Molecular Biology and Genetics / Moleküler Biyoloji ve Genetik
Permanent URI for this collectionhttps://hdl.handle.net/11147/9
Browse
3 results
Search Results
Article Citation - WoS: 3Citation - Scopus: 6Improved 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, DevrimThe 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.Article Citation - WoS: 5Citation - Scopus: 6Micrometer Scale Spacings Between Fibronectin Nanodots Regulate Cell Morphology and Focal Adhesions(IOP Publishing Ltd., 2014) Horzum, Utku; Özdil, Berrin; Pesen Okvur, DevrimCell adhesion to extracellular matrix is an important process for both health and disease states. Surface protein patterns that are topographically flat, and do not introduce other chemical, topographical or rigidity related functionality and, more importantly, that mimic the organization of the in vivo extracellular matrix are desired. Previous work showed that vinculin and cytoskeletal organization are modulated by size and shape of surface nanopatterns. However, quantitative analysis on cell morphology and focal adhesions as a function of micrometer scale spacings of FN nanopatterns was absent. Here, electron beam lithography was used to pattern fibronectin nanodots with micrometer scale spacings on a Kcasein background on indium tin oxide coated glass which, unlike silicon, is transparent and thus suitable for many light microscopy techniques. Exposure times were significantly reduced using the line exposure mode with micrometer scale step sizes. Micrometer scale spacings of 2, 4 and 8 m between fibronectin nanodots proved to modulate cell adhesion through modification of cell area, focal adhesion number, size and circularity. Overall, cell behavior was shown to shift at the apparent threshold of 4 m spacing. The findings presented here offer exciting new opportunities for cell biology research.Article Citation - WoS: 5Citation - Scopus: 5Invadopodia: Proteolytic Feet of Cancer Cells(TUBITAK, 2014) Batı, Gizem; Pesen Okvur, DevrimThe leading cause of death in cancer patients is metastasis. Invasion is an integral part of metastasis and is carried out by proteolytic structures called invadopodia at the cellular level. In this introductory review, we start by evaluating the definition of invadopodia. While presenting the upstream signaling events involved, we integrate current models on invadopodia. In addition, we discuss the significance of invadopodia in 2D and 3D and in vivo. We finally point out technical challenges and conclude with open questions in the field. © TÜBİTAK.