Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
This addresses the problem of reducing annotation burden and domain shift in digital pathology, though it is incremental as it builds on existing UDA and segmentation frameworks.
The paper tackles unsupervised nuclei instance segmentation in histopathology images by adapting from fluorescence microscopy, achieving performance comparable to fully supervised methods and outperforming state-of-the-art UDA approaches on three datasets.
Unsupervised domain adaptation (UDA) for nuclei instance segmentation is important for digital pathology, as it alleviates the burden of labor-intensive annotation and domain shift across datasets. In this work, we propose a Cycle Consistency Panoptic Domain Adaptive Mask R-CNN (CyC-PDAM) architecture for unsupervised nuclei segmentation in histopathology images, by learning from fluorescence microscopy images. More specifically, we first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images. Secondly, a semantic branch with a domain discriminator is designed to achieve panoptic-level domain adaptation. Thirdly, in order to avoid the influence of the source-biased features, we propose a task re-weighting mechanism to dynamically add trade-off weights for the task-specific loss functions. Experimental results on three datasets indicate that our proposed method outperforms state-of-the-art UDA methods significantly, and demonstrates a similar performance as fully supervised methods.