首页|基于改进YOLOv5s的肠镜息肉多分类实时检测方法

基于改进YOLOv5s的肠镜息肉多分类实时检测方法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
为了在肠镜检查过程中对结直肠息肉进行快速鉴别检测,提出一种基于改进YOLOv5s的肠镜息肉多分类实时检测模型.该模型采用ConvNeXt作为主干网络,融入SimAM注意力机制提升检测性能,同时在颈部网络中使用基于GSConv的slim-neck模块减少网络参数.为了对模型进行训练和测试,构建了包含1 676张息肉图像并由专业医生标注的结直肠息肉数据集.提出的模型在测试集上的平均精度均值(mAP@0.5)为83.0％,相较于改进前提升8.4％,检测速度达到120帧/s.此外,模型在边缘侧部署检测速度超过25帧/s.结果表明,改进的YOLOv5s满足临床结肠镜检查对实时性与准确性的要求.
A real-time multi-class detection method for colonoscopy polyps based on improved YOLOv5s
To facilitate rapid identification and detection of colorectal polyps during colonoscopy procedures,a real-time multi-class detection model for colonoscopic polyps based on modified YOLOv5s is proposed.This model utilizes ConvNeXt as thebackbone network and incorporates the SimAM attention mechanism to improve detection performance.Additionally,a slim-neck module based on GSConv is employed in the neck network to reduce network parameters.For model training and testing,a colorectal polyp dataset containing 1 676 images annotated by professional doctors was constructed.The proposed model achieves a mean Average Precision(mAP@0.5)of 83.0％on the test set,which is an improvement of 8.4％compared to the model before modification,with a detection speed of 120 frames per second.Moreover,the model exhibits a detection speed exceeding 25 frames per second when deployed on edge devices.The results demonstrate that the improved YOLOv5s meets the clinical requirementsfor real-time and accurate colonoscopy examinations.

polypsadenomatous polypsobject detectionYOLOv5sreal-time

薛林雁、李轩昂、齐晁仪、曹杰、张颖、艾尚璞、杨昆

展开 >

河北大学质量技术监督学院,河北保定 071002

计量仪器与系统国家地方联合工程研究中心,河北保定 071002

河北省新能源汽车动力系统轻量化技术创新中心,河北保定 071002

息肉 腺瘤 检测 YOLOv5s 实时性

河北省自然科学基金资助项目保定市创新能力提升专项项目河北大学研究生创新项目河北大学研究生创新项目河北大学科研创新团队项目大学生创新创业训练计划创新训练项目大学生创新创业训练计划创新训练项目

F20232010692394G027HBU2024BS021HBU2024SS011IT2023B07DC2024376DC2024381

2024

10.3969/j.issn.1000-1565.2024.04.011

河北大学学报(自然科学版)
河北大学

河北大学学报(自然科学版)

CSTPCD北大核心
影响因子：0.322
ISSN：1000-1565
年,卷(期)：2024.44(4)