Self Adversarial Attack as an Augmentation Method for Immunohistochemical Stainings - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Self Adversarial Attack as an Augmentation Method for Immunohistochemical Stainings

Résumé

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.
Fichier principal
Vignette du fichier
islandora_117460.pdf (6.04 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03321035 , version 1 (16-08-2021)

Identifiants

Citer

Jelica Vasiljevic, Friedrich Feuerhake, Cédric Wemmert, Thomas Lampert. Self Adversarial Attack as an Augmentation Method for Immunohistochemical Stainings. IEEE International Symposium on Biomedical Imaging, 2021, En ligne, France. ⟨10.1109/ISBI48211.2021.9433838⟩. ⟨hal-03321035⟩
79 Consultations
40 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More