计算机应用 ›› 2019, Vol. 39 ›› Issue (10): 2915-2922.DOI: 10.11772/j.issn.1001-9081.2019030510

• 人工智能 • 上一篇    下一篇

基于级联全卷积神经网络的颈部淋巴结自动识别算法

秦品乐, 李鹏波, 曾建潮, 朱辉, 徐少伟   

  1. 中北大学 大数据学院, 太原 030051
  • 收稿日期:2019-03-27 修回日期:2019-04-30 出版日期:2019-10-10 发布日期:2019-05-28
  • 通讯作者: 曾建潮
  • 作者简介:秦品乐(1978-),男,山西长治人,副教授,博士,主要研究方向:大数据、机器视觉、三维重建;李鹏波(1995-),男,山西运城人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理;曾建潮(1963-),男,山西太原人,教授,博士生导师,博士,主要研究方向:复杂系统的维护决策和健康管理;朱辉(1993-),男,江西瑞金人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理;徐少伟(1995-),男,山西太原人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理。

Automatic recognition algorithm for cervical lymph nodes using cascaded fully convolutional neural networks

QIN Pinle, LI Pengbo, ZENG Jianchao, ZHU Hui, XU Shaowei   

  1. School of Data Science and Technology, North University of China, Taiyuan Shanxi 030051, China
  • Received:2019-03-27 Revised:2019-04-30 Online:2019-10-10 Published:2019-05-28

摘要: 针对现有算法自动识别颈部淋巴结效率不高、存在大量假阳性且整体假阳性去除效果不理想的问题,提出一种基于级联全卷积神经网络(FCN)的颈部淋巴结识别算法。首先,结合医生的先验知识采用级联FCN进行初步识别,即第一个FCN从头颈部计算机断层扫描图像(CT)中提取淋巴结医学分区;然后,第二个FCN从分区内提取候选样本并在三维层面合并这些样本以生成三维图像块;最后,将提出的特征块平均池化引入到三维分类网络中,对输入的不同尺度三维图像块进行二分类以去除假阳性。在颈部淋巴结数据集中,采用级联FCN识别颈部淋巴结的召回率可达97.23%;引入特征块平均池化的三维分类网络的分类准确率可达到98.7%。在去除假阳性之后的准确率可达93.26%。实验结果分析表明,所提算法能有效实现颈部淋巴结的自动识别并取得较高的召回率和准确率,优于目前相关文献报道的算法;且算法简单高效,易于扩展到其他三维医学图像的目标检测任务中。

关键词: 颈部淋巴结检测, 计算机辅助诊断, 全卷积神经网络, 假阳性去除, 三维医学影像

Abstract: The existing automatic recognition algorithms for cervical lymph nodes have low efficiency, and the overall false positive removal are unsatisfied, so a cervical lymph node detection algorithm using cascaded Fully Convolutional Neural Networks (FCNs) was proposed. Firstly, combined with the prior knowledge of doctors, the cascaded FCNs were used for preliminary identification, that was, the first FCN was used for extracting the cervical lymph node region from the Computed Tomography (CT) image of head and neck. Then, the second FCN was used to extract the lymph node candidate samples from the region, and merging them at the three-dimensional (3D) level to generate a 3D image block. Finally, the proposed feature block average pooling method was introduced into the 3D classification network, and the 3D input image blocks with different scales were classified into two classes to remove false positives. On the cervical lymph node dataset, the recall of cervical lymph nodes identified by cascaded FCNs is up to 97.23%, the classification accuracy of the 3D classification network with feature block average pooling can achieve 98.7%. After removing false positives, the accuracy of final result reaches 93.26%. Experimental results show that the proposed algorithm can realize the automatic recognition of cervical lymph nodes with high recall and accuracy, which is better than the current methods reported in the literatures; it is simple and efficient, easy to extend to other tasks of 3D medical images recognition.

Key words: cervical lymph node detection, computer-aided diagnosis, Fully Convolutional Neural (FCN) network, false positive removal, Three-Dimensional (3D) medical imaging

中图分类号: