注意力增强的生成对抗网络在医学图像生成领域的研究与应用

doi:10.3969/j.issn.0258-8021.2025.04.010

摘要
图/表
参考文献
相关文章 (13)

全文: PDF (1410 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要生成对抗网络(GAN)以其卓越的图像生成能力,在医学图像数据增强和质量优化等任务中展现出重要的研究价值与应用潜力。然而,传统GAN模型仍面临鲁棒性不足和泛化能力受限等关键挑战。为解决上述问题,注意力机制凭借其对全局特征关联性建模与关键区域聚焦的优势,为提升GAN的医学图像生成性能提供了有效技术路径。近年来,二者的协同融合已成为去噪、重建和跨模态转换等医学图像处理任务的研究热点。系统综述近5年间(2019~2024年)基于注意力增强的GAN技术在医学图像生成中的研究进展。首先概述经典GAN架构与主流注意力模块的理论基础;继而从任务驱动角度,重点回顾和分析注意力机制对GAN在图像生成质量和病理特征保持等方面性能的增强作用;最后剖析当前面临的技术瓶颈及未来的研究方向。通过多维度的分析与讨论,旨在为医学数据集拓展和图像质量提升等技术优化提供理论支持和实践参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	范姗慧
	梁舒心
	王志文
	魏凯华
	王强
	厉力华

关键词 ：生成对抗网络, 注意力机制, 医学图像生成, 数据增强, 跨模态转换

Abstract：Generative adversarial network (GAN) have been demonstrated great research value and application potential in medical image generation, such as data enhancement and image quality improvement, owing to their excellent generation capabilities. However, traditional GAN models still face core challenges, including insufficient robustness and limited generalization capabilities. To address these issues, attention mechanisms, leveraging their strengths in modeling global feature correlations and focusing on key regions, offer a new technical pathway for enhancing GAN-based medical image generation. Thus, exploring how to efficiently combine attention mechanisms with GAN to boost generation quality has become a research hotspot in areas including denoising, reconstruction, data enhancement, and cross-modal generation. This paper systematically reviewed the advancements in attention-enhanced GAN techniques for medical image generation over the past five years (2019-2024). First, the principles of classical GAN and mainstream attention modules were introduced. Next, from a task-driven perspective, we critically analyzed the improved effects of attention mechanisms on GAN in different tasks. Finally, we delved into the current challenges and proposed potential future research directions. Through multidimensional analysis and discussion, this review hopes to provide valuable insights for advancing technologies in medical dataset expansion and image quality enhancement.

Key words： generative adversarial network attention mechanism medical image generation data augmentation cross-modal generation

收稿日期: 2025-04-01

PACS:

R318

基金资助:国家自然科学基金(62271182);温州市基础性公益科研项目(Y2023139);浙江省科技计划项目(公益技术应用研究)(2017C33143)

通讯作者: ^*E-mail: lilh@hdu.edu.cn

引用本文:

范姗慧, 梁舒心, 王志文, 魏凯华, 王强, 厉力华. 注意力增强的生成对抗网络在医学图像生成领域的研究与应用[J]. 中国生物医学工程学报, 2025, 44(4): 478-493.
Fan Shanhui, Liang Shuxin, Wang Zhiwen, Wei Kaihua, Wang Qiang, Li Lihua. Research and Applications of Attention-Enhanced Generative Adversarial Network in MedicalImage Generation. Chinese Journal of Biomedical Engineering, 2025, 44(4): 478-493.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2025.04.010 或 http://cjbme.csbme.org/CN/Y2025/V44/I4/478

