Accurate 3D Cell Segmentation using Deep Feature and CRF Refinement
This work addresses the need for precise cell boundary identification in microscopy for understanding cell morphogenesis, representing an incremental improvement over existing methods.
The paper tackles the problem of accurately segmenting individual cells in 3D confocal microscopy images by proposing a method that combines a deep neural network for boundary confidence maps with a 3D watershed algorithm and CRF refinement, resulting in improved accuracy and generalization across datasets without retraining.
We consider the problem of accurately identifying cell boundaries and labeling individual cells in confocal microscopy images, specifically, 3D image stacks of cells with tagged cell membranes. Precise identification of cell boundaries, their shapes, and quantifying inter-cellular space leads to a better understanding of cell morphogenesis. Towards this, we outline a cell segmentation method that uses a deep neural network architecture to extract a confidence map of cell boundaries, followed by a 3D watershed algorithm and a final refinement using a conditional random field. In addition to improving the accuracy of segmentation compared to other state-of-the-art methods, the proposed approach also generalizes well to different datasets without the need to retrain the network for each dataset. Detailed experimental results are provided, and the source code is available on GitHub.