[1]吕佳,龚枭,何玲.融合空间域与多轴频域分析的儿童肺炎分类模型[J].智能系统学报,2026,21(4):963-978.[doi:10.11992/tis.202510034]
Lü Jia,GONG Xiao,HE Ling.Classification model for pediatric pneumonia built by integrating spatial and multi-axis frequency domain analysis[J].CAAI Transactions on Intelligent Systems,2026,21(4):963-978.[doi:10.11992/tis.202510034]
点击复制
Lü Jia,GONG Xiao,HE Ling.Classification model for pediatric pneumonia built by integrating spatial and multi-axis frequency domain analysis[J].CAAI Transactions on Intelligent Systems,2026,21(4):963-978.[doi:10.11992/tis.202510034]
融合空间域与多轴频域分析的儿童肺炎分类模型
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第4期
页码:
963-978
栏目:
学术论文—机器感知与模式识别
出版日期:
2026-07-05
- Title:
- Classification model for pediatric pneumonia built by integrating spatial and multi-axis frequency domain analysis
- Keywords:
- pediatric pneumonia; image classification; deep learning; X-Ray; spatial-frequency domain collaboration; mutli-axis frequency domain analysis; multi-scale; dynamic gating
- 分类号:
- TP391.4
- 摘要:
- 儿童肺炎是一种严重威胁全球儿童健康的疾病，其精准分类是有效治疗的关键，但其X射线图像兼具细微病理纹理与大范围弥漫性病变，单一空间域模型难以高效协同表征。为此，本文提出融合空间域与多轴频域分析的儿童肺炎分类模型。模型前两阶段构建位移感知多尺度单元，捕捉细粒度病理纹理；后两阶段设计多轴傅里叶单元，在频域建模长距离依赖，刻画大范围病变特征。此外，设计多核卷积门控线性单元增强各阶段特征表示。实验表明，模型在ChestXRay2017数据集上，准确率和F1分数较最优对比模型分别提升2.72%和2.75%，并在VinDr-PCXR和Curated X-Ray数据集上均取得具有竞争力的性能。本文结果验证了模型的有效性与泛化性，为儿童肺炎诊断提供了新方案。
- Abstract:
- Pediatric pneumonia poses a serious threat to children’s health worldwide, and its precise classification is crucial for effective treatment. Chest X-ray images used for pneumonia classification exhibit subtle pathological textures and large-scale diffuse lesions, making it difficult for a single spatial domain model to efficiently and effectively represent both characteristics. To address this issue, this paper proposes a classification model that fuses spatial domain and multi-axis frequency domain analysis. In the first two stages of the model, a shift-aware multi-scale unit is constructed to capture fine-grained pathological textures. In the last two stages, a multi-axis Fourier unit is constructed to model long-range dependencies in the frequency domain and characterize large-scale lesion features. Additionally, a multi-kernel convolutional gated linear unit is developed to enhance feature representation at each stage. Experimental results showed that on the ChestXRay2017 dataset, the model achieved improvements of 2.72% and 2.75% in accuracy and F1-score, respectively, compared to the state-of-the-art model. It also achieved competitive performance on the VinDr-PCXR and Curated X-Ray datasets, validating the model’s effectiveness and generalization. Thus, the proposed model provides a new solution for the auxiliary diagnosis of pediatric pneumonia.
