Bildverarbeitung für die Medizin 2019

The proceedings contain 75 papers. The special focus in this conference is on Bildverarbeitung fur die Medizin. The topics include: Segmentation of Vertebral Metastases in MRI Using an U-Net like Convolutional Neural Network; synthetic Training with Generative Adversarial Networks for Segmentation of Microscopies; Gradient-Based Expanding Spherical Appearance Models for Femoral Model Initialization in MRI; Deep segmentation refinement with result-dependent learning: A double U-net for hip joint segmentation in MRI; automatic Estimation of Cochlear Duct Length and Volume Size; interactive Neural Network Robot User Investigation for Medical Image Segmentation; Tracing of Nerve Fibers Through Brain Regions of Fiber Crossings in Reconstructed 3D-PLI Volumes; Dilated deeply supervised networks for hippocampus segmentation in MRI; Automatic Detection and Segmentation of the Acute Vessel Thrombus in Cerebral CT; automatic Detection of Blood Vessels in Optical Coherence Tomography Scans; Sparsely Connected Convolutional Layers in CNNs for Liver Segmentation in CT; smooth Ride: Low-Pass Filtering of Manual Segmentations Improves Consensus; user Loss A Forced-Choice-Inspired Approach to Train Neural Networks Directly by User Interaction; sodium Image Denoising Based on a Convolutional Denoising Autoencoder; improved X-Ray Bone Segmentation by Normalization and Augmentation Strategies; multi-Modal Super-Resolution with Deep Guided Filtering; semi-Automatic Cell Correspondence Analysis Using Iterative Point Cloud Registration; pediatric Patient Surface Model Atlas Generation and X-Ray Skin Dose Estimation; Blind Rigid Motion Estimation for Arbitrary MRI Sampling Trajectories; maximum Likelihood Estimation of Head Motion Using Epipolar Consistency; Prediction of Liver Function Based on DCE-CT; Retrospective Blind MR Image Recovery with Parametrized Motion Models; phase-Sensitive Region-of-Interest Computed Tomography.