[1]周琳琳,丁卫平,张炜,等.面向医学图像检索的模糊注意力协同哈希网络[J].智能系统学报,2026,21(4):932-942.[doi:10.11992/tis.202508013]
ZHOU Linlin,DING Weiping,ZHANG Wei,et al.Fuzzy attentional collaborative hashing network for medical image retrieval[J].CAAI Transactions on Intelligent Systems,2026,21(4):932-942.[doi:10.11992/tis.202508013]
点击复制
ZHOU Linlin,DING Weiping,ZHANG Wei,et al.Fuzzy attentional collaborative hashing network for medical image retrieval[J].CAAI Transactions on Intelligent Systems,2026,21(4):932-942.[doi:10.11992/tis.202508013]
面向医学图像检索的模糊注意力协同哈希网络
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第4期
页码:
932-942
栏目:
学术论文—机器感知与模式识别
出版日期:
2026-07-05
- Title:
- Fuzzy attentional collaborative hashing network for medical image retrieval
- Keywords:
- medical image; image retrieval; fuzzy systems; attention mechanisms; deep learning; feature extraction; deep hashing; data processing
- 分类号:
- TP391
- 摘要:
- 近年来，医学影像技术的革新推动图像数据激增，高效检索成为提升诊断效率的关键。深度哈希算法以其高效编码广泛应用于图像检索，但在处理不确定的医学图像及不平衡数据时存在局限。为此，本文提出一种基于模糊系统的模糊注意力协同哈希网络，用于高效的医学图像检索。设计一个注意力增强的模糊特征协同器，通过计算模糊特征的注意力权重，提高类间差异性；基于Transformer的后件协同编码器利用多头自注意力机制增强图像语义建模，处理医学图像的非线性关系；最后，综合成对损失、平衡损失、量化损失与分类损失对模型进行优化，生成紧凑哈希码。在两个医学图像数据集上的大量实验证明了该算法的有效性。
- Abstract:
- In recent years, innovations in medical imaging technology have driven a surge in image data, with efficient retrieval becoming a critical factor in enhancing diagnostic efficiency. Deep hashing algorithms are widely used in image retrieval due to their efficient encoding. However, these algorithms have limitations when applied to uncertain medical images and imbalanced datasets. To address these challenges, this paper proposes a fuzzy attention collaborative hashing network (FACH) for efficient medical image retrieval. First, fuzzy feature coordinator enhanced by attention is introduced, which improves inter-class discrimination by calculating attention weights for fuzzy features. Then, Transformer-based posterior collaborative encoder employs the multi-head self-attention mechanism to enhance image semantic modeling and capture the nonlinear relationships in medical images. Finally, the model is optimized by integrating pairwise loss, balance loss, quantization loss, and classification loss to generate compact and discriminative hash codes. Extensive experiments conducted on two medical image datasets validate the effectiveness of the proposed algorithm.
- 参考文献/References:
-
[1] YE Jin, CHENG Junlong, CHEN Jianpin, et al. SA-Med2D-20M dataset: segment anything in 2D medical imaging with 20 million masks[EB/OL]. (2023-11-20)[2025-08-10]. https://arxiv.org/abs/2311.11969.
[2] JUSH F K, TRUONG T, VOGLER S, et al. Medical image retrieval using pretrained embeddings[C]//2024 IEEE International Symposium on Biomedical Imaging. Athens: IEEE, 2024: 1-5.
[3] KARA K, ALONSO G. Fast and robust hashing for database operators[C]//2016 26th International Conference on Field Programmable Logic and Applications. Lausanne: IEEE, 2016: 1-4.
[4] DEVINE R. Design and implementation of DDH: a distributed dynamic hashing algorithm[C]//Foundations of Data Organization and Algorithms. Berlin: Springer, 1993: 101-114.
[5] LENSING P, MEISTER D, BRINKMANN A. HashFS: applying hashing to optimize file systems for small file reads[C]//2010 International Workshop on Storage Network Architecture and Parallel I/Os. Incline Village: IEEE, 2010: 33-42.
[6] 李来, 刘光灿, 孙玉宝, 等. 各向同性的迭代量化哈希算法[J]. 电子学报, 2017, 45(7): 1707-1714 LI Lai, LIU Guangcan, SUN Yubao, et al. Isotropic iterative quantization hashing[J]. Acta electronica sinica, 2017, 45(7): 1707-1714
[7] LIONG V E, LU Jiwen, WANG Gang, et al. Deep hashing for compact binary codes learning[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 2475-2483.
[8] DING Weiping, LIU Chuansheng, HUANG Jiashuang, et al. ViTH-RFG: vision transformer hashing with residual fuzzy generation for targeted attack in medical image retrieval[J]. IEEE transactions on fuzzy systems, 2024, 32(10): 5571-5584
[9] KOU Xuan, XU Chenghao, YANG Xu, et al. Attention-guided contrastive hashing for long-tailed image retrieval[C]//Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. Vienna: International Joint Conferences on Artificial Intelligence Organization, 2022: 1017-1023.
