Medizinische Universität Graz - Research portal
Selected Publication:
SHR Neuro Cancer Cardio Lipid Metab Microb
Mosinska, A; Kozinski, M; Fua, P.
Joint Segmentation and Path Classification of Curvilinear Structures.
IEEE Trans Pattern Anal Mach Intell. 2020; 42(6): 1515-1521.
Doi: 10.1109/TPAMI.2019.2921327
Web of Science
PubMed
FullText
FullText_MUG
- Leading authors Med Uni Graz
- Kozinski Mateusz
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinear network. Most existing delineation approaches first perform binary segmentation of the image and then refine it using either a set of hand-designed heuristics or a separate classifier that assigns likelihood to paths extracted from the pixel-wise prediction. In our work, we bridge the gap between segmentation and path classification by training a deep network that performs those two tasks simultaneously. We show that this approach is beneficial because it enforces consistency across the whole processing pipeline. We apply our approach on roads and neurons datasets.
- Find related publications in this database (Keywords)
- Image segmentation
- Image edge detection
- Roads
- Task analysis
- Decoding
- Feature extraction
- Computer architecture
- Deep convolutional neural networks
- multi-task learning
- segmentation
- delineation
- curvilinear structures
- road detection
- neuron tracing