[1] Ahishakiye E, Bastiaan Van Gijzen M, Tumwiine J, et al. A survey on deep learning in medical image reconstruction[J]. Intelligent Medicine, 2021, 1(3): 118-127.
[2] Elasri M, Elharrouss O, Al-Maadeed S, et al. Image generation: a review[J]. Neural Processing Letters, 2022, 54(5): 4609-4646.
[3] Saxena D, Cao J. Generative adversarial networks (GANs) challenges, solutions, and future directions[J]. ACM Computing Surveys (CSUR), 2021, 54(3): 1-42.
[4] Soydaner D. Attention mechanism in neural networks: where it comes and where it goes[J]. Neural Computing and Applications, 2022, 34(16): 13371-13385.
[5] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144.
[6] Isola P, Zhu JY, Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1125-1134.
[7] Zhu JY, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 2223-2232.
[8] Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Honolulu: IEEE, 2017: 4681-4690.
[9] Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of Wasserstein GANs[J]. Advances in Neural Information Processing Systems (NeurIPS), 2017, 30: 5769-5779.
[10] Wang Z, Zheng H, He P, et al. Diffusion-GAN: training GANs with diffusion[C]//International Conference on Learning Representations. Vancouver: ICLR, 2023 : 1-8.
[11] Woo S, Park J, Lee JY, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 3-19.
[12] He K, Gan C, Li Z, et al. Transformers in medical image analysis[J]. Intelligent Medicine, 2023, 3(1): 59-78.
[13] Han C, Rundo L, Murao K, et al. MADGAN: unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction[J]. BMC Bioinformatics, 2021, 22: 1-20.
[14] Jung E, Luna M, Park SH. Conditional GAN with 3D discriminator for MRI generation of Alzheimer’s disease progression[J]. Pattern Recognition, 2023, 133: 109061.
[15] Xu Z, Tang J, Qi C, et al. Cross-domain attention-guided generative data augmentation for medical image analysis with limited data[J]. Computers in Biology and Medicine, 2024, 168: 107744.
[16] Gan HS, Ramlee MH, Al-Rimy BAS, et al. Hierarchical knee image synthesis framework for generative adversarial network: data from the osteoarthritis initiative[J]. IEEE Access, 2022, 10: 55051-55061.
[17] Li Z, Zhang J, Li B, et al. COVID‐19 diagnosis on CT scan images using a generative adversarial network and concatenated feature pyramid network with an attention mechanism[J]. Medical Physics, 2021, 48(8): 4334-4349.
[18] Liu J, Wang Z, Zhang Y, et al. CycleGAN clinical image augmentation based on mask self-attention mechanism[J]. IEEE Access, 2022, 10: 105942-105953.
[19] Zheng Z, Wang M, Fan C, et al. Light&fast generative adversarial network for high-fidelity CT image synthesis of liver tumor[J]. Computer Methods and Programs in Biomedicine, 2024, 254: 108252.
[20] Zhou Y, Wang B, He X, et al. DR-GAN: conditional generative adversarial network for fine-grained lesion synthesis on diabetic retinopathy images[J]. IEEE Journal of Biomedical And Health Informatics, 2020, 26(1): 56-66.
[21] Lei H, Tian Z, Xie H, et al. LAC-GAN: lesion attention conditional GAN for ultra-widefield image synthesis[J]. Neural Networks, 2023, 158: 89-98.
[22] He Z, Zuo W, Kan M, et al. AttGAN: facial attribute editing by only changing what you want[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5464-5478.
[23] Karras T, Aila T, Laine S, et al. Progressive growing of GANs for improved quality, stability, and variation[C]//International Conference on Learning Representations (ICLR). Vancouver:ICLR, 2018: 1-26.
[24] Ngasa EE, Jang MA, Tarimo SA, et al. Diffusion-based Wasserstein generative adversarial network for blood cell image augmentation[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108221.
[25] Abdelhalim ISA, Mohamed MF, Mahdy YB. Data augmentation for skin lesion using self-attention based progressive generative adversarial network[J]. Expert Systems with Applications, 2021, 165: 113922.
[26] Tang J, Zou B, Li C, et al. Plane-wave image reconstruction via generative adversarial network and attention mechanism[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-15.
[27] Zhao B, Cheng T, Zhang X, et al. CT synthesis from MR in the pelvic area using residual transformer conditional GAN[J]. Computerized Medical Imaging and Graphics, 2023, 103: 102150.
[28] Yang H, Sun J, Carass A, et al. Unsupervised MR-to-CT synthesis using structure-constrained CycleGAN [J]. IEEE Transactions on Medical Imaging, 2020, 39(12): 4249-4261.
[29] Wang J, Wu QMJ, Pourpanah F. An attentive-based generative model for medical image synthesis[J]. International Journal of Machine Learning and Cybernetics, 2023, 14(11): 3897-3910.
