activity
20192021
collaborators

5 papers

cs.LG2021

Continual Active Learning for Efficient Adaptation of Machine Learning Models to Changing Image Acquisition

Matthias Perkonigg, Johannes Hofmanninger, Georg Langs

Imaging in clinical routine is subject to changing scanner protocols, hardware, or policies in a typically heterogeneous set of acquisition hardware. Accuracy and reliability of de…

cs.LG2020

Dynamic memory to alleviate catastrophic forgetting in continuous learning settings

Johannes Hofmanninger, Matthias Perkonigg, James A. Brink +3

In medical imaging, technical progress or changes in diagnostic procedures lead to a continuous change in image appearance. Scanner manufacturer, reconstruction kernel, dose, other…

physics.med-ph2020

Separation of target anatomical structure and occlusions in chest radiographs

Johannes Hofmanninger, Sebastian Roehrich, Helmut Prosch +1

Chest radiographs are commonly performed low-cost exams for screening and diagnosis. However, radiographs are 2D representations of 3D structures causing considerable clutter imped…

eess.IV2020

Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem

Johannes Hofmanninger, Florian Prayer, Jeanny Pan +3

Automated segmentation of anatomical structures is a crucial step in image analysis. For lung segmentation in computed tomography, a variety of approaches exist, involving sophisti…

eess.IV2019

Asymmetric Cascade Networks for Focal Bone Lesion Prediction in Multiple Myeloma

Roxane Licandro, Johannes Hofmanninger, Matthias Perkonigg +7

The reliable and timely stratification of bone lesion evolution risk in smoldering Multiple Myeloma plays an important role in identifying prime markers of the disease's advance an…