Cargando…
Stress Testing Pathology Models with Generated Artifacts
BACKGROUND: Machine learning models provide significant opportunities for improvement in health care, but their “black-box” nature poses many risks. METHODS: We built a custom Python module as part of a framework for generating artifacts that are meant to be tunable and describable to allow for futu...
Autores principales: | Wang, Nicholas Chandler, Kaplan, Jeremy, Lee, Joonsang, Hodgin, Jeffrey, Udager, Aaron, Rao, Arvind |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Wolters Kluwer - Medknow
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8721870/ https://www.ncbi.nlm.nih.gov/pubmed/35070483 http://dx.doi.org/10.4103/jpi.jpi_6_21 |
Ejemplares similares
-
Simulated MRI Artifacts: Testing Machine Learning Failure Modes
por: Wang, Nicholas C., et al.
Publicado: (2022) -
Lung Ultrasound Artifacts Interpreted as Pathology Footprints
por: Demi, Marcello, et al.
Publicado: (2023) -
An Additive Manufacturing Test Artifact
por: Moylan, Shawn, et al.
Publicado: (2014) -
Spatial Habitat Features Derived from Multiparametric Magnetic Resonance Imaging Data Are Associated with Molecular Subtype and 12-Month Survival Status in Glioblastoma Multiforme
por: Lee, Joonsang, et al.
Publicado: (2015) -
Association of graph-based spatial features with overall survival status of glioblastoma patients
por: Lee, Joonsang, et al.
Publicado: (2023)