Medizinische Universität Graz - Research portal
Selected Publication:
SHR Neuro Cancer Cardio Lipid Metab Microb
Oner, D; Kozinski, M; Citraro, L; Fua, P.
Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate.
IEEE Trans Med Imaging. 2022; 41(12): 3675-3685.
Doi: 10.1109/TMI.2022.3193072
Web of Science
PubMed
FullText
FullText_MUG
- Leading authors Med Uni Graz
- Kozinski Mateusz
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data is often hard to interpret visually and in part because the 3D interfaces are awkward to use. In this paper, we introduce a method that explicitly accounts for annotation inaccuracies. To this end, we treat the annotations as active contour models that can deform themselves while preserving their topology. This enables us to jointly train the network and correct potential errors in the original annotations. The result is an approach that boosts performance of deep networks trained with potentially inaccurate annotations.
- Find related publications in this database (Keywords)
- Active contours
- deep learning
- delineation
- neurons
- snakes
- vessels