Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
3 results
Search Results
Article Improved Colorectal Gland Segmentation in Histopathology Images with Adaptive Resizer-Enhanced U-Net Models(Springer Science and Business Media Deutschland GmbH, 2026) Fidan, E.; Gumus, A.Utilizing low-resolution images for computer vision tasks such as classification and segmentation can sometimes hinder the model’s ability to accurately learn essential features. While using high-resolution images and designing compatible models might seem like viable solutions, they are not always feasible due to energy efficiency and graphical computation constraints. Downsizing images for model training and application is an effective approach for improving computational efficiency and optimizing model performance.The bilinear resizing method, commonly employed for this purpose, inherently causes information loss due to its numerical approach, which relies solely on the four nearest pixel values to compute each target pixel. This limitation becomes more pronounced with high-resolution images, where the down sampling process intensifies the loss of critical information. However, recent advancements have introduced adaptive resizer modules, which dynamically adjust image dimensions to better preserve essential features before processing by deep learning models. In this study, an adaptive resizer-based segmentation framework is proposed for the gland segmentation task, which is crucial for accurate disease diagnosis, particularly in cancer analysis. Three distinct encoder-decoder architecture segmentation models are assessed for image segmentation using the Colorectal Adenocarcinoma Gland (CRAG) gland segmentation database. Each architecture was tested separately, employing six different backbone encoders that were pretrained on the ImageNet dataset. The comparative analysis showed that the adaptive resizer improved segmentation performance, increasing the Intersection over Union (IoU) metric by an average of 5.6%. This enhancement raised the lowest IoU from 62% to 70% and the highest to 78%. The code is available on GitHub at https://github.com/miralab-ai/adaptive-resizer-segmentation. © The Author(s) 2026.Article A Machine Learning Framework for Advanced Analytical Detection of CD36 Using Immunosensors Below Limit of Detection(Elsevier Ltd, 2026) Yeke, M.C.; Gelen, S.S.; Fil, H.; Yalcin, M.M.; Gumus, A.; Yazgan, I.; Odaci, D.We introduce a machine learning (ML)-based regression framework for quantitative electrochemical analysis, representing a paradigm shift from traditional univariate methods to a multivariate approach. Conventional analysis is constrained by reducing the entire signal to a single peak current feature to define a linear range and calculate a limit of detection (LOD). In contrast, our methodology treats the Differential Pulse Voltammetry (DPV) curve as time-series data, creating a high-dimensional fingerprint by systematically evaluating multiple data windows with varying widths around the main signal peak to identify the most informative segment. To validate this approach, a biosensor was developed by immobilizing Anti-CD36 antibodies on polydopamine-modified screen-printed carbon electrodes for the detection of CD36, a key protein in metabolism and immunity. Measurements were collected across 12 concentrations, including blank samples, spanning a range of 0 to 25 ng/mL. Following data augmentation, nine different regression models were evaluated, with the top-performing models achieving near-perfect prediction accuracy (R2>0.99) across this entire range. This high accuracy across the full concentration spectrum quantitatively demonstrates the method's ability to operate without relying on traditional concepts like linear range or LOD, enabling reliable detection at ultra-low levels. Furthermore, the immunosensor exhibited high selectivity against common interferents and excellent recovery in human serum. This methodology represents a significant advancement in analytical electrochemistry, providing a transferable approach for enhancing sensitivity in biomarker detection with potential applications in clinical diagnostics and biomedical research. The codes and dataset are made publicly available on GitHub to support further research: https://github.com/miralab-ai/biosensors-AI. © 2026 The Author(s)Article Amino Acid Selection Altered Silver Nanoparticles Morphology and Formation of Silver Oxide Layers(Multidisciplinary Digital Publishing Institute (MDPI), 2025) Bolat, Ş.; Sancak, Z.; Gumus, A.; Yazgan, I.Amino acids are not just monomers of proteins, but they can also carry biological functions. L-cysteine (Cys), L-proline (Pro), L-asparagine (Asn), and L-glutamic acid (Glu) were used to evaluate how different amino acid chemistries alter the morphology and size of the silver nanoparticles (AgNPs) synthesized in the presence of two carbohydrate ligands, which were lactose methoxyaniline (LMA) and galactose 5-aminosalicylic acid (G5AS). UV–vis, infrared (IR), High-Resolution Transmission Electron Microscopy (HR-TEM) and X-ray diffraction (XRD) characterizations revealed that the effect of amino acids on the characteristics of the AgNPs showed dependence on the carbohydrate ligand chemistry. In the case of LMA, AgNPs shifted from aggregates to anisotropic nanoparticles, larger aggregates, and a mixture of anisotropic and 1D nanoparticles in the presence of Cys, Glu, Asn and Pro amino acids, respectively. In contrast to this, the introduction of Cys and Asn caused the formation of cluster-like AgNPs and larger rounded nanoparticles, while G5AS-synthesized AgNPs were multigonal 0D particles. Moreover, Glu and Pro contributed the resistance of silver oxide formation on the particles. Antibacterial characterization showed that LMA_Glu_AgNPs were the most effective ones, while LMA_Cys_AgNPs and G5AS_Cys_AgNPs, which were the smallest AgNPs, did not show any significant antibacterial activity. © 2025 Elsevier B.V., All rights reserved.