Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (7): 2311-2318.DOI: 10.11772/j.issn.1001-9081.2022060924

• Multimedia computing and computer simulation • Previous Articles    

Pulmonary nodule detection algorithm based on attention feature pyramid networks

Yuanyuan QIN1,2(), Hong ZHANG1,2   

  1. 1.School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan Hubei 430065,China
    2.Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System (Wuhan University of Science and Technology),Wuhan Hubei 430065,China
  • Received:2022-06-24 Revised:2022-09-02 Accepted:2022-09-09 Online:2022-09-23 Published:2023-07-10
  • Contact: Yuanyuan QIN
  • About author:QIN Yuanyuan, born in 1998, M. S. candidate. Her research interests include computer vision, medical image processing, machine learning.
    ZHANG Hong, born in 1979, Ph. D., professor. Her research interests include cross-modal retrieval, machine learning, data mining.


秦源源1,2(), 张鸿1,2   

  1. 1.武汉科技大学 计算机科学与技术学院, 武汉 430065
    2.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 430065
  • 通讯作者: 秦源源
  • 作者简介:秦源源(1998—),女,湖南衡阳人,硕士研究生,主要研究方向:计算机视觉、医学图像处理、机器学习;


Aiming at the problems of low sensitivity and high false positive rate caused by various shapes and difficulty in detecting pulmonary nodules by the Computer-Aided Detection (CAD) system of pulmonary nodules, a pulmonary nodule detection algorithm based on attention feature pyramid networks was proposed. In the first stage, a more compact Dual Path Network (DPN) was used as the backbone network, and a Feature Pyramid Network (FPN) was combined for multi-scale prediction to obtain feature information at different levels. At the same time, the Global Attention Mechanism (GAM) was embedded to refine the semantic features to be emphasized in learning and improve the sensitivity of the algorithm. In the second stage, a false positive reduction network was proposed to obtain the final classification prediction results. In the training stage, the focal loss function and various data augmentation techniques were used to deal with the data imbalance problem. Experimental results on the public dataset LUNA16 (LUng Nodule Analysis 2016) show that the Competitive Performance Metric (CPM) of the algorithm only with the first stage reaches 0.908, and after adding the false positive reduction network, the CPM of the algorithm reaches 0.933, which is 1.1 percentage points higher than that of the classic algorithm — Convolutional Neural Network (CNN) based on Maximum Intensity Projection (MIP). And ablation experimental results show that the dual path network, FPN, and GAM are effective in improving the detection sensitivity. The above proves that the proposed two-stage detection algorithm can obtain multi-scale nodule information, improve the sensitivity of pulmonary nodule detection, and reduce the false positive rate.

Key words: pulmonary nodule detection, attention mechanism, Feature Pyramid Network (FPN), false positive reduction, Convolutional Neural Network (CNN)


针对肺结节计算机辅助检测(CAD)系统中肺结节形态各异难以检测带来的敏感度低、假阳性率高的问题,提出一种基于注意力特征金字塔网络的肺结节检测算法。在第一阶段,以更加紧凑的双路径网络(DPN)为骨干网络,并结合特征金字塔网络(FPN)进行多尺度预测,以获取不同层次的特征信息,同时嵌入全局注意力机制(GAM)来细化学习要强调的语义特征,并提高算法的敏感度;在第二阶段,提出一种假阳性抑制网络,以获得最终分类预测结果;在训练阶段,采用焦点损失函数和多种数据增强技术来处理数据不平衡问题。在公开数据集LUNA16 (LUng Nodule Analysis 2016)上的实验结果显示:仅有第一阶段的算法的竞争性能指标(CPM)达到了0.908,而加入假阳性抑制网络后算法的CPM达到了0.933,这与经典算法基于最大强度投影(MIP)的卷积神经网络(CNN)算法相比提升了1.1个百分点;而消融实验的结果表明DPN、FPN、GAM对于提升检测敏感度是有作用的。以上证明了所提出的两阶段检测算法可以获取多尺度结节信息,提高肺结节检测的敏感度,并且降低假阳性率。

关键词: 肺结节检测, 注意力机制, 特征金字塔网络, 假阳性抑制, 卷积神经网络

CLC Number: