Adversarial sample embedded attention U-Net for 3D medical image segmentation

doi:10.11772/j.issn.1001-9081.2024081134

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (9): 3011-3016.DOI: 10.11772/j.issn.1001-9081.2024081134

• Multimedia computing and computer simulation • Previous Articles

Adversarial sample embedded attention U-Net for 3D medical image segmentation

Zhixiong XU¹, Bo LI¹^,²^,³(), Xiaoyong BIAN¹^,²^,³, Qiren HU¹

^1.School of Computer Science and Technology，Wuhan University of Science and Technology，Wuhan Hubei 430065，China
^2.Institute of Big Data Science and Engineering，Wuhan University of Science and Technology，Wuhan Hubei 430072，China
^3.Key Laboratory of Hubei Province for Intelligent Information Processing and Real-time Industrial System （Wuhan University of Science and Technology），Wuhan Hubei 430081，China

Received:2024-08-11 Revised:2024-09-25 Accepted:2024-09-27 Online:2024-11-07 Published:2025-09-10
Contact: Bo LI
About author:XU Zhixiong， born in 2000， M. S. candidate. His research interests include deep learning， medical image segmentation.
BIAN Xiaoyong， born in 1976， Ph. D.， associate professor. His research interests include machine learning， object detection.
HU Qiren， born in 1999， M. S. candidate. His research interests include deep learning， object detection.
Supported by:
National Natural Science Foundation of China(61972299)

对抗样本嵌入注意力U型网络的3D医学图像分割

许志雄¹, 李波¹^,²^,³(), 边小勇¹^,²^,³, 胡其仁¹

^1.武汉科技大学计算机科学与技术学院，武汉 430065
^2.武汉科技大学大数据科学与工程研究院，武汉 430072
^3.智能信息处理与实时工业系统湖北省重点实验室（武汉科技大学），武汉 430081

通讯作者: 李波
作者简介:许志雄（2000—），男，湖北荆州人，硕士研究生，主要研究方向：深度学习、医学图像分割
边小勇（1976—），男，江西吉安人，副教授，博士，主要研究方向：机器学习、目标检测
胡其仁（1999—），男，湖北仙桃人，硕士研究生，主要研究方向：深度学习、目标检测。
基金资助:
国家自然科学基金资助项目(61972299)

Abstract

Abstract:

Computed Tomography （CT） and Magnetic Resonance Imaging （MRI） images are widely used in medical image depth segmentation. However， the traditional segmentation methods are affected by tumor boundary blurring and structural complexity， and ignore adversarial samples’ differentiation ability to the segmentation model， leading to challenges in achieving optimal segmentation results. To address these issues， a 3D medical image segmentation model with adversarial sample-embedded attention U-Net learning was proposed. In the model， by using the adversarial sample-embedded attention U-Net， adversarial samples were constructed through sample transformation， and tumor feature information was extracted from medical images； low-dimensional feature screening and high-dimensional feature fusion modules were introduced to purify the tumor distinguishable feature； the entire network was trained using a combined loss function based on cross-entropy， Dice loss， and contrastive loss to obtain a segmentation model rich in discriminative features. Experimental results show that on Nerve Sheath Tumor （NST） and Automated Cardiac Diagnosis Challenge （ACDC） datasets， the Dice Similarity Coefficients （DSCs） of the proposed method reach 88.14% and 91.75%， respectively， which are improved by 1.26 and 2.48 percentage points compared to those of not new U-Net （nnU-Net） method. It can be seen that the proposed method improves performance of 3D medical image segmentation with blurred tumor boundary effectively.

Key words: medical image segmentation, deep learning, attention U-Net, contrastive learning, feature fusion

摘要：

计算机断层扫描（CT）和核磁共振成像（MRI）图像广泛应用于医学图像深度分割。然而，传统的分割方法受到肿瘤边界模糊及其结构复杂的影响，未能利用对抗样本提升分割模型的区分能力，使获得最好的分割效果面临挑战。针对以上问题，提出一种对抗样本嵌入注意力U型网络学习的3D医学图像分割模型。该模型使用对抗样本嵌入的注意力U型网络以通过样本变换构建对抗样本，并提取医学图像的肿瘤特征信息；引入低维度特征筛选和高维度特征融合模块，以提纯肿瘤可区分特征；使用基于交叉熵、Dice损失和对比损失的组合损失函数训练整个网络，从而得到富于判别性的分割模型。实验结果表明，所提方法在神经鞘膜瘤（NST）和自动心脏诊断挑战（ACDC）数据集上的Dice相似性系数（DSC）分别达到88.14%和91.75%，与非新的U-Net（nnU-Net）方法相比，分别提高了1.26和2.48个百分点。可见，所提方法有效提高了在肿瘤边界模糊时的3D医学图像分割性能。

