1 Ocak 2021 Dergi makalesi Açık Erişim

Ayanzadeh, Aydin; Ozuysal, Ozden Yalcin; Okvur, Devrim Pesen; Onal, Sevgi; Toreyin, Behcet Ugur; Unay, Devrim

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 237150, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Istanbul Tech Univ, Informat Inst, Istanbul, Turkey", 
      "name": "Ayanzadeh, Aydin"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Izmir Inst Technol, Dept Mol Biol & Genet, Izmir, Turkey", 
      "name": "Ozuysal, Ozden Yalcin"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Izmir Inst Technol, Dept Mol Biol & Genet, Izmir, Turkey", 
      "name": "Okvur, Devrim Pesen"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Izmir Inst Technol, Biotechnol & Bioengn Grad Program, Izmir, Turkey", 
      "name": "Onal, Sevgi"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Tech Univ, Informat Inst, Istanbul, Turkey", 
      "name": "Toreyin, Behcet Ugur"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Izmir Democracy Univ, Dept Elect & Elect Engn, Izmir, Turkey", 
      "name": "Unay, Devrim"
    }
  ], 
  "datePublished": "2021-01-01", 
  "description": "The recently popular deep neural networks (DNNs) have a significant effect on the improvement of segmentation accuracy from various perspectives, including robustness and completeness in comparison to conventional methods. We determined that the naive U-Net has some lacks in specific perspectives and there is high potential for further enhancements on the model. Therefore, we employed some modifications in different folds of the U-Net to overcome this problem. Based on the probable opportunity for improvement, we develop a novel architecture by using an alternative feature extractor in the encoder of U-Net and replacing the plain blocks with residual blocks in the decoder. This alteration makes the model superconvergent yielding improved performance results on two challenging optical microscopy image series: a phase-contrast dataset of our own (MDA-MB-231) and a brightfield dataset from a well-known challenge (DSB2018). We utilized the U-Net with pretrained ResNet-18 as the encoder for the segmentation task. Hence, following the modifications, we redesign a novel skip-connection to reduce the semantic gap between the encoder and the decoder. The proposed skip-connection increases the accuracy of the model on both datasets. The proposed segmentation approach results in Jaccard Index values of 85.0% and 89.2% on the DSB2018 and MDA-MB-231 datasets, respectively. The results reveal that our method achieves competitive results compared to the state-of-the-art approaches and surpasses the performance of baseline approaches.", 
  "headline": "Improved cell segmentation using deep learning in label-free optical microscopy images", 
  "identifier": 237150, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "Improved cell segmentation using deep learning in label-free optical microscopy images", 
  "url": "https://aperta.ulakbim.gov.tr/record/237150"
}