
Место рождения
ERZURUM
Языки
АНГЛИЙСКИЙ
2021 - 2025
Городская больница им. проф. д-ра Джемиля Ташчыоглу, Окмейданы
2019 - 2020
Государственная больница Конья Джихан6бейли
2014 - 2018
Учебно-исследовательская больница ГОП Таксим
2013 - 2013
Ширнак, Центр координации скорой помощи 112
2010 - 2010
Исследовательский центр Лондонского Королевского колледжа (King’s College)
2013
Университет Ешитепе, Медицинский факультет
2013
Учебно-исследовательская больница Таксим, Радиология
LUMINA: Мультивендорный бенчмарк маммографии с протоколом гармонизации энергии
Abstract Publicly available full-field digital mammography (FFDM) datasets remain limited in size, clinical annotations, and vendor diversity, hindering the development of robust mod els. We introduce LUMINA, a curated, multi-vendor FFDM dataset that explicitly encodes acquisition energy and vendor metadata to capture clinically relevant appear ance variations often overlooked in existing benchmarks. This dataset contains 1824 images from 468 patients (960 benign, 864 malignant), with pathology-confirmed labels, BI-RADS assessments, and breast-density annotations. LU MINA spans six acquisition systems and includes both high and low-energy imaging styles, enabling systematic analy sis of vendor- and energy-induced domain shifts. To address these variations, we propose a foreground-only pixel-space alignment method (“energy harmonization”) that maps im ages to a low-energy reference while preserving lesion mor phology. We benchmark CNN and transformer models on three clinically relevant tasks: diagnosis (benign vs. malig nant), BI-RADS classification, and density estimation. Two view models consistently outperform single-view models. EfficientNet-B0 achieves an AUC of 93.54% for diagnosis, while Swin-T achieves the best macro-AUC of 89.43% for density prediction. Harmonization improves performance across architectures and produces more localized Grad CAM responses. Overall, LUMINA provides (1) a vendor diverse benchmark and (2) a model-agnostic harmonization framework for reliable and deployable mammography AI.