关键词: 医学图像分割, 深度学习, 注意力U型网络, 对比学习, 特征融合

CLC Number:

TP391.4

Zhixiong XU, Bo LI, Xiaoyong BIAN, Qiren HU. Adversarial sample embedded attention U-Net for 3D medical image segmentation[J]. Journal of Computer Applications, 2025, 45(9): 3011-3016.

许志雄, 李波, 边小勇, 胡其仁. 对抗样本嵌入注意力U型网络的3D医学图像分割[J]. 《计算机应用》唯一官方网站, 2025, 45(9): 3011-3016.

Figures/Tables 7

References 25

[1]	杨健，王媛媛，艾丹妮，等. 多模态图像引导手术导航进展［J］. 光学学报， 2023， 43（15）： No.1500002.
	YANG J， WANG Y Y， AI D N， et al. Developments of multimodal image-guided surgical navigation［J］. Acta Optica Sinica， 2023， 43（15）： No.1500002.
[2]	徐少康，张战成，姚浩男，等. 基于姿态编码器的2D/3D脊椎医学图像实时配准方法［J］. 计算机应用， 2023， 43（2）： 589-594.
	XU S K， ZHANG Z C， YAO H N， et al. 2D/3D spinal medical image real-time registration method for based on pose encoder ［J］. Journal of Computer Applications， 2023， 43（2）： 589-594.
[3]	PHAM D L， XU C， PRINCE J L. Current methods in medical image segmentation ［J］. Annual Review of Biomedical Engineering， 2000， 2： 315-337.
[4]	RONNEBERGER O， FISCHER P， BROX T. U-Net： convolutional networks for biomedical image segmentation ［C］// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 9351. Cham： Springer， 2015： 234-241.
[5]	ÇIÇEK Ö， ABDULKADIR A， LIENKAMP S S， et al. 3D U-Net： learning dense volumetric segmentation from sparse annotation ［C］// Proceedings of the 2016 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 9901. Cham： Springer， 2016： 424-432.
[6]	MILLETARI F， NAVAB N， AHMADI S A. V-Net： fully convolutional neural networks for volumetric medical image segmentation ［C］// Proceedings of the 4th International Conference on 3D Vision. Piscataway： IEEE， 2016： 565-571.
[7]	ZHANG Z， LIU Q， WANG Y. Road extraction by deep residual U-Net ［J］. IEEE Geoscience and Remote Sensing Letters， 2018， 15（5）： 749-753.
[8]	ISENSEE F， JAEGER P F， KOHL S A A， et al. nnU-Net： a self-configuring method for deep learning-based biomedical image segmentation ［J］. Nature Methods， 2021， 18（2）： 203-211.
[9]	SIMPSON A L， ANTONELLI M， BAKAS S， et al. A large annotated medical image dataset for the development and evaluation of segmentation algorithms ［EB/OL］. ［2024-07-10］..
[10]	HUANG H， LIN L， TONG R， et al. UNet 3+： a full-scale connected UNet for medical image segmentation ［C］// Proceedings of the 2020 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2020： 1055-1059.
[11]	LIU X， ONO K， BISE R. A data augmentation approach that ensures the reliability of foregrounds in medical image segmentation［J］. Image and Vision Computing， 2024， 147： No.105056.
[12]	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
[13]	DOSOVITSKIY A， BEYER L， KOLESNIKOV A， et al. An image is worth 16x16 words： Transformers for image recognition at scale［EB/OL］. ［2024-07-13］..
[14]	周腊珍，陈红池，李秋霞，等. 基于Transformer深度学习模型在医学图像分割中的研究进展［J］. 中国生物医学工程学报， 2024， 43（4）：467-476.
	ZHOU L Z， CHEN H C， LI Q X， et al. Research progress on Transformer-based deep learning models for medical image segmentation ［J］. Chinese Journal of Biomedical Engineering， 2024， 43（4）： 467-476.
[15]	OKTAY O， SCHLEMPER J， LE FOLGOC L， et al. Attention U-Net： learning where to look for the pancreas ［EB/OL］. ［2024-08-10］..
[16]	CHEN J， LU Y， YU Q， et al. TransUNet： Transformers make strong encoders for medical image segmentation ［EB/OL］. ［2024-08-13］. .
[17]	CAO H， WANG Y， CHEN J， et al. Swin-Unet： Unet-like pure Transformer for medical image segmentation ［C］// Proceedings of the 2022 European Conference on Computer Vision Workshops， LNCS 13803. Cham： Springer， 2023： 205-218.
[18]	BERNARD O， LALANDE A， ZOTTI C， et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis： is the problem solved？［J］. IEEE Transactions on Medical Imaging， 2018， 37（11）： 2514-2525.
[19]	XIE E， WANG W， YU Z， et al. SegFormer： simple and efficient design for semantic segmentation with Transformers ［C］// Proceedings of the 35th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2021： 12077-12090.
[20]	SHEN Y， LI J， ZHU W， et al. Graph attention U-Net for retinal layer surface detection and choroid neovascularization segmentation in OCT images ［J］. IEEE Transactions on Medical Imaging， 2023， 42（11）： 3140-3154.
[21]	WANG Z， WANG W， LI N， et al. Multimodal parallel attention network for medical image segmentation ［J］. Image and Vision Computing， 2024， 147： No.105069.
[22]	LI Y， YAO T， PAN Y， et al. Contextual Transformer networks for visual recognition ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（2）： 1489-1500.
[23]	CHEN Y， BRUZZONE L， JIANG L， et al. ARU-Net： reduction of atmospheric phase screen in SAR interferometry using attention-based deep residual U-Net ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2021， 59（7）： 5780-5793.
[24]	VALANARASU J M J， SINDAGI V A， HACIHALILOGLU I， et al. KiU-Net： overcomplete convolutional architectures for biomedical image and volumetric segmentation ［J］. IEEE Transactions on Medical Imaging， 2022， 41（4）： 965-976.
[25]	BADRINARAYANAN V， KENDALL A， CIPOLLA R. SegNet： a deep convolutional encoder-decoder architecture for image segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（12）： 2481-2495.

