TY  - JOUR
AU  - Upschulte, Eric
AU  - Harmeling, Stefan
AU  - Amunts, Katrin
AU  - Dickscheid, Timo
TI  - Contour proposal networks for biomedical instance segmentation
JO  - Medical image analysis
VL  - 77
SN  - 1361-8415
CY  - Amsterdam [u.a.]
PB  - Elsevier Science
M1  - FZJ-2022-01559
SP  - 102371 -
PY  - 2022
AB  - We present a conceptually simple framework for object instance segmentation, called Contour Proposal Network (CPN), which detects possibly overlapping objects in an image while simultaneously fitting closed object contours using a fixed-size representation based on Fourier Descriptors. The CPN can incorporate state-of-the-art object detection architectures as backbone networks into a single-stage instance segmentation model that can be trained end-to-end. We construct CPN models with different backbone networks and apply them to instance segmentation of cells in datasets from different modalities. In our experiments, CPNs outperform U-Net, Mask R-CNN and StarDist in instance segmentation accuracy. We present variants with execution times suitable for real-time applications. The trained models generalize well across different domains of cell types. Since the main assumption of the framework is closed object contours, it is applicable to a wide range of detection problems also beyond the biomedical domain. An implementation of the model architecture in PyTorch is freely available.
LB  - PUB:(DE-HGF)16
C6  - 35180674
UR  - <Go to ISI:>//WOS:000912927000003
DO  - DOI:10.1016/j.media.2022.102371
UR  - https://juser.fz-juelich.de/record/906623
ER  -