Contact bio photo

Contact

Twitter   G. Scholar LinkedIn Github e-Mail

Publications & Talks

You can also browse my Google Scholar profile.

Journal Publications

  • C. Isil, K. de Haan, Z. Gorocs, H. Ceylan Koydemir, S. Peterman, D. Baum, F. Song, T. Skandakumar, E. Gumustekin, and A. Ozcan
    Phenotypic analysis of microalgae populations using label-free imaging flow cytometry and deep learning
    ACS Photonics, 2021.
    [BibTeX] [PDF] 

    @article{Isil:21,
author = {Işıl, Çaǧatay and de Haan, Kevin and Göröcs, Zoltán and Koydemir, Hatice Ceylan and Peterman, Spencer and Baum, David and Song, Fang and Skandakumar, Thamira and Gumustekin, Esin and Ozcan, Aydogan},
title = {Phenotypic Analysis of Microalgae Populations Using Label-Free Imaging Flow Cytometry and Deep Learning},
journal = {ACS Photonics},
volume = {8},
number = {4},
pages = {1232-1242},
year = {2021},
doi = {10.1021/acsphotonics.1c00220},
URL = {https://doi.org/10.1021/acsphotonics.1c00220},
eprint = {https://doi.org/10.1021/acsphotonics.1c00220}
}

  • C. Isil, F. S. Oktem, and A. Koc
    Deep iterative reconstruction for phase retrieval
    Applied Optics, 2019.
    [BibTeX] [PDF] 

    @article{Isil:19,
author = {\c{C}a\u{g}atay I\c{s}{i}l and Figen S. Oktem and Aykut Ko\c{c}},
journal = {Applied Optics},
keywords = {Image quality; Inverse problems; Medical image processing; Phase retrieval; Scanning electron microscopy; Stochastic gradient descent},
number = {20},
pages = {5422--5431},
publisher = {OSA},
title = {Deep iterative reconstruction for phase retrieval},
volume = {58},
month = {Jul},
year = {2019},
url = {http://ao.osa.org/abstract.cfm?URI=ao-58-20-5422},
doi = {10.1364/AO.58.005422},
abstract = {The classical phase retrieval problem is the recovery of a constrained image from the magnitude of its Fourier transform. Although there are several well-known phase retrieval algorithms, including the hybrid input-output (HIO) method, the reconstruction performance is generally sensitive to initialization and measurement noise. Recently, deep neural networks (DNNs) have been shown to provide state-of-the-art performance in solving several inverse problems such as denoising, deconvolution, and superresolution. In this work, we develop a phase retrieval algorithm that utilizes two DNNs together with the model-based HIO method. First, a DNN is trained to remove the HIO artifacts, and is used iteratively with the HIO method to improve the reconstructions. After this iterative phase, a second DNN is trained to remove the remaining artifacts. Numerical results demonstrate the effectiveness of our approach, which has little additional computational cost compared to the HIO method. Our approach not only achieves state-of-the-art reconstruction performance but also is more robust to different initialization and noise levels.},
}

  • C. Isil, M. Yorulmaz, B. Solmaz, A. B. Turhan, C. Yurdakul, S. Unlu, E. Ozbay, and A. Koc
    Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders
    Applied Optics, 2018.
    [BibTeX] [PDF] 

    @article{icsil2018resolution,
  title={Resolution enhancement of wide-field interferometric microscopy by coupled deep autoencoders},
  author={I{\c{s}}il, {\c{C}}a{\u{g}}atay and Yorulmaz, Mustafa and Solmaz, Berkan and Turhan, Adil Burak and Yurdakul, Celalettin and {\"U}nl{\"u}, Selim and Ozbay, Ekmel and Ko{\c{c}}, Aykut},
  journal={Applied optics},
  volume={57},
  number={10},
  pages={2545--2552},
  year={2018},
  publisher={Optical Society of America}
}

