1 Ocak 2021 Dergi makalesi Açık Erişim

Alis, Deniz; Yergin, Mert; Alis, Ceren; Topel, Cagdas; Asmakutlu, Ozan; Bagcilar, Omer; Senli, Yeseren Deniz; Ustundag, Ahmet; Salt, Vefa; Dogan, Sebahat Nacar; Velioglu, Murat; Selcuk, Hakan Hatem; Kara, Batuhan; Oksuz, Ilkay; Kizilkilic, Osman; Karaarslan, Ercan

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 235848, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Acibadem Mehmet Ali Aydinlar Univ, Dept Radiol, Sch Med, Istanbul, Turkey", 
      "name": "Alis, Deniz"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Bahcesehir Univ, Dept Software Engn & Appl Sci, Istanbul, Turkey", 
      "name": "Yergin, Mert"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Neurol Dept, Istanbul, Turkey", 
      "name": "Alis, Ceren"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Mehmet Akif Ersoy Thorac & Cardiovasc Su, Dept Radiol, Halkali Istanbul, Turkey", 
      "name": "Topel, Cagdas"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Mehmet Akif Ersoy Thorac & Cardiovasc Su, Dept Radiol, Halkali Istanbul, Turkey", 
      "name": "Asmakutlu, Ozan"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Silivri State Hosp, Radiol Dept, Istanbul, Turkey", 
      "name": "Bagcilar, Omer"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Radiol Dept, Istanbul, Turkey", 
      "name": "Senli, Yeseren Deniz"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Radiol Dept, Istanbul, Turkey", 
      "name": "Ustundag, Ahmet"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Radiol Dept, Istanbul, Turkey", 
      "name": "Salt, Vefa"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Gaziosmanpasa Training & Res Hosp, Radiol Dept, Istanbul, Turkey", 
      "name": "Dogan, Sebahat Nacar"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Fatih Sultan Mehmet Training & Res Hosp, Radiol Dept, Istanbul, Turkey", 
      "name": "Velioglu, Murat"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Bakirkoy Sadi Konuk Training & Res Hosp, Radiol Dept, Istanbul, Turkey", 
      "name": "Selcuk, Hakan Hatem"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Bakirkoy Sadi Konuk Training & Res Hosp, Radiol Dept, Istanbul, Turkey", 
      "name": "Kara, Batuhan"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Tech Univ, Dept Software Engn & Appl Sci, Istanbul, Turkey", 
      "name": "Oksuz, Ilkay"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Radiol Dept, Istanbul, Turkey", 
      "name": "Kizilkilic, Osman"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Acibadem Mehmet Ali Aydinlar Univ, Dept Radiol, Sch Med, Istanbul, Turkey", 
      "name": "Karaarslan, Ercan"
    }
  ], 
  "datePublished": "2021-01-01", 
  "description": "There is little evidence on the applicability of deep learning (DL) in the segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n=2986) and B (n=3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets, and six neuroradiologists created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B. The models subsequently fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist's performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that the inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learning; thereby, their clinical applicability and generalizability could be improved.", 
  "headline": "Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study", 
  "identifier": 235848, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study", 
  "url": "https://aperta.ulakbim.gov.tr/record/235848"
}