Meniscal Tear and ACL Injury Detection Model Based on AlexNet and Iterative ReliefF.

Magnetic resonance (MR) is one of the special imaging techniques used to diagnose orthopedics and traumatology. In this study, a new method has been proposed to detect highly accurate automatic meniscal tear and anterior cruciate ligament (ACL) injuries. In this study, images in three different slic...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Digital Imaging Vol. 35; no. 2; pp. 200 - 213
Autores principales: Key, Sefa, Baygin, Mehmet, Demir, Sukru, Dogan, Sengul, Tuncer, Turker
Formato: diagnostic images equations & formulas pictorial research tables/charts Journal Article
Publicado: Springer Nature Apr2022
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=155757684&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 155757684
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        08971889
        DOQ
      jtl: Journal of Digital Imaging
      issn: 08971889
      maglogo: N
    pubinfo:
      dt: Apr2022
      vid: 35
      iid: 2
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        155757684
        154756341
        155757684
        155757684
        10.1007/s10278-022-00581-3
        155757684
      ppf: 200
      ppct: 13
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Meniscal Tear and ACL Injury Detection Model Based on AlexNet and Iterative ReliefF.
      aug:
        au:
          Key, Sefa
          Baygin, Mehmet
          Demir, Sukru
          Dogan, Sengul
          Tuncer, Turker
        affil: Department of Orthopedics, Bingol State Hospital, Health Ministry, Bingol, Turkey
      sug:
        subj:
          Meniscal Injuries Diagnosis
          Anterior Cruciate Ligament Injuries Diagnosis
          Magnetic Resonance Imaging Methods
          Human
          Female
          Male
          Algorithms
          Image Processing, Computer Assisted
          Software
          Validity
          Machine Learning
          Descriptive Statistics
          Female
          Male
      ab: Magnetic resonance (MR) is one of the special imaging techniques used to diagnose orthopedics and traumatology. In this study, a new method has been proposed to detect highly accurate automatic meniscal tear and anterior cruciate ligament (ACL) injuries. In this study, images in three different slices were collected. These are the sagittal, coronal, and axial slices, respectively. Images taken from each slice were categorized in 3 different ways: sagittal database (sDB), coronal database (cDB), and axial database (aDB). The proposed model in the study uses deep feature extraction. In this context, deep features have been obtained by using fully-connected layers of AlexNet architecture. In the second stage of the study, the most significant features were selected using the iterative RelifF (IRF) algorithm. In the last step of the application, the features are classified by using the k-nearest neighbor (kNN) method. Three datasets were used in the study. These datasets, sDB, and cDB, have four classes and consist of 442 and 457 images, respectively. The aDB used in the study has two class labels and consists of 190 images. The model proposed within the scope of the study was applied in 3 datasets. In this context, 98.42%, 100%, and 100% accuracy values were obtained for sDB, cDB, and aDB datasets, respectively. The study results showed that the proposed method detected meniscal tear and anterior cruciate ligament (ACL) injuries with high accuracy.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        equations & formulas
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N