- 参考文献/References:
-
[1] ZHENG Jingyuan, LIU Dingming, YANG Zhifu, et al. SEACC: self-evolving and adaptive contrastive learning for classification of pediatric pneumonia and anteroposterior/posteroanterior chest radiographs[J]. Displays, 2024, 81: 102607
[2] 吕佳, 于明楷 , 陈欣, 等. 差异感知引导的边界Transformer儿童肺炎CT图像分割网络[J]. 光学学报, 2025, 45(15): 112-136 L? Jia, YU Mingkai, CHEN Xin, et al. Difference aware guided boundary Transformer network for childhoodPneumonia CT image segmentation[J]. Acta optica sinca, 2025, 45(15): 112-136
[3] KAYA M. Feature fusion-based ensemble CNN learning optimization for automated detection of pediatric pneumonia[J]. Biomedical signal processing and control, 2024, 87: 105472
[4] 贠恺, 贾荣浩, 魏国辉, 等. 基于CNN与Transformer混合模型的肺炎辅助诊断[J]. 计算机系统应用, 2025, 34(2): 216-224 YUN Kai, JIA Ronghao, WEI Guowei, et al. Pneumonia assisted diagnosis based on hybrid model of CNN and Transformer[J]. Computer systems and applications, 2025, 34(2): 216-224
[5] RICKARD D, KABIR M A, HOMAIRA N. Machine learning-based approaches for distinguishing viral and bacterial pneumonia in paediatrics: a scoping review[J]. Computer methods and programs in biomedicine, 2025, 268: 108802
[6] 程文娟, 于国庆. 基于XDense-RC-NET的CXR图像分类算法[J]. 计算机应用研究, 2022, 39(12): 3803-3807 CHENG Wenjun, YU Guoqing. Improved CXR image classification algorithm based on XDense-RC-NET[J]. Application research of computers, 2022, 39(12): 3803-3807
[7] KHAN W, ZAKI N, ALI L. Intelligent pneumonia identification from chest X-rays: a systematic literature review[J]. IEEE access, 2021, 9: 51747-51771
[8] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Medical image analysis, 2017, 42: 60-88
[9] RAJPURKAR P, IRVIN J, ZHU K, et al. Chexnet: radiologist-level pneumonia detection on chest X-rays with deep learning[EB/OL]. (2017-12-25)[2025-08-21]. https://arxiv.org/abs/1711.05225.
[10] 潘伟, 马志庆, 魏国辉, 等. 卷积神经网络在肺炎图像分类中的研究进展与展望[J]. 中国医疗设备, 2025, 40(7): 147-154 PAN Wei, MA Zhiqing, WEI Guohui, et al. Research progress and prospect of convolutional neural networks in pneumoniaimage classification[J]. China medical devices, 2025, 40(7): 147-154
[11] HAMMOUDI K, BENHABILES H, MELKEMI M, et al. Deep learning on chest X-ray images to detect and evaluate pneumonia cases at the era of COVID-19[J]. Journal of medical systems, 2021, 45(7): 75
[12] DU Jie, GUAN Kai, ZHOU Yanhong, et al. Parameter-free similarity-aware attention module for medical image classification and segmentation[J]. IEEE transactions on emerging topics in computational intelligence, 2023, 7(3): 845-857
[13] 周涛, 叶鑫宇, 陆惠玲, 等. 基于多分辨率注意密集网络的肺炎分类识别方法[J]. 模式识别与人工智能, 2023, 36(6): 544-555 ZHOU Tao, YE Xinyu, LU Huiling, et al. Pneumonia classification and recognition method based on multi-resolution attention dense network[J]. Pattern recognition and artificial intelligence, 2023, 36(6): 544-555
[14] SUN Junding, XUE Jianxiang, XU Zhaozhao, et al. SAGCN: self-adaptive graph convolutional network for pneumonia detection[J]. Biomedical signal processing and control, 2025, 106: 107634
[15] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers forimage recognition at scale[C]//International Conference on Learning Representations. Online: ICLR Foundation, 2021: 1-22.
[16] OKOLO G I, KATSIGIANNIS S, RAMZAN N. IEViT: an enhanced vision transformer architecture for chest X-ray image classification[J]. Computer methods and programs in biomedicine, 2022, 226: 107141
[17] UKWUOMA C C, QIN Zhiguang, BELAL BIN HEYAT M, et al. A hybrid explainable ensemble transformer encoder for pneumonia identification from chest X-ray images[J]. Journal of advanced research, 2023, 48: 191-211
[18] MANZARI O N, AHMADABADI H, KASHIANI H, et al. MedViT: a robust vision transformer for generalized medical image classification[J]. Computers in biology and medicine, 2023, 157: 106791
[19] LASKER A, GHOSH M, SK M O, et al. LungConVT-Net: a visual transformer network with blended features for Pneumonia detection[J]. Pattern recognition, 2026, 171: 112150
[20] 王梦溪, 雷涛, 姜由涛, 等. 基于空频协同的CNN-Transformer多器官分割网络[J]. 智能系统学报, 2025, 20(5): 1266-1280 WANG Mengxi, LEI Tao, JIANG Youtao, et al. CNN-transformer multiorgan segmentation network based on space-frequency collaboration[J]. CAAI transactions on intelligent systems, 2025, 20(5): 1266-1280
[21] 葛斌, 卞文强, 夏晨星, 等. 基于空间频域交互感知的医学图像分割[J/OL]. 光电子·激光(2025-09-26) [2025-11-26]. https://link.cnki.net/urlid/12.1182.O4.20250926.1622.022. GE Bin, BIAN Wenqiang, XIA Chenxing, et al. Medical image segmentation based on spatial frequency domain interactive perception[J/OL]. Journal of optoelectronics·laser(2025-09-26) [2025-11-26]. https://link.cnki.net/urlid/12.1182.O4.20250926.1622.022.