[10] HE Chao, WEI Hongxi. HybridHash: hybrid convolutional and self-attention deep hashing for image retrieval[C]//Proceedings of the 2024 International Conference on Multimedia Retrieval. Phuket: ACM, 2024: 824-832.
[11] SHEN Yang, SUN Xuhao, WEI Xiushen, et al. SEMICON: a learning-to-hash solution forLarge-scale fine-grained image retrieval[C]//Computer Vision–ECCV 2022. Cham: Springer, 2022: 531-548.
[12] 周天奕, 丁卫平, 黄嘉爽, 等. 模糊逻辑引导的多粒度深度神经网络[J]. 模式识别与人工智能, 2023, 36(9): 778-792 ZHOU Tianyi, DING Weiping, HUANG Jiashuang, et al. Fuzzy logic guided deep neural network with multi-granularity[J]. Pattern recognition and artificial intelligence, 2023, 36(9): 778-792
[13] ZHANG Yuanpeng, YANG Dongrong, LAM S, et al. Radiomics-based detection of COVID-19 from chest X-ray using interpretable soft label-driven TSK fuzzy classifier[J]. Diagnostics, 2022, 12(11): 2613
[14] SONG Guanghao, ZHAI Jia, ZHOU Ta. Classification of acute radiation dermatitis by active-guided-based T-S fuzzy classifier[C]//2023 2nd International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics. Tianjin: IEEE, 2024: 154-160.
[15] TA Zhou, WEI Xue, NAN Chuxi, et al. A screening mechanism fast-aggregation-based Takagi-Sugeno-Kang fuzzy classification for epileptic electroencephalograms signal[J]. Journal of medical imaging and health informatics, 2019, 9(7): 1458-1463
[16] LI Andong, DENG Zhaohong, ZHANG Wei, et al. Multiview transfer representation learning with TSK fuzzy system for EEG epilepsy detection[J]. IEEE transactions on fuzzy systems, 2024, 32(1): 38-52
[17] ONTIVEROS E, MELIN P, CASTILLO O. Comparative study of interval Type-2 and general Type-2 fuzzy systems in medical diagnosis[J]. Information sciences, 2020, 525: 37-53
[18] 王海鹏, 高自强, 董佳俊, 等. 基于粗糙注意力融合机制与Group Transformer的视网膜血管分割网络[J]. 南通大学学报(自然科学版), 2024, 23(1): 28-37,48 WANG Haipeng, GAO Ziqiang, DONG Jiajun, et al. Retinal vessel segmentation network based on rough attention fusion mechanism and Group Transformer[J]. Journal of Nantong University (natural science edition), 2024, 23(1): 28-37,48
[19] JUANG C F. A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithms[J]. IEEE transactions on fuzzy systems, 2002, 10(2): 155-170
[20] DENG Zhaohong, XU Peng, XIE Lixiao, et al. Transductive joint-knowledge-transfer TSK FS for recognition of epileptic EEG signals[J]. IEEE transactions on neural systems and rehabilitation engineering, 2018, 26(8): 1481-1494
[21] 蒋亦樟, 邓赵红, 王士同. 0阶L2型TSK迁移学习模糊系统[J]. 电子学报, 2013, 41(5): 897-904 JIANG Yizhang, DENG Zhaohong, WANG Shitong. 0-order-L2-norm-Takagi-Sugeno-Kang type transfer learning fuzzy system[J]. Acta electronica sinica, 2013, 41(5): 897-904
[22] HERRERA L J, P?REZ M M, SANTANA J, et al. A data mining approach based on a local-global fuzzy modelling for prediction of color change after tooth bleaching using vita classical shades[C]//2009 Ninth International Conference on Intelligent Systems Design and Applications. Pisa: IEEE, 2009: 1268-1273.
[23] HASHEMI S E, GHOLIAN-JOUYBARI F, HAJIAGHAEI-KESHTELI M. A fuzzy C-means algorithm for optimizing data clustering[J]. Expert systems with applications, 2023, 227: 120377
[24] 陈昌红, 彭腾飞, 干宗良. 基于深度哈希算法的极光图像分类与检索方法[J]. 电子与信息学报, 2020, 42(12): 3029-3036 CHEN Changhong, PENG Tengfei, GAN Zongliang. Aurora image classification and retrieval method based on deep hashing algorithm[J]. Journal of electronics & information technology, 2020, 42(12): 3029-3036
[25] LUO Xiao, WANG Haixin, WU Daqing, et al. A survey on deep hashing methods[J]. ACM transactions on knowledge discovery from data, 2023, 17(1): 1-50
[26] SHEN Fumin, XU Yan, LIU Li, et al. Unsupervised deep hashing with similarity-adaptive and discrete optimization[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 40(12): 3034-3044
[27] VENKATESWARA H, EUSEBIO J, CHAKRABORTY S, et al. Deep hashing network for unsupervised domain adaptation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 5385-5394.
