Segmenting and tracking cell instances with cosine embeddings and recurrent hourglass networks

Horst Bischof, Christian Payer, Darko Stern, Marlies Feiner, Martin Urschler

Research output: Contribution to journalArticlepeer-review


Differently to semantic segmentation, instance segmentation assigns unique labels to each individual instance of the same object class. In this work, we propose a novel recurrent fully convolutional network architecture for tracking such instance segmentations over time, which is highly relevant, e.g., in biomedical applications involving cell growth and migration. Our network architecture incorporates convolutional gated recurrent units (ConvGRU) into a stacked hourglass network to utilize temporal information, e.g., from microscopy videos. Moreover, we train our network with a novel embedding loss based on cosine similarities, such that the network predicts unique embeddings for every instance throughout videos, even in the presence of dynamic structural changes due to mitosis of cells. To create the final tracked instance segmentations, the pixel-wise embeddings are clustered among subsequent video frames …
Original languageEnglish
Pages (from-to)106-119
JournalMedical Image Analysis
Publication statusPublished - 2019

Cite this