[22] RUAN Jiacheng, GAO Jingsheng, XIE Mingye, et al. Learning multi-axis representation in frequency domain for medical image segmentation[J]. Machine learning, 2025, 114(1): 10
[23] WANG Wenxuan, WANG Jing, CHEN Chen, et al. FreMIM: fourier transform meets masked image modeling for medical image segmentation[C]//2024 IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2024.
[24] GAO Tian, ZHANG Yu, ZHANG Zhiyuan, et al. BHViT: binarized hybrid vision transformer[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2025.
[25] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016.
[26] SHI Dai. TransNeXt: robust foveal visual perception for vision transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024.
[27] KERMANY D S, GOLDBAUM M, CAI Wenjia, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5): 1122-1131. e9.
[28] PHAM H H, NGUYEN N H, TRAN T T, et al. PediCXR: an open, large-scale chest radiograph dataset for interpretation of common thoracic diseases in children[J]. Scientific data, 2023, 10: 240
[29] SAIT U, LAL K, PRAJAPATI S, et al. Curated dataset for covid-19 posterior-anterior chest radiography images(X-rays)[EB/OL]. (2020-09-15)[2025-08-21]. https://data.mendeley.com/datasets/9xkhgts2s6/1.
[30] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016.
[31] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017.
[32] TAN M, LE Q. Efficientnetv2: smaller models and faster training[C]//Proceedings of the 38th International Conference on Machine Learning. Online: IMLS, 2021.
[33] HOWARD A, SANDLER M, CHEN Bo, et al. Searching for MobileNetV3[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019.
[34] KUMAR V, GUPTA A, HAZARIKA B B, et al. Automatic diagnosis of COVID-19 from chest X-ray images using transfer learning-based deep features and machine learning models[J]. China communications, 2025, 22(7): 274-289
[35] KILI?ARSLAN S, K?ZKURT C, BA? S, et al. Detection and classification of pneumonia using novel superior exponential(SupEx) activation function in convolutional neural networks[J]. Expert systems with applications, 2023, 217: 119503
[36] LIU Zhuang, MAO Hanzi, WU Chaoyuan, et al. A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022.
[37] WANG Ao, CHEN Hui, LIN Zijia, et al. LSNet: see large, focus small[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2025.
[38] OUYANG Haibin, LIU Dongmei, LI S, et al. Two-stage deep feature selection method using voting differential evolution algorithm for pneumonia detection from chest X-ray images[J]. IEEE transactions on emerging topics in computational intelligence, 2025, 9(1): 918-932
[39] LIU Ze, LIN Yutong, CAO Yue, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021.
[40] MEHTA S, RASTEGARI M. MobileViT: light-weight, general-purpose, and mobile-friendly uivision transformer[EB/OL]. (2021-10-05)[2025-10-17]. https://arxiv.org/abs/2110.02178.
[41] YU Weihao, LUO Mi, ZHOU Pan, et al. MetaFormer is actually what you need for vision[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022.
[42] LOU Meng, ZHANG Shu, ZHOU Hongyu, et al. TransXNet: learning both global and local dynamics with a dual dynamic token mixer for visual recognition[J]. IEEE transactions on neural networks and learning systems, 2025, 36(6): 11534-11547
- 相似文献/References:
-
[1]李海峰,杜军平.颜色特征的图像分类技术研究[J].智能系统学报,2008,3(2):65.[doi:CNKI:SUN:ZNXT.0.2008-02-017]
[2]李海峰,杜军平.颜色特征的图像分类技术研究[J].智能系统学报,2008,3(2):155.
LI Hai-feng,DU Jun-ping.Image classification technology based on color features[J].CAAI Transactions on Intelligent Systems,2008,3():155.
