[1]臧佳明,郑力新,何建海,等.边缘细节增强的肺炎胸部X射线病灶定位[J].华侨大学学报(自然科学版),2025,46(5):493-504.[doi:10.11830/ISSN.1000-5013.202503008]
　ZANG Jiaming,ZHENG Lixin,HE Jianhai,et al.Edge-Enhanced Lesion Localization in Chest X-Rays for Pneumonia Detection[J].Journal of Huaqiao University(Natural Science),2025,46(5):493-504.[doi:10.11830/ISSN.1000-5013.202503008]
点击复制

边缘细节增强的肺炎胸部X射线病灶定位()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第46卷
期数:
2025年第5期
页码:
493-504
栏目:
出版日期:
2025-09-20

文章信息/Info

Title:
Edge-Enhanced Lesion Localization in Chest X-Rays for Pneumonia Detection
文章编号:
1000-5013(2025)05-0493-12
作者:
臧佳明;  郑力新;  何建海;  潘书万
华侨大学 工学院, 福建 泉州 362021
Author(s):
ZANG Jiaming;  ZHENG Lixin;  HE Jianhai;  PAN Shuwan
College of Engineering, Huaqiao University, Quanzhou 362021, China
关键词:
肺炎检测;  病灶定位;  辅助诊断;  SEIF模块;  YOLO11算法
Keywords:
pneumonia detection;  lesion localization;  aided diagnosis;  SEIF module;  YOLO11 algorithm
分类号:
TP399
DOI:
10.11830/ISSN.1000-5013.202503008
文献标志码:
A
摘要:
设计一种基于YOLO11s算法改进的YOLO11s-SAD算法,用于缓解微小病灶难以检测、复杂背景下病灶定位效果差和误检、漏检等情况。首先,设计空间边缘信息融合(SEIF)模块,使用基于Sobel算子实现的边缘检测与最大池化操作并行处理输入图像,以提升主干对病灶边缘的特征提取能力。然后,使用ASF-Neck作为新的颈部网络,通过优化特征融合机制更好地捕捉多尺度特征之间的相互关系。最后,使用动态上采样(DySample)替换了ASF-Neck中尺度序列特征融合(SSFF)模块内的双线性插值,减少上采样过程中肺炎细节特征的丢失,并采用Adam优化器进行模型参数优化。结果表明:文中算法在不显著增加参数量和浮点运算量的情况下,平均精度均值可以达到57.9%,相较于基准算法提升3.4%,其病灶定位效果优于其他主流检测算法。
Abstract:
An improved YOLO11s-SAD algorithm based on YOLO11 is designed to relieve the situation of difficult detection of tiny lesions, poor lesion localization performance in complex backgrounds, and issues of missed and false detections. First, a spatial edge information fusion(SEIF)module is designed, which enhances the feature extraction capability of backbone for lesion edges by procesings input images in parallel useing Sobel operator-based edge detection and max pooling. Then, ASF-Neck is employed as the new neck network to better capture relationships between multi-scale features by optimizing the feature fusion mechanism. Finally, dynamic upsampling(DySample)replaces bilinear interpolation in the scale sequence feature fusion(SSFF)module of ASF-Neck to reduce the loss of pneumonia detail features during upsampling. The model parameters are optimized using the Adam optimizer. Experimental results show that the proposed algorithm achieves a mean average precision of 57.9%, improving by 3.4% compared to the baseline, while introducing no significant increase in parameters or floating-point operations. The lesion localization performance also outperforms other mainstream detection algorithms.

参考文献/References:

