Molecular Biology and Genetics / Moleküler Biyoloji ve Genetik

Permanent URI for this collectionhttps://hdl.handle.net/11147/9

Browse

Filters

2021 - 20232

Settings

Subject: search.filters.subject.Convolutional neural networks

Search Results

Now showing 1 - 2 of 2
  • Book Part
    Citation - Scopus: 1
    Automated Analysis of Phase-Contrast Optical Microscopy Time-Lapse Images: Application To Wound Healing and Cell Motility Assays of Breast Cancer
    (Elsevier, 2023) Erdem, Yusuf Sait; Ayanzadeh, Aydın; Mayalı, Berkay; Balıkçı, Muhammed; Belli, Özge Nur; Uçar, Mahmut; Yalçın Özuysal, Özden; Pesen Okvur, Devrim; Önal, Sevgi; Morani, Kenan; Iheme, Leonardo Obinna; Töreyin, Behçet Uğur
    This chapter describes a workflow for analyzing phase-contrast microscopy (PCM) data from two fundamental types of biomedical assays: assays for cell motility and assays for wound healing. The workflow of the analysis is composed of the methods for acquiring, restoring, segmenting, and quantifying biomedical data. In the literature, there have been separate methods aimed at specific stages of PCM data analysis. Nonetheless, there has never been a complete workflow for all stages of analysis. This work is an innovation that proposes an end-to-end workflow for image pre-processing, deep learning segmentation, tracking, and quantification stages in cell motility and wound healing assay analyses. The findings indicate that domain knowledge can be used to make simple but significant improvements to the results of cutting-edge methods. Furthermore, even for deep learning-based methods, pre-processing is clearly a necessary step in the workflow. © 2023 Elsevier Inc. All rights reserved.
  • Article
    Citation - WoS: 3
    Citation - Scopus: 6
    Improved Cell Segmentation Using Deep Learning in Label-Free Optical Microscopy Images
    (TÜBİTAK - Türkiye Bilimsel ve Teknolojik Araştırma Kurumu, 2021) Ayanzadeh, Aydın; Yalçın Özuysal, Özden; Pesen Okvur, Devrim; Önal, Sevgi; Töreyin, Behçet Uğur; Ünay, Devrim
    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.