Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 55, Issue 5, 051006(2018)

Detection of Pulmonary Nodules CT Images Combined with Two-Dimensional and Three-Dimensional Convolution Neural Networks

Guang Miao1、1; and Chaofeng Li1、2;
Author Affiliations
  • 1 Key Laboratory of Advanced Process Control for Light Industry, Jiangnan University, Wuxi, Jiangsu 214122, China
  • 1 School of Internet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (11)
    Equations (0)
    References (25)
    Cited By (8)
    Tools
    Paper Information
    Topics
    Figures & Tables(11)
    Flow chart of lung nodule detection system

    Fig. 1. Flow chart of lung nodule detection system

    Download full size
    CT slice original images and U-net prediction images. (a) Original images; (b) prediction images

    Fig. 2. CT slice original images and U-net prediction images. (a) Original images; (b) prediction images

    Download full size
    Structure of 3D convolution neural network false positive removal system network

    Fig. 3. Structure of 3D convolution neural network false positive removal system network

    Download full size
    Number distribution of nodules with different sizes

    Fig. 4. Number distribution of nodules with different sizes

    Download full size
    Images of nodules with different sizes in the database. (a) Small nodules; (b) middle nodules; (c) big nodules

    Fig. 5. Images of nodules with different sizes in the database. (a) Small nodules; (b) middle nodules; (c) big nodules

    Download full size
    Training error and test accuracy curves of 3D convolution neural network model

    Fig. 6. Training error and test accuracy curves of 3D convolution neural network model

    Download full size
    Accuracy of average number of false positives per CT image

    Fig. 7. Accuracy of average number of false positives per CT image

    Download full size
    Effect of the dimensions of the input image block on the experimental results

    Fig. 8. Effect of the dimensions of the input image block on the experimental results

    Download full size
    Effect of the selection of network model on experimental results

    Fig. 9. Effect of the selection of network model on experimental results

    Download full size
    False negative nodules

    Fig. 10. False negative nodules

    Download full size

    • Table 1. Comparison of detection algorithms of pulmonary nodules in LIDC-IDRI database

      View table

      Table 1. Comparison of detection algorithms of pulmonary nodules in LIDC-IDRI database

      CAD systemsYearNumber of casesNodules size /mmNodule number(Sensitivity /%) /(FPs /a.u.)
      Proposed method-888≥3118687.3/1.097.0/4.0
      Literature [12]2016888≥3118684.4/1.090.5/4.0
      Literature [13]2015888≥3118673.0/1.076.0/4.0
      Literature [20]2015949≥3174980.0/8.0
      Literature [18]2014108≥46875.0/2.0
      Literature [19]2013583-3015195.3/2.3
      Literature [25]201284≥314897.0/6.188/2.5
    Tools

    Get Citation

    Copy Citation Text

    Guang Miao, Chaofeng Li. Detection of Pulmonary Nodules CT Images Combined with Two-Dimensional and Three-Dimensional Convolution Neural Networks[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051006

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image processing

    Received: Nov. 2, 2017

    Accepted: --

    Published Online: Sep. 11, 2018

    The Author Email: Guang Miao (miao1094@126.com)

    DOI:10.3788/LOP55.051006

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology