19 citations · 41 across the 24 of their papers we have counts for
11 papers · 1 filter
Measuring Prediction Uncertainty in Neural Cellular Automata
Ario Sadafi, Michael Deutges, Nassir Navab +1
Neural cellular automata (NCA) provide a lightweight alternative to encoder-decoder segmentation networks. However, it can be difficult to decide when a prediction should be truste…
Non-intrusive Body Composition Assessment from Full-body mmWave Scans
Miriam Senne, Benjamin D. Killeen, Tony Danjun Wang +1
Body composition assessment (BCA) provides detailed information about the distribution of different tissue types in the body, enabling more precise characterization of individuals…
Can ultrasound confidence maps predict sonographers' labeling variability?
Vanessa Gonzalez Duque, Leonhard Zirus, Yordanka Velikova +2
Measuring cross-sectional areas in ultrasound images is a standard tool to evaluate disease progress or treatment response. Often addressed today with supervised deep-learning segm…
DefCor-Net: Physics-Aware Ultrasound Deformation Correction
Zhongliang Jiang, Yue Zhou, Dongliang Cao +1
The recovery of morphologically accurate anatomical images from deformed ones is challenging in ultrasound (US) image acquisition, but crucial to accurate and consistent diagnosis,…
LOTUS: Learning to Optimize Task-based US representations
Yordanka Velikova, Mohammad Farid Azampour, Walter Simson +2
Anatomical segmentation of organs in ultrasound images is essential to many clinical applications, particularly for diagnosis and monitoring. Existing deep neural networks require…
Thoracic Cartilage Ultrasound-CT Registration using Dense Skeleton Graph
Zhongliang Jiang, Chenyang Li, Xuesong Li +1
Autonomous ultrasound (US) imaging has gained increased interest recently, and it has been seen as a potential solution to overcome the limitations of free-hand US examinations, su…
Motion Magnification in Robotic Sonography: Enabling Pulsation-Aware Artery Segmentation
Dianye Huang, Yuan Bi, Nassir Navab +1
Ultrasound (US) imaging is widely used for diagnosing and monitoring arterial diseases, mainly due to the advantages of being non-invasive, radiation-free, and real-time. In order…
Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET
Francesca De Benetti, Walter Simson, Magdalini Paschali +5
Dynamic positron emission tomography imaging (dPET) provides temporally resolved images of a tracer enabling a quantitative measure of physiological processes. Voxel-wise physiolog…
Skeleton Graph-based Ultrasound-CT Non-rigid Registration
Zhongliang Jiang, Xuesong Li, Chenyu Zhang +3
Autonomous ultrasound (US) scanning has attracted increased attention, and it has been seen as a potential solution to overcome the limitations of conventional US examinations, suc…
Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images
Ario Sadafi, Oleksandra Adonkina, Ashkan Khakzar +5
Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level expl…
MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization
Yuan Bi, Zhongliang Jiang, Ricarda Clarenbach +3
Generalization capabilities of learning-based medical image segmentation across domains are currently limited by the performance degradation caused by the domain shift, particularl…