Výsledky vyhledávání - "Uderhardt, Stefan"

Report

Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN

Autor: Utz, Jonas, Weise, Tobias, Schlereth, Maja, Wagner, Fabian, Thies, Mareike, Gu, Mingxuan, Uderhardt, Stefan, Breininger, Katharina

Annotating nuclei in microscopy images for the training of neural networks is a laborious task that requires expert knowledge and suffers from inter- and intra-rater variability, especially in fluorescence microscopy. Generative networks such as Cycl

Externí odkaz: http://arxiv.org/abs/2308.01769

Zobrazit plný text záznamu

Report

Exploring Epipolar Consistency Conditions for Rigid Motion Compensation in In-vivo X-ray Microscopy

Autor: Thies, Mareike, Wagner, Fabian, Gu, Mingxuan, Mei, Siyuan, Huang, Yixing, Pechmann, Sabrina, Aust, Oliver, Weidner, Daniela, Neag, Georgiana, Uderhardt, Stefan, Schett, Georg, Christiansen, Silke, Maier, Andreas

Intravital X-ray microscopy (XRM) in preclinical mouse models is of vital importance for the identification of microscopic structural pathological changes in the bone which are characteristic of osteoporosis. The complexity of this method stems from

Externí odkaz: http://arxiv.org/abs/2303.00449

Zobrazit plný text záznamu

Report

Noise2Contrast: Multi-Contrast Fusion Enables Self-Supervised Tomographic Image Denoising

Autor: Wagner, Fabian, Thies, Mareike, Pfaff, Laura, Maul, Noah, Pechmann, Sabrina, Gu, Mingxuan, Utz, Jonas, Aust, Oliver, Weidner, Daniela, Neag, Georgiana, Uderhardt, Stefan, Choi, Jang-Hwan, Maier, Andreas

Self-supervised image denoising techniques emerged as convenient methods that allow training denoising models without requiring ground-truth noise-free data. Existing methods usually optimize loss metrics that are calculated from multiple noisy reali

Externí odkaz: http://arxiv.org/abs/2212.04832

Zobrazit plný text záznamu

Report

SYNTA: A novel approach for deep learning-based image analysis in muscle histopathology using photo-realistic synthetic data

Autor: Mill, Leonid, Aust, Oliver, Ackermann, Jochen A., Burger, Philipp, Pascual, Monica, Palumbo-Zerr, Katrin, Krönke, Gerhard, Uderhardt, Stefan, Schett, Georg, Clemen, Christoph S., Schröder, Rolf, Holtzhausen, Christian, Jabari, Samir, Maier, Andreas, Grüneboom, Anika

Artificial intelligence (AI), machine learning, and deep learning (DL) methods are becoming increasingly important in the field of biomedical image analysis. However, to exploit the full potential of such methods, a representative number of experimen

Externí odkaz: http://arxiv.org/abs/2207.14650

Zobrazit plný text záznamu

Report

Ultra Low-Parameter Denoising: Trainable Bilateral Filter Layers in Computed Tomography

Autor: Wagner, Fabian, Thies, Mareike, Gu, Mingxuan, Huang, Yixing, Pechmann, Sabrina, Patwari, Mayank, Ploner, Stefan, Aust, Oliver, Uderhardt, Stefan, Schett, Georg, Christiansen, Silke, Maier, Andreas

Publikováno v: Med.Phys. 49 (2022) 5107-5120

Computed tomography is widely used as an imaging tool to visualize three-dimensional structures with expressive bone-soft tissue contrast. However, CT resolution and radiation dose are tightly entangled, highlighting the importance of low-dose CT com

Externí odkaz: http://arxiv.org/abs/2201.10345

Zobrazit plný text záznamu