Auxiliary CycleGAN-guidance for Task-Aware Domain Translation from Duplex to Monoplex IHC Images
This work addresses a domain-specific challenge in medical imaging for pathology, offering an incremental improvement over existing methods.
The paper tackled the problem of translating duplex to monoplex IHC images, where CycleGAN fails due to non-invertible mappings, by proposing a novel training design using auxiliary immunofluorescence images as a constraint, resulting in improved performance on a downstream segmentation task.
Generative models enable the translation from a source image domain where readily trained models are available to a target domain unseen during training. While Cycle Generative Adversarial Networks (GANs) are well established, the associated cycle consistency constrain relies on that an invertible mapping exists between the two domains. This is, however, not the case for the translation between images stained with chromogenic monoplex and duplex immunohistochemistry (IHC) assays. Focusing on the translation from the latter to the first, we propose - through the introduction of a novel training design, an alternative constrain leveraging a set of immunofluorescence (IF) images as an auxiliary unpaired image domain. Quantitative and qualitative results on a downstream segmentation task show the benefit of the proposed method in comparison to baseline approaches.