Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/7
Browse
2 results
Search Results
Article Comparative Evaluation of Vision Transformers and Convolutional Networks for Breast Ultrasound Image Classification(Open Exploration Publishing Inc, 2026) Naral S.; Cakmak Y.; Pacal I.; Pacal, Ishak; Cakmak, Yigitcan; Naral, SuleymanAim: Interobserver variability continues to limit the consistency of breast ultrasound interpretation. This study compares two Vision Transformer (ViT) models and two Convolutional Neural Network (CNN) models for automated three-class breast ultrasound classification, with a specific focus on the tradeoff between predictive performance and computational efficiency. Methods: Swin Transformer Base and DeiT Base were evaluated alongside InceptionV3 and MobileNetV3 Large using the public Breast Ultrasound Images (BUSI) dataset, which contains 780 images labeled as benign, malignant, and normal. A consistent on-the-fly augmentation pipeline was applied during training to promote robustness and reduce sensitivity to incidental image variations. Results: Swin Transformer Base achieved the highest test accuracy (0.9167) and F1 score (0.8981). MobileNetV3 Large reached an accuracy of 0.8583 with substantially lower computational demand. The efficiency contrast was pronounced, with Swin requiring 30.33 GFLOPs versus 0.43 GFLOPs for MobileNetV3 Large. Conclusions: On this benchmark, ViT models can yield higher classification performance, while lightweight CNNs offer a strong efficiency profile that may better match deployment-constrained settings. These results suggest that model selection should be guided by both predictive accuracy and operational feasibility within the target clinical workflow. © The Author(s) 2026.Article Citation - WoS: 2Citation - Scopus: 3Biological Activities of Etodolac-Based Hydrazone, Thiazolidinone and Triazole Derivatives on Breast Cancer Cell Lines MCF-7 and MDA-MB(Wiley, 2025) Sevinc, Sevgi Kocyigit; Cikla-Suzgun, Pelin; Tiber, Pinar Mega; Kucukguzel, S. Guniz; Orun, Oya; Güniz Küçükgüzel, Ş.In this study, several etodolac-based hydrazone, thiazolidinone, and triazole derivatives that we synthesized and characterized in our earlier research were tested against the hormone-responsive breast cell line MCF-7 and the triple-negative MDA-MB-231, as well as the murine origin fibroblast cell line L-929, at varying doses for their effects on cell viability and toxicity and for their inhibitory activity on cyclooxygenase-2 (COX-2)/prostaglandin E2 (PGE2) formation. Cell viability and apoptosis tests were utilized to assess the anti-cancer potential of etodolac and its derivatives after the cells were exposed to varied concentrations of synthesized compounds for three different time periods. ELISA and Western blot methods were used to detect protein levels. All synthesized compounds demonstrated higher anti-cancer activity at significantly lower doses compared to etodolac (half-maximal inhibitory concentration [IC50] of 0-50 mu M range in derivatives versus 0.5-1 mM range in etodolac). Except for SGK 242, which had a major toxic effect on all cells, the chemicals SGK 206 and SGK 217 had a twice-less impact on control murine L-929 fibroblasts. Similar to proliferation, low concentrations of SGK 206 and SGK 217 (25-50 mu M) significantly induced apoptosis in breast cancer cells but not in normal cells. Additionally, they inhibited COX-2 protein expression at 50 mu M, and SGK 206 inhibited PGE2 release more effectively than etodolac in cancer cells. The results of this study suggest that, in comparison to a healthy control group, the thiazolidinone derivative SGK 206 and the thiazolidinone derivative SGK 217 are more effective than etodolac when it comes to the breast cancer cell lines MCF-7 and MDA-MB-231. SGK 206 exhibits a low IC50 value, a distinct dose-response relationship, and strong apoptotic effects, particularly on MDA-MB-231 cells.