Cargando…

Training calibration-based counterfactual explainers for deep learning models in medical image analysis

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernibl...

Descripción completa

Detalles Bibliográficos
Autores principales: Thiagarajan, Jayaraman J., Thopalli, Kowshik, Rajan, Deepta, Turaga, Pavan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8755769/
https://www.ncbi.nlm.nih.gov/pubmed/35022467
http://dx.doi.org/10.1038/s41598-021-04529-5