1 code implementation • 15 Mar 2024 • Yipeng Sun, Yixing Huang, Linda-Sophie Schneider, Mareike Thies, Mingxuan Gu, Siyuan Mei, Siming Bayer, Andreas Maier
However, the choice of loss function profoundly affects the reconstructed images.
no code implementations • 1 Mar 2024 • Chengze Ye, Linda-Sophie Schneider, Yipeng Sun, Andreas Maier
The filter is designed for a specific orbit geometry and is obtained using a data-driven approach based on deep learning.
no code implementations • 29 Jan 2024 • Yuzhong Zhou, Linda-Sophie Schneider, Fuxin Fan, Andreas Maier
We use a U-Net-based architecture for defect segmentation.
1 code implementation • 29 Jan 2024 • Yipeng Sun, Linda-Sophie Schneider, Fuxin Fan, Mareike Thies, Mingxuan Gu, Siyuan Mei, Yuzhong Zhou, Siming Bayer, Andreas Maier
In this study, we introduce a Fourier series-based trainable filter for computed tomography (CT) reconstruction within the filtered backprojection (FBP) framework.
no code implementations • 29 Jan 2024 • Linda-Sophie Schneider, Gabriel Herl, Andreas Maier
X-ray computed tomography (CT) plays a key role in digitizing three-dimensional structures for a wide range of medical and industrial applications.
no code implementations • 17 Jan 2024 • Mareike Thies, Fabian Wagner, Noah Maul, Haijun Yu, Manuela Meier, Linda-Sophie Schneider, Mingxuan Gu, Siyuan Mei, Lukas Folle, Andreas Maier
The analytic Jacobian for the backprojection operation, which is at the core of the proposed method, is made publicly available.
no code implementations • 21 Mar 2023 • Linda-Sophie Schneider, Mareike Thies, Christopher Syben, Richard Schielein, Mathias Unberath, Andreas Maier
We present a method for selecting valuable projections in computed tomography (CT) scans to enhance image reconstruction and diagnosis.
no code implementations • 13 Feb 2023 • Mareike Thies, Fabian Wagner, Noah Maul, Laura Pfaff, Linda-Sophie Schneider, Christopher Syben, Andreas Maier
In computed tomography (CT), the projection geometry used for data acquisition needs to be known precisely to obtain a clear reconstructed image.
1 code implementation • 5 Dec 2022 • Mareike Thies, Fabian Wagner, Noah Maul, Lukas Folle, Manuela Meier, Maximilian Rohleder, Linda-Sophie Schneider, Laura Pfaff, Mingxuan Gu, Jonas Utz, Felix Denzinger, Michael Manhart, Andreas Maier
The cost function is parameterized by a trained neural network which regresses an image quality metric from the motion affected reconstruction alone.