[28] ZHANG Jian, PENG Yuxin. SSDH: semi-supervised deep hashing for large scale image retrieval[J]. IEEE transactions on circuits and systems for video technology, 2019, 29(1): 212-225
[29] WANG Guan’an, HU Qinghao, YANG Yang, et al. Adversarial binary mutual learning for semi-supervised deep hashing[J]. IEEE transactions on neural networks and learning systems, 2022, 33(8): 4110-4124
[30] LI Wujun, WANG Sheng, KANG Wangcheng. Feature learning based deep supervised hashing with pairwise labels[EB/OL]. (2015-11-12)[2025-08-10]. https://arxiv.org/abs/1511.03855.
[31] LIU Haomiao, WANG Ruiping, SHAN Shiguang, et al. Deep supervised hashing for fast image retrieval[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 2064-2072.
[32] JIANG Qingyuan, LI Wujun. Asymmetric deep supervised hashing[C]//Proceedings of the AAAI conference on artificial intelligence, New Orleans: AAAI Press, 2018.
[33] DUBEY S R, SINGH S K, CHU Weita. Vision transformer hashing for image retrieval[C]//2022 IEEE International Conference on Multimedia and Expo. Taipei: IEEE, 2022: 1-6.
[34] CHEN Yongbiao, ZHANG Sheng, LIU Fangxin, et al. TransHash: transformer-based hamming hashing for efficient image retrieval[C]//Proceedings of the 2022 International Conference on Multimedia Retrieval. Newark: ACM, 2022: 127-136.
[35] 刘传升, 丁卫平, 程纯, 等. ViTH: 面向医学图像检索的视觉Transformer哈希改进算法[J]. 西南大学学报(自然科学版), 2024, 46(5): 11-26 LIU Chuansheng, DING Weiping, CHENG Chun, et al. ViTH: improved vision transformer hashing algorithm for medical image retrieval[J]. Journal of Southwest University (natural science edition), 2024, 46(5): 11-26
[36] HU Fuping, DENG Zhaohong, WANG Guanjin, et al. Graph fuzzy system for the whole graph prediction: concepts, models, and algorithms[J]. IEEE transactions on fuzzy systems, 2024, 32(3): 1383-1398
[37] HAN Dezhi, SHI Jingya, ZHAO Jiahao, et al. LRCN: layer-residual co-attention networks for visual question answering[J]. Expert systems with applications, 2025, 263: 125658
[38] LU Huimin, ZHANG Ming, XU Xing, et al. Deep fuzzy hashing network for efficient image retrieval[J]. IEEE transactions on fuzzy systems, 2021, 29(1): 166-176
[39] ZHANG Zheng, ZOU Qin, LIN Yuewei, et al. Improved deep hashing with soft pairwise similarity for multi-label image retrieval[J]. IEEE transactions on multimedia, 2020, 22(2): 540-553
[40] YU Zhengyang, WU Song, DOU Zhihao, et al. Deep hashing with self-supervised asymmetric semantic excavation and margin-scalable constraint[J]. Neurocomputing, 2022, 483: 87-104
[41] FAN Lixin, NG K W, JU Ce, et al. Deep polarized network for supervised learning of accurate binary hashing codes[C]//Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence Main Track. Yokohama: IJCAI, 2021: 825-831.
