Self adversarial attack as an augmentation method for immunohistochemical stainings
This addresses data scarcity in medical imaging for renal pathology, but it is incremental as it builds on existing translation methods.
The paper tackled the problem of limited data in histopathology by using hidden noise from unpaired image-to-image translation as an augmentation method, resulting in improved performance for supervised glomeruli segmentation.
It has been shown that unpaired image-to-image translation methods constrained by cycle-consistency hide the information necessary for accurate input reconstruction as imperceptible noise. We demonstrate that, when applied to histopathology data, this hidden noise appears to be related to stain specific features and show that this is the case with two immunohistochemical stainings during translation to Periodic acid- Schiff (PAS), a histochemical staining method commonly applied in renal pathology. Moreover, by perturbing this hidden information, the translation models produce different, plausible outputs. We demonstrate that this property can be used as an augmentation method which, in a case of supervised glomeruli segmentation, leads to improved performance.