Conference Talks

  • C. Isil, K. de Haan, H. Ceylan Koydemir, Z. Gorocs, D. Baum, F. Song, T. Skandakumar, E. Gumustekin, and A. Ozcan
    Label-free analysis of micro-algae populations using a high-throughput holographic imaging flow cytometer and deep learning
    Label-free Biomedical Imaging and Sensing, 2021.
    [BibTeX] [PDF] 

    @inproceedings{Isil21_spie,
author = {Cagatay Isil and Kevin De Haan and Hatice Ceylan Koydemir and Zolt{\'a}n G{\"o}r{\"o}cs and David Baum and Fang Song and Thamira Skandakumar and Esin Gumustekin and Aydogan Ozcan},
title = ,
volume = {11655},
booktitle = {Label-free Biomedical Imaging and Sensing (LBIS) 2021},
editor = {Natan T. Shaked and Oliver Hayden},
organization = {International Society for Optics and Photonics},
publisher = {SPIE},
pages = {116550B},
keywords = {deep learning microscopy, lensfree microscopy, computational cytometry},
year = {2021},
doi = {10.1117/12.2579674},
URL = {https://doi.org/10.1117/12.2579674}
}

  • C. Isil, K. de Haan, Z. Gorocs, H. Ceylan Koydemir, S. Peterman, D. Baum, F. Song, T. Skandakumar, E. Gumustekin, and A. Ozcan
    Label-free imaging flow cytometry for phenotypic analysis of microalgae populations using deep learning
    Frontiers in Optics + Laser Science, 2021.
    [BibTeX] [PDF] 

    @inproceedings{Isil21_Osa,
author = {\c{C}a\u{g}atay I\c{s}{i}l and Kevin de Haan and Zolt\'{a}n Gӧrӧcs and Hatice Ceylan Koydemir and Spencer Peterman and David Baum and Fang Song and Thamira Skandakumar and Esin Gumustekin and Aydogan Ozcan},
booktitle = {Frontiers in Optics $+$ Laser Science 2021},
journal = {Frontiers in Optics $+$ Laser Science 2021},
keywords = {Analytical techniques; Copper; Cytometry; Feature extraction; High throughput optics; Spatial resolution},
pages = {FM3D.4},
publisher = {Optica Publishing Group},
title = {Label-free imaging flow cytometry for phenotypic analysis of microalgae populations using deep learning},
year = {2021},
url = {http://opg.optica.org/abstract.cfm?URI=FiO-2021-FM3D.4},
doi = {10.1364/FIO.2021.FM3D.4},
abstract = {We report a field-portable and high-throughput imaging flow-cytometer to perform label-free phenotypic analysis of microalgae populations by extracting and processing the spatial and spectral features of their reconstructed holographic images using deep learning.},
}

  • C. Isil and F. S. Oktem
    Model-based phase retrieval with deep denoiser prior
    Computational Optical Sensing and Imaging, 2020.
    [BibTeX] [PDF] 

    @inproceedings{Isil:20,
author = {\c{C}a\u{g}atay I\c{s}{i}l and Figen S. Oktem},
booktitle = {Imaging and Applied Optics Congress},
journal = {Imaging and Applied Optics Congress},
keywords = {Algorithms; Fourier transforms; Image quality; Inverse problems; Phase retrieval; Ptychography},
pages = {CF2C.5},
publisher = {Optica Publishing Group},
title = {Model-based Phase Retrieval with Deep Denoiser Prior},
year = {2020},
url = {http://opg.optica.org/abstract.cfm?URI=COSI-2020-CF2C.5},
doi = {10.1364/COSI.2020.CF2C.5},
abstract = {We develop a novel phase-retrieval algorithm with deep denoiser prior. The approach incorporates learning-based prior to the hybrid input-output method through plug- and-play regularization. Results demonstrate the state-of-the-art performance of our approach and its computational efficiency.},
}

  • C. Isil, F. S. Oktem, and A. Koc
    Deep learning-based hybrid approach for phase retrieval
    Computational Optical Sensing and Imaging, 2018.
    [BibTeX] [PDF] 

