Improved cell segmentation using deep learning in label-free optical microscopy images

by Ayda Fıtrıye Aktaş | Oct 11, 2021
Informatics Institute faculty member Behçet Uğur Töreyin coauthored paper titled 'Improved cell segmentation using deep learning in label-free optical microscopy images' has been published in 'Turkish Journal of Electrical Engineering & Computer Sciences'.
Informatics Institute faculty member Behçet Uğur Töreyin coauthored paper titled 'Improved cell segmentation using deep learning in label-free optical microscopy images' has been published in 'Turkish Journal of Electrical Engineering & Computer Sciences'. 

DOI: 10.3906/elk-2105-244 (This number will become active after the manuscript has been selected for inclusion in an issue.)


The recently popular deep neural networks (DNNs) have a significant effect on the improvement of seg- mentation 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 us- ing 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.
    Improved Cell Segmentation-1

    İTÜ Informatics Institute


    ITU Informatics Institute provides graduate-level education and research in applied informatics, computer sciences, computational science and engineering, communication systems under the following programs.

    Faculty members and students conduct research supported by national and international organızatıons in the fields of electromagnetic fields, communication systems/regulations, computational materials design, computational chemistry/biology, cryptography, signal/data processing/visualization, big data management, climate and ocean sciences, 

    • List of Most Influential Scientists; Associate Professor. B. Uğur Töreyin (article by Dr. John PA Ioannidis, K. W. Boyack and J. Baas published in the journal PLOS Biology)
    • Beltus Nkwawir Wiysobunri, the best project award in the Science category, in the 2020 International Students Project Competition
    • Argenit company, of which Dr. Abdulkerim Çapar is among the founding partners, received the "National-International Supports" First Prize of ITU ARI Teknokent.
    • TÜBİTAK 2242 University Students Project Competition in Priority Areas: Istanbul region first place - Ahmet Burak Özyurt
    • Best Presentation Award at ICAT'18 Conference: Sena Efsun Cebeci, 2018
    • Tubitak Incentive Award; 2016 Assoc. Prof. Adem Tekin
    • “Technical Paper” and “Willis H. Carrier” Award by the American Heating, Cooling and Air Conditioning Association; 2016 Assist. Prof. Dr. H. Salih Erden
    • Science Heroes Association Young Scientist of the Year Award; 2016 Assoc. B. Uğur Töreyin Best Poster Award at PRACEdays 2016 conference; Samet Demir
    • ITU Most Successful Thesis Award; 2016 Hatice Gokcan

    There is also a High Performance Computing Laboratory established with the support of the State Planning Organization within the Institute.