[1] WANG Xiaosong,PENG Yifan,LU Le,et al.Chest X-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:3462-3471.DOI:10.1109/CVPR.2017.369.
[2] WHO.The top 10 causes of death[EB/OL].(2024-08-07)[2025-03-18] .https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death.
[3] 国家卫生健康委员会.中国卫生健康统计年鉴2023[EB/OL].(2025-01-24)[2025-03-19] .http://www.nhc.gov.cn/mohwsbwstjxxzx/tjtjnj/202501/b8d57baa95834269b5b3562bfec801a7.shtml.
[4] REN Shaoqing,HE Kaiming,GIRSHICK R,et al.Faster R-CNN: Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.DOI:10.1109/TPAMI.2016.2577031.
[5] KONG Tao,YAO Anbang,CHEN Yurong,et al.HyperNet: Towards accurate region proposal generation and joint object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:845-853.DOI:10.1109/CVPR.2016.98.
[6] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Press,2016:779-788.DOI:10.1109/CVPR.2016.91.
[7] REDMON J,FARHADI A.YOLO9000: Better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE Press,2017:7263-7271.DOI:10.1109/CVPR.2017.690.
[8] REDMON J,FARHADI A.YOLOV3: An incremental improvement[EB/OL].(2018-04-08)[2025-03-19] .https://arxiv.org/abs/1804.02767.
[9] LIU Wei,ANGUELOV D,ERHAN D,et al.SSD: Single shot multibox detector[C]//Computer Vision-ECCV 2016: 14th European Conference.Cham:Springer International Publishing,2016:21-37.DOI:10.1007/978-3-319-46448-0_2.
[10] CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection with transformers[C]//European Conference on Computer Vision.Cham:Springer International Publishing,2020:213-229.DOI:10.1007/978-3-030-58452-8_13.
[11] GABRUSEVA T,POPLAVSKIY D,KALININ A.Deep learning for automatic pneumonia detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.Seattle:IEEE Press,2020:1436-1443.DOI:10.1109/CVPRW50498.2020.00183.
[12] WU Hongli,PING Mingzhu,LU Huijuan,et al.A deep learning method for pneumonia detection based on fuzzy non-maximum suppression[C]//Proceedings of the 2nd International Conference on Artificial Intelligence and Computer Engineering.Hangzhou:IEEE Press,2021:89-94.DOI:10.1109/ICAICE54393.2021.00026.
[13] YAO Shangjie,CHEN Yaowu,TIAN Xiang,et al.An improved algorithm for detecting pneumonia based on YOLOv3[J].Applied Sciences,2020,10(5):1818.DOI:10.3390/app10051818.
[14] LIU Hailong,CUI Jinrong,PENG Chaoda.Pneumonia detection algorithm based on improved YOLOv3[C]//IoT and Big Data Technologies for Health Care 2021.Cham:Springer International Publishing,2021:313-320.DOI:10.1007/978-3-030-94182-6_22.
[15] 马书浩,安居白.基于YOLOv3改进的肺炎检测算法[J].激光与光电子学进展,2020,57(18):318-324.DOI:10.3788/LOP57.181505.
[16] YUAN Yiling,YAO Shaochen,REN Xuan,et al.Chest X-ray disease diagnosis method based on YOLO model and pseudo color conversion[C]//Proceedings of the 5th International Conference on Data Science and Information Technology.Shanghai:IEEE Press,2022:1-5.DOI:10.1109/DSIT55514.2022.9943871.
[17] WU Linghua,ZHANG Jing,WANG Yilin,et al.Pneumonia detection based on RSNA dataset and anchor-free deep learning detector[J].Scientific Reports,2024,14(1):1929.DOI:10.1038/s41598-024-52156-7.
[18] YAN Nan,TAO Ye.Pneumonia X-ray detection with anchor-free detection framework and data augmentation[J].International Journal of Imaging Systems and Technology,2023,33(4):1235-1246.DOI:10.1002/ima.22860.
[19] YAO Shangjie,CHEN Yaowu,TIAN Xiang,et al.Pneumonia detection using an improved algorithm based on faster R-CNN[J].Computational and Mathematical Methods in Medicine,2021,2021(1):8854892.DOI:10.1155/2021/8854892.
[20] 王合佳,林宁,林振超,等.改进YOLO的X射线管道焊缝检测算法[J].华侨大学学报(自然科学版),2024,45(6):766-775.DOI:10.11830/ISSN.1000-5013.202403040.
[21] KANG Ming,TING C M,TING F F,et al.ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation[J].Image and Vision Computing,2024,147:105057.DOI:10.1016/j.imavis.2024.105057.
[22] LIU Wenze,LU Hao,FU Hongtao,et al.Learning to upsample by learning to sample[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Paris:IEEE Press,2023:6004-6014.DOI:10.1109/ICCV51070.2023.00554.
[23] 覃诗译,张畅,刘遥,等.组织内异物声光成像的COMSOL仿真模拟[J].福建师范大学学报(自然科学版),2025,41(2):117-124.DOI:10.12046/j.issn.1000-5277.2024050032.
[24] STEIN A,WU C,CARR C,et al.RSNA pneumonia detection challenge[EB/OL].(2018-10-17)[2025-03-19] .https://kaggle.com/competitions/rsna-pneumonia-detection-challenge.
[25] LI Hulin,LI Jun,WEI Hanbing,et al.Slim-neck by GSConv: A lightweight-design for real-time detector architectures[J].Journal of Real-Time Image Processing,2024,21(3):62.DOI:10.1007/s11554-024-01436-6.
[26] LI Kaige,GENG Qichuan,WAN Maoxian,et al.Context and spatial feature calibration for real-time semantic segmentation[J].IEEE Transactions on Image Processing,2023,32:5465-5477.DOI:10.1109/TIP.2023.3318967.
[27] TAN Mingxing,PANG Ruoming,LE Q V.Efficientdet: Scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle:IEEE Press,2020:10778-10787.DOI:10.1109/CVPR42600.2020.01079.
[28] WANG Jiaqi,CHEN Kai,XU Rui,et al.CARAFE: Content-aware reassembly of features[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision.Seoul:IEEE Press,2019:3007-3016.DOI:10.1109/ICCV.2019.00310.

备注/Memo

备注/Memo:
收稿日期: 2025-03-20
通信作者: 郑力新(1967-),男,教授,博士,主要从事图像分析、机器视觉、深度学习方法的研究。E-mail:zlx@hqu.edu.cn。
基金项目: 福建省科技计划项目(2020Y0039)https://hdxb.hqu.edu.cn/
更新日期/Last Update: 2025-09-20