    @inproceedings{Isil:19,
author = {\c{C}}a\u{g}atay I\c{s}il and Figen S. Oktem and Aykut Ko\c{c}},
booktitle = {Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP)},
journal = {Imaging and Applied Optics 2019 (COSI, IS, MATH, pcAOP)},
keywords = {Algorithms; Fourier transforms; Inverse problems; Neural networks; Numerical simulation; Phase retrieval},
pages = {CTh2C.5},
publisher = {Optical Society of America},
title = {Deep Learning-Based Hybrid Approach for Phase Retrieval},
year = {2019},
url = {http://www.osapublishing.org/abstract.cfm?URI=COSI-2019-CTh2C.5},
doi = {10.1364/COSI.2019.CTh2C.5},
abstract = {We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.},
}

  • C. Isil and F. S. Oktem
    A phase-space approach to diffraction-limited resolution
    Adaptive Optics: Analysis, Methods & Systems, 2018.
    [BibTeX] [PDF] 

    @inproceedings{Isil18_Osa,
author = {\c{C}a\u{g}atay I\c{s}{i}l and Figen S. Oktem},
booktitle = {Imaging and Applied Optics 2018 (3D, AO, AIO, COSI, DH, IS, LACSEA, LS\&C, MATH, pcAOP)},
journal = {Imaging and Applied Optics 2018 (3D, AO, AIO, COSI, DH, IS, LACSEA, LS\&C, MATH, pcAOP)},
keywords = {Diffraction limit; Light propagation; Optical design; Optical elements; Refractive index; Spatial frequency},
pages = {JM4A.32},
publisher = {Optical Society of America},
title = {A Phase-Space Approach to Diffraction-Limited Resolution},
year = {2018},
url = {http://www.osapublishing.org/abstract.cfm?URI=AOMS-2018-JM4A.32},
abstract = {We show, using a phase-space approach, how to determine the diffraction-limited resolution for imaging systems with multiple diffracting apertures. A microscope objective is analyzed using the developed approach, and results are compared with the known technical specifications of the inspected optical system.},
}

  • C. Isil, B. Solmaz, and A. Koc
    Variational autoencoders with triplet loss for representation learning
    Signal Processing and Communications Applications Conference (SIU), 2018.
    [BibTeX] [PDF] 

    @INPROCEEDINGS{cisil2018_ae, 
author={Ç. Işıl and B. Solmaz and A. Koç}, 
booktitle={2018 26th Signal Processing and Communications Applications Conference (SIU)}, 
title={Variational autoencoders with triplet loss for representation learning}, 
year={2018}, 
volume={}, 
number={}, 
pages={1-4}, 
keywords={data visualisation;learning (artificial intelligence);pattern clustering;representation learning;deep learning;variational autoencoder clustering performance improvement;Dogs;Support vector machines;Conferences;Machine learning;Computer vision;Face recognition;deep learning;autoencoders;representation learning;triplet loss}, 
doi={10.1109/SIU.2018.8404227}, 
ISSN={}, 
month={May},}

  • M. Yorulmaz, C. Isil, E. Seymour, C. Yurdakul, B. Solmaz, A. Koc, and S. Unlu
    Single-particle imaging for biosensor applications
    Emerging Imaging and Sensing Technologies for Security and Defence II, 2017.
    [BibTeX] [PDF] 

    @proceeding{yorulmaz20107single,
author = { Mustafa  Yorulmaz,Cagatay  Isil,Elif  Seymour,Celalettin  Yurdakul,Berkan  Solmaz,Aykut  Koc,M. Selim  Ünlü},
title = {Single-particle imaging for biosensor applications},
journal = {Proc.SPIE},
volume = {10438},
number = {},
pages = {10438 - 10438 - 8},
year = {2017},
doi = {10.1117/12.2279005},
URL = {https://doi.org/10.1117/12.2279005},
eprint = {}
}