方法	DSC	IoU
3D U-Net^［5］	82.38	72.42
3D ResU-Net^［7］	84.09	75.32
nnU-Net^［8］	86.88	77.78
Att-UNet^［15］	72.10	61.31
TransUNet^［16］	76.60	66.48
Swin-Unet^［17］	80.68	71.16
ARU-Net^［23］	70.72	57.06
KiU-Net^［24］	70.72	58.94
SegNet^［25］	69.67	58.31
本文方法	88.14	79.84

方法	DSC	IoU
3D U-Net^［5］	82.38	72.42
3D ResU-Net^［7］	84.09	75.32
nnU-Net^［8］	86.88	77.78
Att-UNet^［15］	72.10	61.31
TransUNet^［16］	76.60	66.48
Swin-Unet^［17］	80.68	71.16
ARU-Net^［23］	70.72	57.06
KiU-Net^［24］	70.72	58.94
SegNet^［25］	69.67	58.31
本文方法	88.14	79.84

方法	平均DSC	不同部位DSC
方法	平均DSC	RV	Myo	LV
3D U-Net^［5］	87.42	85.78	86.01	90.47
3D ResU-Net^［7］	87.55	87.10	80.63	94.92
nnU-Net^［8］	89.27	88.95	87.16	91.70
Att-UNet^［15］	86.75	87.58	79.20	93.47
TransUNet^［16］	89.71	88.86	84.53	95.73
Swin-Unet^［17］	90.00	88.55	85.62	95.83
ARU-Net^［23］	88.82	87.99	85.25	93.22
KiU-Net^［24］	86.21	85.33	83.41	89.87
SegNet^［25］	86.79	85.05	84.94	90.38
本文方法	91.75	89.50	90.35	95.41

