Yaşam ve Doğa Bilimleri Fakültesi

Permanent URI for this communityhttps://hdl.handle.net/20.500.12573/39

Browse

Browsing Yaşam ve Doğa Bilimleri Fakültesi by Author "0000-0002-0947-6166"

Filter results by typing the first few letters
Now showing 1 - 3 of 3
  • Thumbnail Image
    Article
    Deep learning based semantic segmentation and quantification for MRD biochip images
    (ELSEVIER SCI LTD, 2022) Çelebi, Fatma; Tasdemir, Kasim; Icoz, Kutay; 0000-0002-0947-6166; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Çelebi, Fatma; Tasdemir, Kasim; Icoz, Kutay
    Microfluidic platforms offer prominent advantages for the early detection of cancer and monitoring the patient response to therapy. Numerous microfluidic platforms have been developed for capturing and quantifying the tumor cells integrating several readout methods. Earlier, we have developed a microfluidic platform (MRD Biochip) to capture and quantify leukemia cells. This is the first study which employs a deep learning-based segmentation to the MRD Biochip images consisting of leukemic cells, immunomagnetic beads and micropads. Implementing deep learning algorithms has two main contributions; firstly, the quantification performance of the readout method is improved for the unbalanced dataset. Secondly, unlike the previous classical computer visionbased method, it does not require any manual tuning of the parameters which resulted in a more generalized model against variations of objects in the image in terms of size, color, and noise. As a result of these benefits, the proposed system is promising for providing real time analysis for microfluidic systems. Moreover, we compare different deep learning based semantic segmentation algorithms on the image dataset which are acquired from the real patient samples using a bright-field microscopy. Without cell staining, hyper-parameter optimized, and modified U-Net semantic segmentation algorithm yields 98.7% global accuracy, 86.1% mean IoU, 92.2% mean precision, 92.2% mean recall and 92.2% mean F-1 score measure on the patient dataset. After segmentation, quantification result yields 89% average precision, 97% average recall on test images. By applying the deep learning algorithms, we are able to improve our previous results that employed conventional computer vision methods.
  • Thumbnail Image
    Article
    Immunomagnetic separation of B type acute lymphoblastic leukemia cells from bone marrow with flow cytometry validation and microfluidic chip measurements
    (TAYLOR & FRANCIS INC, 530 WALNUT STREET, STE 850, PHILADELPHIA, PA 19106 USA, 2020) Icoz, Kutay; Eken, Ahmet; Cinar, Suzan; Murat, Aysegul; Ozcan, Servet; Unal, Ekrem; Deniz, Gunnur; 0000-0002-8330-7010; 0000-0002-0947-6166; AGÜ, Yaşam ve Doğa Bilimleri Fakültesi, Biyomühendislik Bölümü
    In order to detect the blast cells from bone marrow of patients, one strategy is to first isolate the cells using immunomagnetic beads. The aim of this study was to report the experimental results of the immunomagnetic separation efficiency of the blast cells from bone marrow of pediatric leukemia patients. To test the efficiency of immunomagnetic separation, flow cytometry measurements at critical steps were performed. We here reported 94.5% capture efficiency for CD10 nano beads. Patients samples were also analyzed with a microfluidic chip to test the feasibility for further developments.
  • Thumbnail Image
    Article
    Microfluidic Devices: A New Paradigm in Toxicity Studies
    (Hacettepe Üniversitesi, 2020) Yiğit, Fatma Esra; İçöz, Kutay; Boşgelmez, İpek; 0000-0002-0947-6166; AGÜ, Yaşam ve Doğa Bilimleri Fakültesi, Biyomühendislik Bölümü; İçöz, Kutay
    In recent years, great emphasis has been placed on non-animal toxicological methods (e.g. in vitro models, in silico or −omicsdata) as alternative strategies to reduce animal-testing, in line with the 3R (Replacement, Reduction, and Refinement) principle.These methods help in the rapid and accurate estimation of preclinical efficacy and safety associated with discovery of new drugs,and reduction of failure rates in clinical trials. Currently, the in vitro studies have been in a transformation or replacement fromtwo-dimensional (2D) cell cultures to three-dimensional (3D) cell cultures that can mimic the physiology of tissues, organs, andorganisms.In this context, organ-on-a-chip systems have been developed by integration of 3D culture models with emerging microfluidictechnologies. Since the organ-on-a-chip systems provide a good understanding of dose-response and toxicity mechanisms in drugresearch and development (R&D), the impact of xenobiotics on the human body can be predicted in a satisfactory level. Besides,these systems may support assessment of pharmacokinetic-pharmacodynamic parameters as well as detection of drug resistance.Models can be generated as “disease-models-on-a-chip” or with healthy cells to the evaluate response to xenobiotic under test.In this review, we will focus on the microfluidic systems being used in organ-on-a-chip systems and emphasize their potential fortoxicity studies in which micro-environments of examples including liver, kidney, brain, lung, heart, and intestines and their physiologicalproperties as reflected to organ-on-a-chip models.