[30] Li H, Han Y, Guo L, et al. LKDA-GAN: cross-modality image synthesis via generative adversarial network aggregating large kernel decomposable attention bottleneck block[J]. Computer Vision and Image Understanding, 2023, 237: 103856.
[31] Liu X, Pan J, Li X, et al. Attention based cross-domain synthesis and segmentation from unpaired medical images[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023, 8(1): 917-929.
[32] Dong X, Wang T, Lei Y, et al. Synthetic CT generation from non-attenuation corrected PET images for whole-body PET imaging[J]. Physics in Medicine and Biology, 2019, 64(21): 215016.
[33] Gao X, Shi F, Shen D, et al. Task-induced pyramid and attention GAN for multimodal brain image imputation and classification in Alzheimer′s disease[J]. IEEE Journal of Biomedical and Health Informatics, 2021, 26(1): 36-43.
[34] Amirkolaee HA, Bokov DO, Sharma H. Development of a GAN architecture based on integrating global and local information for paired and unpaired medical image translation[J]. Expert Systems with Applications, 2022, 203: 117421.
[35] Liu J, Yang Y, Ai Y, et al. MVI-Wise GAN: synthetic MRI to improve microvascular invasion prediction in hepatocellular carcinoma[C]//2023 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Seattle: IEEE, 2023: 1-4.
[36] Pan M, Zhang H, Tang Z, et al. Attention-based multi-scale generative adversarial network for synthesizing contrast-enhanced MRI[C]//2021 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Guadalajara: IEEE, 2021: 3650-3653.
[37] Gutierrez A, Tuladhar A, Wilms M, et al. Lesion-preserving unpaired image-to-image translation between MRI and CT from ischemic stroke patients[J]. International Journal of Computer Assisted Radiology and Surgery, 2023, 18(5): 827-836.
[38] Yang Y, Li Y, Chen Q, et al. Spatial attention-guided generative adversarial network for synthesizing contrast-enhanced computed tomography images[C]//2023 45th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Seattle: IEEE, 2023: 1-4.
[39] Yang Y, Chen Q, Li Y, et al. Segmentation guided crossing dual decoding generative adversarial network for synthesizing contrast-enhanced computed tomography images[J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28(8): 4737-4750.
[40] Ge R, Fang Z, Wei P, et al. UWAFA-GAN: ultra-wide-angle fluorescein angiography transformation via multi-scale generation and registration enhancement[J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28(8): 4820-4829.
[41] Cai Z, Xin J, Wu J, et al. Triple multi-scale adversarial learning with self-attention and quality loss for unpaired fundus fluorescein angiography synthesis[C]//2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Montreal: IEEE, 2020: 1592-1595.
[42] Wang TC, Liu MY, Zhu JY, et al. High-resolution image synthesis and semantic manipulation with conditional GANs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8798-8807.
[43] Jiang W, Yu C, Chen X, et al. Ultrasound to X-ray synthesis generative attentional network (UXGAN) for adolescent idiopathic scoliosis[J]. Ultrasonics, 2022, 126: 106819.
[44] Wang Y, Sun ZL, Zeng Z, et al. TRCT-GAN: CT reconstruction from biplane X-rays using transformer and generative adversarial networks[J]. Digital Signal Processing, 2023, 140: 104123.
[45] Hamghalam M, Wang T, Lei B. High tissue contrast image synthesis via multistage attention-GAN: application to segmenting brain MR scans[J]. Neural Networks, 2020, 132: 43-52.
[46] Aetesam H, Maji SK. Perceptually motivated generative model for magnetic resonance image denoising[J]. Journal of Digital Imaging, 2023, 36(2): 725-738.
[47] Ran M, Hu J, Chen Y, et al. Denoising of 3D magnetic resonance images using a residual encoder-decoder Wasserstein generative adversarial network[J]. Medical Image Analysis, 2019, 55: 165-180.
[48] Huang J, Ding W, Lv J, et al. Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information[J]. Applied Intelligence, 2022, 52(13): 14693-14710.
[49] Xu J, Bi W, Yan L, et al. An efficient lightweight generative adversarial network for compressed sensing magnetic resonance imaging reconstruction[J]. IEEE Access, 2023, 11: 24604-24614.
[50] Zhao X, Yang T, Li B, et al. SwinGAN: a dual-domain Swin Transformer-based generative adversarial network for MRI reconstruction[J]. Computers in Biology and Medicine, 2023, 153: 106513.
[51] Huang Z, Chen Z, Zhang Q, et al. CaGAN: a cycle-consistent generative adversarial network with attention for low-dose CT imaging[J]. IEEE Transactions on Computational Imaging, 2020, 6: 1203-1218.
[52] Bera S, Biswas PK. Noise conscious training of non local neural network powered by self attentive spectral normalized Markovian patch GAN for low dose CT denoising[J]. IEEE Transactions on Medical Imaging, 2021, 40(12): 3663-3673.
