Laser & Optoelectronics Progress, Volume. 57, Issue 6, 060003(2020)

Research Progress on Content-Based Medical Image Retrieval

Feng Yang, Guohui Wei, Hui Cao*, Mengmeng Xing, Jing Liu, and Junzhong Zhang
Author Affiliations
  • School of Science and Technology, Shandong University of Traditional Chinese Medicine, Jinan, Shandong 250355, China
  • show less
    Figures & Tables(6)
    Flow chart of image retrieval using deep global features
    Flow chart of image retrieval based on deep local feature aggregation
    Diagram of IRMA system structure
    • Table 1. Representative methods of image feature extraction and their development stages

      View table

      Table 1. Representative methods of image feature extraction and their development stages

      TimeRepresentative methodCategory
      1996Methods featured by color[4],edge[5], and texture[6]Hand-craft global features
      2001Method featured by GIST (generalized search trees)[7]
      2003BoW (bag of word)[8]
      2004Method featured by SIFT (scale-invariant feature transform)[9]
      2005Method featured by HOG (histogram of oriented gradients)[10]
      2006SURF (speeded up robust features)[11],LBP (local binary pattern)[12]Hand-craft local features
      2007FV (fisher vector)[13]
      2012VLAD (vector of locally aggregated descriptor)[14]
      2014Triangulation embedding[15]
      2014Neural code[16]Deep global features
      2014MOP-CNN (multiscale orderlesspooling-convolutional neural network)[17]
      2015SPoC (sum-pooled convolutional features)[18]
      2016R-MAC (regional maximum activation of convolutions)[19],CroW (cross weight aggregation code)[20]Deep local features
      2017Class weighted[21]
      2018PWA (progressive web app)[22]
    • Table 2. Classification of depth feature extraction methods

      View table

      Table 2. Classification of depth feature extraction methods

      TypeCommon model
      Convolutionalneural network,
      Superviseddeep networkdeep stackingnetwork,
      deep-structuredconditional random fields
      Unsuperviseddeep networkAuto encoders, restrictedBoltzmann machines,sparse coding, K-means
      Semi-superviseddeep networkPre-trained deepneural networks
    • Table 3. Common CBMIR systems

      View table

      Table 3. Common CBMIR systems

      System nameApplication objectFeature extractionSimilarity measureRelated feedback
      ASSERT[75]CT image of lungLabeled area featureBased on classification×
      NHANES III[76]Spinal X-ray imageContour shapeContour matching×
      MRIAGE[77]MRI imageof brain3D TextureHistogram×
      FICBDS[78]FunctionalPETPhysiologicalinformationVectordistance×
      IRMA[79]Integrated medicalimagingMultiple featuredescriptionMultipleranging metric
      VisMed [80]Integratedmedical imagingVisual wordWordmatching×
      medGIFT[81]Integratedmedical imagingText andvisual featuresMultimodal informationsorting fusion×
      NovaMedSearech[82]Integrated medicalimagingText andvisual featuresMultimodal informationsorting fusion
      iMedline[83]Clinical caseText and visualfeaturesLinear weighting ofmultiple features
    Tools

    Get Citation

    Copy Citation Text

    Feng Yang, Guohui Wei, Hui Cao, Mengmeng Xing, Jing Liu, Junzhong Zhang. Research Progress on Content-Based Medical Image Retrieval[J]. Laser & Optoelectronics Progress, 2020, 57(6): 060003

    Download Citation

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

    Category: Reviews

    Received: Aug. 2, 2019

    Accepted: Aug. 22, 2019

    Published Online: Mar. 6, 2020

    The Author Email: Cao Hui (caohui63@163.com)

    DOI:10.3788/LOP57.060003

    Topics