方法	平均DSC	不同部位DSC
方法	平均DSC	RV	Myo	LV
3D U-Net^［5］	87.42	85.78	86.01	90.47
3D ResU-Net^［7］	87.55	87.10	80.63	94.92
nnU-Net^［8］	89.27	88.95	87.16	91.70
Att-UNet^［15］	86.75	87.58	79.20	93.47
TransUNet^［16］	89.71	88.86	84.53	95.73
Swin-Unet^［17］	90.00	88.55	85.62	95.83
ARU-Net^［23］	88.82	87.99	85.25	93.22
KiU-Net^［24］	86.21	85.33	83.41	89.87
SegNet^［25］	86.79	85.05	84.94	90.38
本文方法	91.75	89.50	90.35	95.41

方法	DSC	IoU
本文方法	88.14	79.84
w/o adversarial sample	86.71	78.19
w/o token selection	87.39	78.75
w/o feature fusion	87.30	78.94

Adversarial sample embedded attention U-Net for 3D medical image segmentation

对抗样本嵌入注意力U型网络的3D医学图像分割

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 25

Related Articles 15

Recommended Articles

Metrics

[1]	Weigang LI, Jiale SHAO, Zhiqiang TIAN. Point cloud classification and segmentation network based on dual attention mechanism and multi-scale fusion [J]. Journal of Computer Applications, 2025, 45(9): 3003-3010.
[2]	Panfeng JING, Yudong LIANG, Chaowei LI, Junru GUO, Jinyu GUO. Semi-supervised image dehazing algorithm based on teacher-student learning [J]. Journal of Computer Applications, 2025, 45(9): 2975-2983.
[3]	Yiming LIANG, Jing FAN, Wenze CHAI. Multi-scale feature fusion sentiment classification based on bidirectional cross attention [J]. Journal of Computer Applications, 2025, 45(9): 2773-2782.
[4]	Hongjun ZHANG, Gaojun PAN, Hao YE, Yubin LU, Yiheng MIAO. Multi-source heterogeneous data analysis method combining deep learning and tensor decomposition [J]. Journal of Computer Applications, 2025, 45(9): 2838-2847.
[5]	Jin LI, Liqun LIU. SAR and visible image fusion based on residual Swin Transformer [J]. Journal of Computer Applications, 2025, 45(9): 2949-2956.
[6]	Bing YIN, Zhenhua LING, Yin LIN, Changfeng XI, Ying LIU. Emotion recognition method compatible with missing modal reasoning [J]. Journal of Computer Applications, 2025, 45(9): 2764-2772.
[7]	Chao LIU, Yanhua YU. Knowledge-aware recommendation model combining denoising strategy and multi-view contrastive learning [J]. Journal of Computer Applications, 2025, 45(9): 2827-2837.
[8]	Zhiyuan WANG, Tao PENG, Jie YANG. Integrating internal and external data for out-of-distribution detection training and testing [J]. Journal of Computer Applications, 2025, 45(8): 2497-2506.
[9]	Chengzhi YAN, Ying CHEN, Kai ZHONG, Han GAO. 3D object detection algorithm based on multi-scale network and axial attention [J]. Journal of Computer Applications, 2025, 45(8): 2537-2545.
[10]	Yanhua LIAO, Yuanxia YAN, Wenlin PAN. Multi-target detection algorithm for traffic intersection images based on YOLOv9 [J]. Journal of Computer Applications, 2025, 45(8): 2555-2565.
[11]	Lina GE, Mingyu WANG, Lei TIAN. Review of research on efficiency of federated learning [J]. Journal of Computer Applications, 2025, 45(8): 2387-2398.
[12]	Yimeng XI, Zhen DENG, Qian LIU, Libo LIU. Cross-modal information fusion for video-text retrieval [J]. Journal of Computer Applications, 2025, 45(8): 2448-2456.
[13]	Peng PENG, Ziting CAI, Wenling LIU, Caihua CHEN, Wei ZENG, Baolai HUANG. Speech emotion recognition method based on hybrid Siamese network with CNN and bidirectional GRU [J]. Journal of Computer Applications, 2025, 45(8): 2515-2521.
[14]	Shuo ZHANG, Guokai SUN, Yuan ZHUANG, Xiaoyu FENG, Jingzhi WANG. Dynamic detection method of eclipse attacks for blockchain node analysis [J]. Journal of Computer Applications, 2025, 45(8): 2428-2436.
[15]	Jinhao LIN, Chuan LUO, Tianrui LI, Hongmei CHEN. Thoracic disease classification method based on cross-scale attention network [J]. Journal of Computer Applications, 2025, 45(8): 2712-2719.