 2021;110:106271.
|
| [42] |
Zhang J, Jiang Z, Dong J, et al. Attention gate resU-Net for automatic MRI brain tumour segmentation. IEEE Access. 2020;8:58533-58545.
|
| [43] |
Ates GC, Mohan P, Celik E. Dual cross-attention for medical image segmentation. Eng Appl Artif Intell. 2023;126:107139.
|
| [44] |
Yang H, Xu Q, Yu L. A Survey of Multi-modal Medical Image Segmentation Based on Deep Learning. Application Res Comp. 2022;39(5):1297-1306.
|
| [45] |
Kaul C, Manandhar S, Pears N, Focusnet: an attention-based fully convolutional network for medical image segmentation. In: 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019). IEEE; 2019:455-458.
|
| [46] |
Rahman MM, Marculescu R. Medical image segmentation via cascaded attention decoding. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision. 2023:6222-6231.
|
| [47] |
Zhang L, Lan C, Fu L, et al. Segmentation of brain tumour MRI image based on improved attention module Unet network. Signal Image Video Process. 2023;17(5):2277-2285.
|
| [48] |
Cui K, Tian Q, Lian L. A survey of medical image segmentation algorithms based on U-Net variants. Comp Eng Applications. 2024;60(11):32-49.
|
| [49] |
Zhao X, Zhang P, Song F, et al. Prior attention network for multi-lesion segmentation in medical images. IEEE Trans Med Imaging. 2022;41(12):3812-3823.
|
| [50] |
Deng H, Zhang Y, Li R, et al. Combining residual attention mechanisms and generative adversarial networks for hippocampus segmentation. Tsinghua Science and Technology. 2021;27(1):68-78.
|
| [51] |
Fan T, Wang G, Li Y, et al. Ma-net: a multi-scale attention network for liver and tumour segmentation. IEEE Access. 2020;8:179656-179665.
|
| [52] |
Du Y, Chen X, Fu Y. Multiscale transformers and multi-attention mechanism networks for pathological nuclei segmentation. Sci Rep. 2025;15(1):12549.
|
| [53] |
Zhang J, Lv X, Zhang H, et al. AResU-Net: attention residual U-Net for brain tumour segmentation. Symmetry. 2020;12(5):721.
|
| [54] |
Cao J, Liu J, Chen J. A brain tumour segmentation method based on attention mechanism. Sci Rep. 2025;15(1):15229.
|
| [55] |
Chen B, Liu Y, Zhang Z, et al. Transattunet: multi-level attention-guided U-Net with transformer for medical image segmentation. IEEE Trans Emerg Topic Comput Intell. 2023;8(1):55-68.
|
| [56] |
Angona TM, Mondal MRH. An attention based residual U-Net with Swin Transformer for brain MRI segmentation. Array. 2025;25:100376.
|
| [57] |
Jia Q, Shu H. BiTr-Unet: a CNN-transformer combined network for MRI brain tumour segmentation. In: International MICCAI brainlesion workshop. Springer International Publishing; 2021:3-14.
|
| [58] |
Magadza T, Viriri S. Efficient nnU-net for brain tumour segmentation. IEEE Access. 2023;11:126386-126397.
|
| [59] |
Jiang Y, Zhang Y, Lin X, et al. SwinBTS: a method for 3D multimodal brain tumour segmentation using swin transformer. Brain Sciences. 2022;12(6):797.
|
| [60] |
Ghazouani F, Vera P, Ruan S. Efficient brain tumour segmentation using Swin transformer and enhanced local self-attention. Int J Comp Assist Radiol Surg. 2024;19(2):273-281.
|
| [61] |
Anari S, Ranjbarzadeh R, Cunneen M, et al. Privacy-preserving federated learning for human intention modeling in pediatric cerebral palsy using extended reality. In: 2025 IEEE 49th annual computers, software, and applications conference (COMPSAC). IEEE; 2025:1-6.
|
| [62] |
Ranjbarzadeh R, Anari S, Cunneen M, et al. Lightweight deep learning with virtual reality visualization for offline tumour segmentation in rural environments. In: 2025 IEEE 49th annual computers, software, and applications conference (COMPSAC). IEEE; 2025:1577-1582.
|
| [63] |
De Bruijne M, Cattin PC, Cotin S, et al., eds. Medical Image Computing and Computer Assisted Intervention–MICCAI 2021. 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part III. Vol. 12903. Springer Nature; 2021.
|
| [64] |
Zhang Y, Han Y, Zhang J. MAU-Net: mixed attention U-Net for MRI brain tumour segmentation. Math Biosci Eng. 2023;20(12):20510-20527.
|
| [65] |
Zhou T, Ruan S, Guo Y, et al. A multi-modality fusion network based on attention mechanism for brain tumour segmentation. In: 2020 IEEE 17th international symposium on biomedical imaging (ISBI). IEEE. 2020:377-380.
|
| [66] |
Hu H, Li Q, Zhao Y, et al. Parallel deep learning algorithms with hybrid attention mechanism for image segmentation of lung tumors. IEEE Trans Ind Inf. 2020;17(4):2880-2889.
|
| [67] |
Shaik NS, Cherukuri TK. Multi-level attention network: application to brain tumour classification. Signal Image Video Process. 2022;16(3):817-824.
|
| [68] |
Li C, Tan Y, Chen W, et al. Attention UNET++: a nested attention-aware U-Net for liver CT image segmentation. In: 2020 IEEE international conference on image processing (ICIP). IEEE; 2020:345-349.
|
| [69] |
Kasgari AB, Sadeghi S, Zarbakhsh P, et al. A Spiking Convolutional Neural Network for glioma brain tumour segmentation using a spike-timing-dependent plasticity method. Neurocomputing. 2025;660:131903.
|
| [70] |
Alwadee EJ, Sun X, Qin Y, et al. LATUP-Net: A lightweight 3D attention U-Net with parallel convolutions for brain tumor segmentation[J]. Comput Biol Med. 2025;184:109353.
|
| [71] |
Yang S, Li X, Mei J, et al. 3d-transunet for brain metastases segmentation in the brats2023 challenge[M]//International Challenge on Cross-Modality Domain Adaptation for Medical Image Segmentation. Springer Nature Switzerland, 2023: 190–199.
|
| [72] |
Js N. Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis[J]. Sci Rep. 2025;15(1):1–20.
|
| [73] |
Soni T, Gupta S, Almogren A, et al. ARCUNet: enhancing skin lesion segmentation with residual convolutions and attention mechanisms for improved accuracy and robustness[J]. Sci Rep. 2025;15(1):9262.
|
| [74] |
Cai L, Hou K, Zhou S. Intelligent skin lesion segmentation using deformable attention Transformer U-Net with bidirectional attention mechanism in skin cancer images[J]. Skin Res Technol. 2024;30(8):e13783.
|
RIGHTS & PERMISSIONS
2026 The Author(s). Clinical and Translational Discovery published by John Wiley & Sons Australia, Ltd on behalf of Shanghai Institute of Clinical Bioinformatics.
PDF
(663KB)
