Optimal matrix size of chest radiographs for computer-aided detection on lung nodule or mass with deep learning.

Objectives: To investigate the optimal input matrix size for deep learning-based computer-aided detection (CAD) of nodules and masses on chest radiographs.Methods: We retrospectively collected 2088 abnormal (nodule/mass) and 352 normal chest radiographs from two institutions. Three thoracic radiolog...

Descripción completa

Detalles Bibliográficos
Publicado en:European Radiology Vol. 30; no. 9; pp. 4943 - 4952
Autores principales: Kim, Young-Gon, Lee, Sang Min, Lee, Kyung Hee, Jang, Ryoungwoo, Seo, Joon Beom, Kim, Namkug
Formato: research Journal Article
Publicado: Springer Nature Sep2020
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=145263165&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 145263165
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        09387994
        NPH
      jtl: European Radiology
      issn: 09387994
      maglogo: N
    pubinfo:
      dt: Sep2020
      vid: 30
      iid: 9
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        145263165
        143913145
        145263165
        NLM32350657
        145263165
        10.1007/s00330-020-06892-9
        NLM32350657
        145263165
      ppf: 4943
      ppct: 9
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: Optimal matrix size of chest radiographs for computer-aided detection on lung nodule or mass with deep learning.
      aug:
        au:
          Kim, Young-Gon
          Lee, Sang Min
          Lee, Kyung Hee
          Jang, Ryoungwoo
          Seo, Joon Beom
          Kim, Namkug
        affil: Department of Biomedical Engineering, Asan Institute of Life Science, University of Ulsan College of Medicine, Asan Medical Center, Seoul, South Korea
      sug:
        subj:
          Precancerous Conditions Diagnosis
          Solitary Pulmonary Nodule Diagnosis
          Radiographic Image Interpretation, Computer-Assisted Methods
          Radiography, Thoracic Methods
          Lung Neoplasms Diagnosis
          Lung
          Aged
          Radiography
          Human
          Middle Age
          Male
          Retrospective Design
          Diagnosis, Computer Assisted
          Female
          Validation Studies
          Comparative Studies
          Evaluation Research
          Multicenter Studies
          Funding Source
          Aged: 65+ years
          Middle Aged: 45-64 years
          Male
          Female
      ab: Objectives: To investigate the optimal input matrix size for deep learning-based computer-aided detection (CAD) of nodules and masses on chest radiographs.Methods: We retrospectively collected 2088 abnormal (nodule/mass) and 352 normal chest radiographs from two institutions. Three thoracic radiologists drew 2758 abnormalities regions. A total of 1736 abnormal chest radiographs were used for training and tuning convolutional neural networks (CNNs). The remaining 352 abnormal and 352 normal chest radiographs were used as a test set. Two CNNs (Mask R-CNN and RetinaNet) were selected to validate the effects of the squared different matrix size of chest radiograph (256, 448, 896, 1344, and 1792). For comparison, figure of merit (FOM) of jackknife free-response receiver operating curve and sensitivity were obtained.Results: In Mask R-CNN, matrix size 896 and 1344 achieved significantly higher FOM (0.869 and 0.856, respectively) for detecting abnormalities than 256, 448, and 1792 (0.667-0.820) (p < 0.05). In RetinaNet, matrix size 896 was significantly higher FOM (0.906) than others (0.329-0.832) (p < 0.05). For sensitivity of abnormalities, there was a tendency to increase sensitivity when lesion size increases. For small nodules (< 10 mm), the sensitivities were 0.418 and 0.409, whereas the sensitivities were 0.937 and 0.956 for masses. Matrix size 896 and 1344 in Mask R-CNN and matrix size 896 in RetinaNet showed significantly higher sensitivity than others (p < 0.05).Conclusions: Matrix size 896 had the highest performance for various sizes of abnormalities using different CNNs. The optimal matrix size of chest radiograph could improve CAD performance without additional training data.Key Points: • Input matrix size significantly affected the performance of a deep learning-based CAD for detection of nodules or masses on chest radiographs. • The matrix size 896 showed the best performance in two different CNN detection models. • The optimal matrix size of chest radiographs could enhance CAD performance without additional training data.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N