Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wilm, Frauke, Fragoso, Marco, Bertram, Christof A., Stathonikos, Nikolas, Öttl, Mathias, Qiu, Jingna, Klopfleisch, Robert, Maier, Andreas, Aubreville, Marc, Breininger, Katharina
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929559679533056
author Wilm, Frauke
Fragoso, Marco
Bertram, Christof A.
Stathonikos, Nikolas
Öttl, Mathias
Qiu, Jingna
Klopfleisch, Robert
Maier, Andreas
Aubreville, Marc
Breininger, Katharina
author_facet Wilm, Frauke
Fragoso, Marco
Bertram, Christof A.
Stathonikos, Nikolas
Öttl, Mathias
Qiu, Jingna
Klopfleisch, Robert
Maier, Andreas
Aubreville, Marc
Breininger, Katharina
contents Computer-aided systems in histopathology are often challenged by various sources of domain shift that impact the performance of these algorithms considerably. We investigated the potential of using self-supervised pre-training to overcome scanner-induced domain shifts for the downstream task of tumor segmentation. For this, we present the Barlow Triplets to learn scanner-invariant representations from a multi-scanner dataset with local image correspondences. We show that self-supervised pre-training successfully aligned different scanner representations, which, interestingly only results in a limited benefit for our downstream task. We thereby provide insights into the influence of scanner characteristics for downstream applications and contribute to a better understanding of why established self-supervised methods have not yet shown the same success on histopathology data as they have for natural images.
format Preprint
id arxiv_https___arxiv_org_abs_2211_16141
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology
Wilm, Frauke
Fragoso, Marco
Bertram, Christof A.
Stathonikos, Nikolas
Öttl, Mathias
Qiu, Jingna
Klopfleisch, Robert
Maier, Andreas
Aubreville, Marc
Breininger, Katharina
Image and Video Processing
Computer Vision and Pattern Recognition
Computer-aided systems in histopathology are often challenged by various sources of domain shift that impact the performance of these algorithms considerably. We investigated the potential of using self-supervised pre-training to overcome scanner-induced domain shifts for the downstream task of tumor segmentation. For this, we present the Barlow Triplets to learn scanner-invariant representations from a multi-scanner dataset with local image correspondences. We show that self-supervised pre-training successfully aligned different scanner representations, which, interestingly only results in a limited benefit for our downstream task. We thereby provide insights into the influence of scanner characteristics for downstream applications and contribute to a better understanding of why established self-supervised methods have not yet shown the same success on histopathology data as they have for natural images.
title Mind the Gap: Scanner-induced domain shifts pose challenges for representation learning in histopathology
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.16141