Comparative Study of Deep Transfer Learning Models for Semantic Segmentation of Human Mesenchymal Stem Cell Micrographs.

Journal: International journal of molecular sciences
PMID:

Abstract

The aim of this study is to conduct a comparative assessment of the effectiveness of neural network models-U-Net, DeepLabV3+, SegNet and Mask R-CNN-for the semantic segmentation of micrographs of human mesenchymal stem cells (MSCs). A dataset of 320 cell micrographs annotated by cell biology experts was created. The models were trained using a transfer learning method based on ImageNet pre-trained weights. As a result, the U-Net model demonstrated the best segmentation accuracy according to the metrics of the Dice coefficient (0.876) and the Jaccard index (0.781). The DeepLabV3+ and Mask R-CNN models also showed high performance, although slightly lower than U-Net, while SegNet exhibited the least accurate results. The obtained data indicate that the U-Net model is the most suitable for automating the segmentation of MSC micrographs and can be recommended for use in biomedical laboratories to streamline the routine analysis of cell cultures.

Authors

  • Maksim Solopov
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
  • Elizaveta Chechekhina
    Department of Biochemistry and Regenerative Biomedicine, Faculty of Medicine, Lomonosov Moscow State University, Moscow, Russia.
  • Anna Kavelina
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
  • Gulnara Akopian
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
  • Viktor Turchin
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
  • Andrey Popandopulo
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
  • Dmitry Filimonov
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.
  • Roman Ishchenko
    V.K. Gusak Institute of Emergency and Reconstructive Surgery, 283045 Donetsk, Russia.