Cargando…
Generalisation effects of predictive uncertainty estimation in deep learning for digital pathology
Deep learning (DL) has shown great potential in digital pathology applications. The robustness of a diagnostic DL-based solution is essential for safe clinical deployment. In this work we evaluate if adding uncertainty estimates for DL predictions in digital pathology could result in increased value...
Autores principales: | Pocevičiūtė, Milda, Eilertsen, Gabriel, Jarkman, Sofia, Lundström, Claes |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9117245/ https://www.ncbi.nlm.nih.gov/pubmed/35585087 http://dx.doi.org/10.1038/s41598-022-11826-0 |
Ejemplares similares
-
Generalization of Deep Learning in Digital Pathology: Experience in Breast Cancer Metastasis Detection
por: Jarkman, Sofia, et al.
Publicado: (2022) -
2020 Vision of Digital Pathology in Action
por: Asa, Sylvia L., et al.
Publicado: (2019) -
Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology
por: MacDonald, Samual, et al.
Publicado: (2023) -
Summary of third Nordic symposium on digital pathology
por: Lundström, Claes, et al.
Publicado: (2016) -
Uncertainty-informed deep learning models enable high-confidence predictions for digital histopathology
por: Dolezal, James M., et al.
Publicado: (2022)