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. 56, Issue 24, 241003(2019)

Malignant Thyroid Nodule Detection Based on Circular Convolutional Neural Network

Bin Zheng1, Chen Yang1, Xiaoping Ma2, and Libo Liu1、*
Author Affiliations
  • 1School of Information Engineering, Ningxia University, Yinchuan, Ningxia 750021, China
  • 2Medical Technologic Departments, Yinchuan People's Hospital, Yinchuan, Ningxia 750002, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (10)
    Equations (0)
    References (19)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(10)
    Experimental procedure of circular CNN

    Fig. 1. Experimental procedure of circular CNN

    Download full size
    Ultrasound images of thyroid. (a) Original image; (b) noise-removal image; (c) region of interest

    Fig. 2. Ultrasound images of thyroid. (a) Original image; (b) noise-removal image; (c) region of interest

    Download full size
    Basic principle of circular CNN

    Fig. 3. Basic principle of circular CNN

    Download full size
    Structure of CNN-Fusion

    Fig. 4. Structure of CNN-Fusion

    Download full size
    Activation function plots. (a) Sigmoid; (b) ReLUs

    Fig. 5. Activation function plots. (a) Sigmoid; (b) ReLUs

    Download full size
    Experimental data. (a) Accuracy rate; (b) Loss value

    Fig. 6. Experimental data. (a) Accuracy rate; (b) Loss value

    Download full size
    Loss curves of ReLUs and Sigmoid functions

    Fig. 7. Loss curves of ReLUs and Sigmoid functions

    Download full size
    Feature maps of ultrasound image of thyroid

    Fig. 8. Feature maps of ultrasound image of thyroid

    Download full size

    • Table 1. Image numbers of thyroid classification

      View table

      Table 1. Image numbers of thyroid classification

      DatasourceClassification ⅠClassification ⅡClassification Ⅲ
      NormalNoduleBenignMalignantMalignantHighly deteriorated
      Local21571101609492288288
      Romero213714580580
      Total215711018221206868868
      Test648330246361260260

    • Table 2. Comparison of classification results for good and malignancy

      View table

      Table 2. Comparison of classification results for good and malignancy

      MethodAccuracy /%
      ANN[8]88.24
      SVM[8]76.47
      LOOCV[9]86.60
      TND[10]65.50
      ResNet[19]92.40
      Proposed method94.30
    Tools

    Get Citation

    Copy Citation Text

    Bin Zheng, Chen Yang, Xiaoping Ma, Libo Liu. Malignant Thyroid Nodule Detection Based on Circular Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(24): 241003

    Download Citation

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

    Category: Image Processing

    Received: Apr. 8, 2019

    Accepted: Jun. 6, 2019

    Published Online: Nov. 26, 2019

    The Author Email: Liu Libo (liulib@163.com)

    DOI:10.3788/LOP56.241003

    Topics

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