[53] Han Z, Shangguan H, Zhang X, et al. A dual-encoder-single-decoder based low-dose CT denoising network[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(7): 3251-3260.
[54] Du W, Chen H, Liao P, et al. Visual attention network for low-dose CT[J]. IEEE Signal Processing Letters, 2019, 26(8): 1152-1156.
[55] Liu Y, Lei Y, Wang T, et al. CBCT‐based synthetic CT generation using deep‐attention CycleGAN for pancreatic adaptive radiotherapy[J]. Medical Physics, 2020, 47(6): 2472-2483.
[56] Liu Y, Chen A, Li Y, et al. CT synthesis from CBCT using a sequence-aware contrastive generative network[J]. Computerized Medical Imaging and Graphics, 2023, 109: 102300.
[57] Sun H, Yang Z, Zhu J, et al. Pseudo-medical image-guided technology based on 'CBCT-only' mode in esophageal cancer radiotherapy[J]. Computer Methods and Programs in Biomedicine, 2024, 245: 108007.
[58] Shang C, Zhao G, Li Y, et al. Short‐axis PET image quality improvement by attention CycleGAN using total-body PET[J]. Journal of Healthcare Engineering, 2022, 2022(1): 4247023.
[59] Chen S, Tian X, Wang Y, et al. DAEGAN: generative adversarial network based on dual-domain attention-enhanced encoder-decoder for low-dose PET imaging[J]. Biomedical Signal Processing and Control, 2023, 86: 105197.
[60] You Q, Wan C, Sun J, et al. Fundus image enhancement method based on CycleGAN[C]//2019 41st Annual International Conference of the IEEE Engineering In Medicine and Biology Society (EMBC). Berlin: IEEE, 2019: 4500-4503.
[61] Zhong G, Ding W, Chen L, et al. Multi-scale attention generative adversarial network for medical image enhancement[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023, 7(4): 1113-1125.
[62] Li S, Wang Y, Higashita R, et al. A contrast-aware edge enhancement GAN for unpaired anterior segment OCT image denoising[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(2): 1673-1685.
[63] Khor HG, Ning G, Zhang X, et al. Ultrasound speckle reduction using wavelet-based generative adversarial network[J]. IEEE Journal of Biomedical and Health Informatics, 2022, 26(7): 3080-3091.
[64] Liang M, Zhang Q, Wang G, et al. Multi-scale self-attention generative adversarial network for pathology image restoration[J]. The Visual Computer, 2023, 39(9): 4305-4321.
[65] Yue G, Gao J, Duan L, et al. Colorectal endoscopic image enhancement via unsupervised deep learning[J]. Multimedia Tools and Applications, 2023, 82(10): 15761-15783.
[66] Gu Y, Zeng Z, Chen H, et al. MedSRGAN: medical images super-resolution using generative adversarial networks[J]. Multimedia Tools and Applications, 2020, 79: 21815-21840.
[67] Ledig C, Theis L, Huszár F, et al. Photo-realistic single image super-resolution using a generative adversarial network [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 4681-4690.
[68] Song Z, Qiu D, Zhao X, et al. Channel attention generative adversarial network for super-resolution of glioma magnetic resonance image[J]. Computer Methods and Programs in Biomedicine, 2023, 229: 107255.
[69] Zhou S, Yu L, Jin M. Texture transformer super-resolution for low-dose computed tomography[J]. Biomedical Physics and Engineering Express, 2022, 8(6): 065024.
[70] Liu X, Su S, Gu W, et al. Super-resolution reconstruction of CT images based on multi-scale information fused generative adversarial networks[J]. Annals of Biomedical Engineering, 2024, 52(1): 57-70.
[71] Wang X, Xie L, Dong C, et al. Real-ESRGAN: training real-world blind super-resolution with pure synthetic data[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 1905-1914.
[72] Li P, He Y, Wang P, et al. Synthesizing multi-frame high-resolution fluorescein angiography images from retinal fundus images using generative adversarial networks[J]. BioMedical Engineering OnLine, 2023, 22(1): 16.
[73] Dharejo FA, Zawish M, Deeba F, et al. Multimodal-boost: multimodal medical image super-resolution using multi-attention network with wavelet transform[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, 20(4): 2420-2433.
[74] Kim S, Jun D, Kim BG, et al. Single image super-resolution method using CNN-based lightweight neural networks[J]. Applied Sciences, 2021, 11(3): 1092.
[75] Li P, Li Z, Pang X, et al. Multi-scale residual denoising GAN model for producing super-resolution CTA images[J]. Journal of Ambient Intelligence and Humanized Computing, 2022, 13(10): 4877-4886.
[76] Lyu Y, Jiang X, Xu Y, et al. ARU-GAN: U-shaped GAN based on attention and residual connection for super-resolution reconstruction[J]. Computers in Biology and Medicine, 2023, 164: 107316.