Recep Tayyip Erdoğan Üniversitesi Kurumsal Akademik Arşivi
DSpace@RTEÜ, Recep Tayyip Erdoğan Üniversitesi tarafından doğrudan ve dolaylı olarak yayınlanan; kitap, makale, tez, bildiri, rapor, araştırma verisi gibi tüm akademik kaynakları uluslararası standartlarda dijital ortamda depolar, Üniversitenin akademik performansını izlemeye aracılık eder, kaynakları uzun süreli saklar ve yayınların etkisini artırmak için telif haklarına uygun olarak Açık Erişime sunar.
Güncel Gönderiler
Breast ultrasound images for segmentation and classification using multi-task U-Net
(Nature Publishing, 2026) Anitha, Maddhi; Prasad, CH Rajendra; Awotunde, Joseph Bamidele; Adeniyi, Abidemi Emmanuel; Aroba, Oluwasegun Julius
Breast ultrasound imaging is widely used for the early detection of breast cancer due to its accessibility and effectiveness, particularly in dense breast tissues. However, its diagnostic performance is often affected by operator dependency, speckle noise, low contrast, and variability in data quality. Although deep learning methods have shown promise in automated tumor segmentation and classification, their clinical applicability remains limited due to challenges such as small and imbalanced datasets, inconsistent annotations, and the lack of integrated learning strategies. In this work, we propose a Multi-Task U-Net framework that jointly performs lesion segmentation and tumor classification by leveraging shared feature representations. The proposed method incorporates a deterministic oversampling strategy for handling class imbalance, a prediction-refinement module to ensure consistency between segmentation and classification outputs, and an attention-guided feature learning mechanism to enhance lesion localization. Additionally, a curated version of the BUSI dataset is constructed by removing duplicate and inconsistent samples to ensure reliable evaluation. The proposed model achieves a Dice score of up to 0.81 in comparative evaluation, along with classification accuracy of up to 0.96-0.98, demonstrating improved performance over baseline methods. The consistent performance across both segmentation and classification tasks indicates good generalization capability despite dataset limitations. Finally, the proposed multi-task framework provides an effective and reliable solution for automated breast cancer detection in ultrasound images and shows strong potential for clinical application.
Targeting SARS-CoV-2 main protease (3CLpro) with Paeonia-derived phytochemicals
(Springer, 2026) Sandallı, Cemal; Bostancıoğlu, Safiye Merve; Aytül, Sandallı; Turumtay, Emine Akyüz; Almohazey, Dana; Alsaeed, Moneerah; Tombuloğlu, Hüseyin
Coronavirus Disease 19 (COVID-19), caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), stimulated intensive drug-development efforts throughout the world. As COVID-19 has become endemic in many regions of the world, phytochemicals used in ethnomedicine may have utility in the prevention or treatment of COVID-19. Here, we employed machine learning/deep learning drug discovery tools to evaluate compounds previously identified in roots of plants of the Paeonia genus for their drug-like properties and potential to inhibit 3CLpro, the main protease of SARS-CoV2. Our results identify Paeonia-derived compounds that have favorable drug-like properties and are predicted to have a high binding affinity for 3CLpro. Molecular dynamics simulations supported the binding affinity of Paeonia-derived compounds for 3CLpro. We validated these in silico computational results by experimentally determining the 50% inhibitory concentration (IC50) of two Paeonia-derived compounds, paeoniflorigenone and 3-O-methylquercetin, using purified 3CLpro with baicalein as a control. The IC50 values for paeoniflorigenone, 3-O-methylquercetin and baicalein were 9.33 µM, 43.94 and 43.85 µM, respectively. Root extracts from five Paeonia species were found to have minimal cytotoxicity against three different human cell types. Our results represent a proof-of-concept study demonstrating that in silico techniques, including machine and deep learning methods, can be used to identify phytochemicals as starting points for the discovery of antiviral compounds against SARS-CoV-2.
Structural, electronic, mechanical, optical, and thermodynamic properties of novel quaternary oxychalcogenide LaCuTeO for optoelectronic applications
(Nature Publishing, 2026) Elkenany, Elkenany Brens; Ghebouli, B.; Yaylacı, Murat; Albargi, Hasan B.; Smerat, Aseel; Dhahri, Ramzi; Abdelghany, A.M.
We present a comprehensive first-principles study of the newly proposed quaternary oxychalcogenide LaCuTeO with tetragonal P4/nmm symmetry, combining ab initio DFT calculations to explore its potential for optoelectronic applications. Using the full-potential linearized augmented plane wave (FP-LAPW) method within the WIEN2k code, we systematically investigated the structural, electronic, elastic, optical, and thermodynamic properties. The optimized lattice parameters are a = b = 4.101 Å and c = 9.062 Å with a bulk modulus of 108.33 GPa, confirming excellent structural stability. Phonon dispersion calculations reveal dynamic stability with no imaginary frequencies. Electronic band structure calculations using LDA and LDA + U (U = 6 eV) predict a direct bandgap of 0.999 eV and 1.324 eV, respectively, suitable for visible-to-near-infrared optoelectronic and photovoltaic applications. The elastic constants satisfy all mechanical stability criteria with a universal anisotropy index of 4.58 and Vickers hardness of 24.70 GPa (Chen model), indicating significant mechanical resilience. Optical properties demonstrate strong absorption in the visible-UV range with refractive indices of 3.253 (nxx) and 3.061 (nzz) at zero frequency, suggesting promising applications in photovoltaic and photocatalytic devices. Thermodynamic analysis shows heat capacity approaching the Dulong-Petit limit (99.45 J/mol·K) at high temperatures. Furthermore, the calculated electronic and optical characteristics reveal favorable carrier transport properties and strong light-matter interaction, highlighting the suitability of LaCuTeO for efficient solar energy harvesting and optoelectronic device performance. Our comprehensive computational study establishes LaCuTeO as a promising multifunctional material for next-generation optoelectronic technologies.
Excessive use and unjustified combination of inhaled and nebulized corticosteroids in stable COPD: preliminary results
(Oxford University Press, 2026) Olcay, S.; Ercelik, M.; Marim, F.; Altin, S.; Onyilmaz, T.; Karadoğan, Dilek
.....
The possibility of rationality in the gap as a critique of instrumental rationality
(İlahiyat Bilimleri Araştırma Vakfı, 2026) Karaköse, Ömer Faruk; Türer, Celal
This study explores the possibility of rationality in the gap as a critical approach that reveals the limits of instrumental rationality. Instrumental rationality, as the dominant model explaining human action through the consistent coordination of beliefs and desires, defines rational behavior by the correspondence between means and ends. However, this approach overlooks the ever-present possibility of "acting otherwise," thereby narrowing the freedom-related dimension of rationality. The tension between determinism and freedom is not merely philosophical but indicates a fundamental problem concerning rational agency. Rationality in the gap is conceptualized as a discontinuous field where action cannot be entirely determined by ends and where both irrationality and deontological obligations intervene. Drawing on Gaston Bachelard's "interval of inaction" (intervalle d'inaction) and John R. Searle's "gap of rational decision," this approach the first systematic attempt to bring together two philosophers from the Continental and analytic traditions around a shared problem. In both thinkers, the "gap" appears as causal discontinuity inaction, uncertainty in decision, and a space of freedom. Within this discontinuity, free choice emerges in the tension between irrationality-arising independently of instrumental reasoning-and deontological obligation-appearing as normative necessity. The main aim of the article is not to present rationality in the gap as an alternative model to instrumental rationality, but rather to initiate a discussion that undermines the conceptual limits of instrumental rationality and allows human action to be rethought beyond these boundaries.
