BFS-Net: Weakly Supervised Cell Instance Segmentation from Bright-Field Microscopy Z-Stacks
This work addresses the challenge of volumetric cell segmentation for microscopy researchers, offering a practical solution that reduces data collection and annotation burdens while maintaining competitive accuracy.
The paper tackles the problem of 3D cell instance segmentation from Bright-Field Microscopy Z-stacks, proposing a weakly supervised method that uses only approximate cell centroids and achieves performance close to fully supervised methods with significantly reduced labeling effort.
Despite its broad availability, volumetric information acquisition from Bright-Field Microscopy (BFM) is inherently difficult due to the projective nature of the acquisition process. We investigate the prediction of 3D cell instances from a set of BFM Z-Stack images. We propose a novel two-stage weakly supervised method for volumetric instance segmentation of cells which only requires approximate cell centroids annotation. Created pseudo-labels are thereby refined with a novel refinement loss with Z-stack guidance. The evaluations show that our approach can generalize not only to BFM Z-Stack data, but to other 3D cell imaging modalities. A comparison of our pipeline against fully supervised methods indicates that the significant gain in reduced data collection and labelling results in minor performance difference.