Výsledky vyhledávání - "Yiğitsoy, Mehmet"

Report

Differentially Private Active Learning: Balancing Effective Data Selection and Privacy

Autor: Schwethelm, Kristian, Kaiser, Johannes, Kuntzer, Jonas, Yigitsoy, Mehmet, Rueckert, Daniel, Kaissis, Georgios

Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods, particula

Externí odkaz: http://arxiv.org/abs/2410.00542

Zobrazit plný text záznamu

Report

Simulation of acquisition shifts in T2 Flair MR images to stress test AI segmentation networks

Autor: Posselt, Christiane, Avci, Mehmet Yigit, Yigitsoy, Mehmet, Schünke, Patrick, Kolbitsch, Christoph, Schäffter, Tobias, Remmele, Stefanie

Purpose: To provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2 weighted (T2w) fluid attenuated

Externí odkaz: http://arxiv.org/abs/2311.01894

Zobrazit plný text záznamu

Report

Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments

Autor: Kayhan, Mert, Köpüklü, Okan, Sarhan, Mhd Hasan, Yigitsoy, Mehmet, Eslami, Abouzar, Rigoll, Gerhard

For many practical problems and applications, it is not feasible to create a vast and accurately labeled dataset, which restricts the application of deep learning in many areas. Semi-supervised learning algorithms intend to improve performance by als

Externí odkaz: http://arxiv.org/abs/1912.04618

Zobrazit plný text záznamu

Report

Multi-scale Microaneurysms Segmentation Using Embedding Triplet Loss

Autor: Sarhan, Mhd Hasan, Albarqouni, Shadi, Yigitsoy, Mehmet, Navab, Nassir, Eslami, Abouzar

Deep learning techniques are recently being used in fundus image analysis and diabetic retinopathy detection. Microaneurysms are an important indicator of diabetic retinopathy progression. We introduce a two-stage deep learning approach for microaneu

Externí odkaz: http://arxiv.org/abs/1904.12732

Zobrazit plný text záznamu