Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
4 results
Search Results
Conference Object Detection and Restoration Pipeline for Phase Contrast Microscopy Time Series Images(IEEE, 2022) Iheme, Leonardo O.; Uçar, Mahmut; Önal, Sevgi; Yalçın Özuysal, Özden; Pesen Okvur, Devrim; Töreyin, Behçet U.; Ünay, DevrimWe propose a pre-processing pipeline for the de-tection and restoration of distorted frames in phase-contrast microscopy time-series images. The analysis is based on the average intensity values of the frames within any given time- series image. The extent of the correction of intensity variation in frames is determined by the normalization of the difference between the current frame's average intensity and the median of average intensity of all frames. Our restoration algorithm preserves regional trans-passing pixels, does not cause new distortions, and increases the histogram similarity between the distorted and non-distorted frames. The algorithm was validated on 15,395 time-series image frames from 27 experiments and the results were found to be visually and quantitatively accurate.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.Conference Object Citation - WoS: 3Citation - Scopus: 4Deep Learning Based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images(IEEE, 2020) Ayanzadeh, Aydın; Yalçın Özuysal, Özden; Okvur, Devrim Pesen; Önal, Sevgi; Töreyin, Behçet Uğur; Ünay, DevrimThe segmentation of cells is necessary for biologists in the morphological statistics for quantitative and qualitative analysis in Phase-contrast Microscopy (PCM) images. In this paper, we address the cell segmentation problem in PCM images. Deep Neural Networks (DNNs) commonly is initialized with weights from a network pre-trained on a large annotated data set like ImageNet have superior performance than those trained from scratch on a small dataset. Here, we demonstrate how encoder-decoder type architectures such as U-Net and Feature Pyramid Network (FPN) can be improved by an alternative encoder which pre-trained on the ImageNet dataset. In particular, our experimental results confirm that the image descriptors from ResNet-18 are highly effective in accurate prediction of the cell boundary and have higher Intersection over Union (IoU) in comparison to the classical U-Net and require fewer training epochs.Conference Object Citation - WoS: 1Citation - Scopus: 6Faz Kontrast Optik Mikroskopi Zaman Serisi Görüntülerinde Hücrelerin Otomatik Bölütlenmesi(Institute of Electrical and Electronics Engineers Inc., 2019) Binici, Rıfkı Can; Şahin, Umut; Ayanzadeh, Aydın; Töreyin, Behçet Uğur; Önal, Sevgi; Okvur, Devrim Pesen; Yalçın Özuysal, Özden; Ünay, DevrimFaz kontrast optik mikroskopi hücrelerin canlı ortamlarında zamana bağlı incelenmesi için tercih edilen görüntüleme yöntemidir. Bu yöntem ile elde edilen zaman serisi görüntülerinde hücrelerin bölütlenmesi işi hücre biyolojisi araştırmacılarının çözümüne ihtiyaç duyduğu emek yoğun ve zaman alan bir iştir. Bu çalışmada faz kontrast optik mikroskopi zaman serilerinde hücrelerin otomatik bölütlenmesi için geleneksel görüntü işleme ve derin öğrenme temelli yöntemler önerilmiş ve başarımları elle işaretlenmiş veri kümelerinde nicel olarak ölçülmüştür.