[3]姚伏天,钱沄涛.高斯过程及其在高光谱图像分类中的应用[J].智能系统学报,2011,6(5):396.
YAO Futian,QIAN Yuntao.Gaussian process and its applications in hyperspectral image classification[J].CAAI Transactions on Intelligent Systems,2011,6():396.
[4]尤雅萍,成运,苏松志,等.基于谱域-空域结合特征和图割原理的高光谱图像分类[J].智能系统学报,2015,10(2):201.[doi:10.3969/j.issn.1673-4785.201410040]
YOU Yaping,CHENG Yun,SU Songzhi,et al.Hyperspectral image classification based on spectral-spatial combination features and graph cut[J].CAAI Transactions on Intelligent Systems,2015,10():201.[doi:10.3969/j.issn.1673-4785.201410040]
[5]赵骞,李敏,赵晓杰,等.基于感受野学习的特征词袋模型简化算法[J].智能系统学报,2016,11(5):663.[doi:10.11992/tis.201601001]
ZHAO Qian,LI Min,ZHAO Xiaojie,et al.Learning receptive fields for compact bag-of-feature model[J].CAAI Transactions on Intelligent Systems,2016,11():663.[doi:10.11992/tis.201601001]
[6]费宇杰,吴小俊.一种局部聚合描述符和组显著编码相结合的编码方法[J].智能系统学报,2017,12(2):172.[doi:10.11992/tis.201602010]
FEI Yujie,WU Xiaojun.A new feature coding algorithm based on the combination of group salient coding and VLAD[J].CAAI Transactions on Intelligent Systems,2017,12():172.[doi:10.11992/tis.201602010]
[7]杨梦铎,栾咏红,刘文军,等.基于自编码器的特征迁移算法[J].智能系统学报,2017,12(6):894.[doi:10.11992/tis.201706037]
YANG Mengduo,LUAN Yonghong,LIU Wenjun,et al.Feature transfer algorithm based on an auto-encoder[J].CAAI Transactions on Intelligent Systems,2017,12():894.[doi:10.11992/tis.201706037]
[8]马忠丽,刘权勇,武凌羽,等.一种基于联合表示的图像分类方法[J].智能系统学报,2018,13(2):220.[doi:10.11992/tis.201611036]
MA Zhongli,LIU Quanyong,WU Lingyu,et al.Syncretic representation method for image classification[J].CAAI Transactions on Intelligent Systems,2018,13():220.[doi:10.11992/tis.201611036]
[9]魏彩锋,孙永聪,曾宪华.图正则化字典对学习的轻度认知功能障碍预测[J].智能系统学报,2019,14(2):369.[doi:10.11992/tis.201709033]
WEI Caifeng,SUN Yongcong,ZENG Xianhua.Dictionary pair learning with graph regularization for mild cognitive impairment prediction[J].CAAI Transactions on Intelligent Systems,2019,14():369.[doi:10.11992/tis.201709033]
[10]赵玉新,赵廷.海底声呐图像智能底质分类技术研究综述[J].智能系统学报,2020,15(3):587.[doi:10.11992/tis.202004026]
ZHAO Yuxin,ZHAO Ting.Survey of the intelligent seabed sediment classification technology based on sonar images[J].CAAI Transactions on Intelligent Systems,2020,15():587.[doi:10.11992/tis.202004026]
备注/Memo
收稿日期:2025-10-28。
基金项目:国家自然科学基金重大项目（11991024）；重庆市自然科学基金创新发展联合基金重点项目（CSTB2025NSCQ-LZX0074, CSTB2024NSCQ-LZX0090）.
作者简介:吕佳，教授，博士，主要研究方向为机器学习、数据挖掘及其在医学图像处理中的应用。主持或参与国家、省部级科研项目 20余项，发表学术论文 70 余篇。 E-mail：lvjia@cqnu.edu.cn。;龚枭，硕士研究生，主要研究方向为深度学习及其在医学图像处理中的应用。E-mail：2024110516036@stu.cqnu.edu.cn。;何玲，主任医师，博士，主要研究方向为儿科影像、人工智能和影像诊断。E-mail：heling508@sina.com。
通讯作者:吕佳. E-mail：lvjia@cqnu.edu.cn
更新日期/Last Update:
1900-01-01