[42] SU Hai, FANG Jianwei, LIU Weixing, et al. A deep hashing method of likelihood function adaptive mapping[J]. Neural computing and applications, 2023, 35(8): 5903-5921
- 相似文献/References:
-
[1]辛雨璇,闫子飞.基于手绘草图的图像检索技术研究进展[J].智能系统学报,2015,10(2):167.[doi:10.3969/j.issn.1673-4785.201401045]
XIN Yuxuan,YAN Zifei.Research progress of image retrieval based on hand-drawn sketches[J].CAAI Transactions on Intelligent Systems,2015,10():167.[doi:10.3969/j.issn.1673-4785.201401045]
[2]陈阳,董肖莉,李卫军,等.基于仿生形象思维方法的图像检索算法的改进[J].智能系统学报,2015,10(2):209.[doi:10.3969/j.issn.1673-4785.201411022]
CHEN Yang,DONG Xiaoli,LI Weijun,et al.Improvement of an image retrieval algorithm based on biomimetic imaginal thinking[J].CAAI Transactions on Intelligent Systems,2015,10():209.[doi:10.3969/j.issn.1673-4785.201411022]
[3]龚震霆,陈光喜,任夏荔,等.基于卷积神经网络和哈希编码的图像检索方法[J].智能系统学报,2016,11(3):391.[doi:10.11992/tis.201603028]
GONG Zhenting,CHEN Guangxi,REN Xiali,et al.An image retrieval method based on a convolutional neural network and hash coding[J].CAAI Transactions on Intelligent Systems,2016,11():391.[doi:10.11992/tis.201603028]
[4]唐文静,许兆新,张小峰.峰值检测FCM算法的医学图像分割[J].智能系统学报,2014,9(5):584.[doi:10.3969/j.issn.1673-4785.201408007]
TANG Wenjing,XU Zhaoxin,ZHANG Xiaofeng.Medical image segmentation based on FCM with peak detection[J].CAAI Transactions on Intelligent Systems,2014,9():584.[doi:10.3969/j.issn.1673-4785.201408007]
[5]杨晓兰,强彦,赵涓涓,等.基于医学征象和卷积神经网络的肺结节CT图像哈希检索[J].智能系统学报,2017,12(6):857.[doi:10.11992/tis.201706035]
YANG Xiaolan,QIANG Yan,ZHAO Juanjuan,et al.Hashing retrieval for CT images of pulmonary nodules based on medical signs and convolutional neural networks[J].CAAI Transactions on Intelligent Systems,2017,12():857.[doi:10.11992/tis.201706035]
[6]阿丽亚·巴吐尔,努尔毕亚·亚地卡尔,吾尔尼沙·买买提,等.改进SURF特征的维吾尔文复杂文档图像匹配检索[J].智能系统学报,2019,14(2):296.[doi:10.11992/tis.201709014]
ALIYA Batur,NURBIYA Yadikar,HORNISA Mamat,et al.Complex Uyghur document image matching and retrieval based on modified SURF feature[J].CAAI Transactions on Intelligent Systems,2019,14():296.[doi:10.11992/tis.201709014]
[7]韩璐,毕晓君.多尺度特征融合网络的视网膜OCT图像分类[J].智能系统学报,2022,17(2):360.[doi:10.11992/tis.202111024]
HAN Lu,BI Xiaojun.Retinal optical coherence tomography image classification based on multiscale feature fusion[J].CAAI Transactions on Intelligent Systems,2022,17():360.[doi:10.11992/tis.202111024]
[8]许柏祥,刘丽,邱桃荣.面向近重复文本图像检索的三分支孪生网络[J].智能系统学报,2022,17(3):515.[doi:10.11992/tis.202105018]
XU Boxiang,LIU Li,QIU Taorong.Near-duplicate document image retrieval based on three-stream convolutional Siamese network[J].CAAI Transactions on Intelligent Systems,2022,17():515.[doi:10.11992/tis.202105018]
备注/Memo
收稿日期:2025-8-10。
基金项目:国家重点研发计划项目（2024YFE0202700）；国家自然科学基金项目（62576178, U2433216，62471259，62506176）；江苏省自然科学基金项目（BK20231337）；江苏省高等学校自然科学基金项目（24KJB520032）；江苏省研究生科研与实践创新计划项目（SJCX25_2004，KYCX25_3741）.
作者简介:周琳琳，硕士研究生，主要研究方向为图像检索和多粒度计算。E-mail：15861759190@163.com。;丁卫平，教授，博士生导师，IEEE 高级会员，中国计算机学会杰出会员。主要研究方向为数据挖掘、多模态机器学习、多粒度计算、演化计算和医学大数据分析。连续6年(2020—2025)入选美国斯坦福大学全球前2%顶尖科学家榜单，其中2024年和2025年入选“终身科学影响力排行榜”，入选国际学术机构ScholarGPS 2024年全球前0.05%顶尖科学家榜单。江苏省高层次人才培养计划“333工程”第二层次培养对象， 江苏省“六大人才高峰”高层次人才，江苏省“青蓝工程”中青年学术带头人，江苏省“青蓝工程”优秀青年骨干教师，南通市“226 高层次人才培养工程”第二层次、第三层次培养对象。主持和主要参加国家重点研发计划重点专项、国家自然科学基金民航联合重点项目、国家自然科学基金面上和青年项目、江苏省自然科学基金、江苏省高校自然科学研究重大项目、江苏省现代农机装备与技术推广项目等各类科研项目20余项。获发明专利授权43项，其中美国发明专利3项，澳大利亚发明专利1项。 发表相关学术论文400余篇。E-mail：dwp9988@163.com。;张炜，讲师，硕士生导师，博士，主要研究方向为人工智能、模式识别和多视图学习。E-mail：weizhang@ntu.edu.cn。
通讯作者:丁卫平. E-mail：dwp9988@163.com
更新日期/Last Update:
1900-01-01