Search Results for author:
Found 5 papers, 2 papers with code
Differentiable Score-Based Likelihoods: Learning CT Motion Compensation From Clean Images
Motion artifacts can compromise the diagnostic value of computed tomography (CT) images.
Focus on Content not Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN
We show that this increases coherence between generated images and cycled masks and evaluate synthetic datasets on a downstream nuclei segmentation task.
Noise2Contrast: Multi-Contrast Fusion Enables Self-Supervised Tomographic Image Denoising
We stack denoising with domain-transfer operators to utilize the independent noise realizations of different image contrasts to derive a self-supervised loss.
Gradient-Based Geometry Learning for Fan-Beam CT Reconstruction
The cost function is parameterized by a trained neural network which regresses an image quality metric from the motion affected reconstruction alone.
On the Benefit of Dual-domain Denoising in a Self-supervised Low-dose CT Setting
In this work, we present an end-to-end trainable CT reconstruction pipeline that contains denoising operators in both the projection and the image domain and that are optimized simultaneously without requiring ground-truth high-dose CT data.
