Bayesian Polytrees with Learned Deep Features for Multi-Class Cell Segmentation

Hamid Fehri, Ali Gooya, Yuanjun Lu, Erik Meijering, Simon A. Johnston, Alejandro F. Frangi

Research output: Contribution to journalArticlepeer-review


The recognition of different cell compartments, the types of cells, and their interactions is a critical aspect of quantitative cell biology. However, automating this problem has proven to be non-trivial and requires solving multi-class image segmentation tasks that are challenging owing to the high similarity of objects from different classes and irregularly shaped structures. To alleviate this, graphical models are useful due to their ability to make use of prior knowledge and model inter-class dependences. Directed acyclic graphs, such as trees, have been widely used to model top-down statistical dependences as a prior for improved image segmentation. However, using trees, a few inter-class constraints can be captured. To overcome this limitation, we propose polytree graphical models that capture label proximity relations more naturally compared to tree-based approaches. A novel recursive mechanism based on two-pass message passing was developed to efficiently calculate closed-form posteriors of graph nodes on polytrees. The algorithm is evaluated on simulated data and on two publicly available fluorescence microscopy datasets, outperforming directed trees and three state-of-the-art convolutional neural networks, namely, SegNet, DeepLab, and PSPNet. Polytrees are shown to outperform directed trees in predicting segmentation error by highlighting areas in the segmented image that do not comply with prior knowledge. This paves the way to uncertainty measures on the resulting segmentation and guide subsequent segmentation refinement.

Original languageEnglish
Article number8626539
Pages (from-to)3246-3260
Number of pages15
JournalIEEE Transactions on Image Processing
Issue number7
Publication statusPublished - Jul 2019


  • cell and nucleus segmentation
  • error prediction
  • Hierarchical graphs
  • multi-class segmentation


Dive into the research topics of 'Bayesian Polytrees with Learned Deep Features for Multi-Class Cell Segmentation'. Together they form a unique fingerprint.

Cite this