Cargando…
Physical imaging parameter variation drives domain shift
Statistical learning algorithms strongly rely on an oversimplified assumption for optimal performance, that is, source (training) and target (testing) data are independent and identically distributed. Variation in human tissue, physician labeling and physical imaging parameters (PIPs) in the generat...
Autores principales: | Kilim, Oz, Olar, Alex, Joó, Tamás, Palicz, Tamás, Pollner, Péter, Csabai, István |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9734181/ https://www.ncbi.nlm.nih.gov/pubmed/36494393 http://dx.doi.org/10.1038/s41598-022-23990-4 |
Ejemplares similares
-
Automated prediction of COVID-19 severity upon admission by chest X-ray images and clinical metadata aiming at accuracy and explainability
por: Olar, Alex, et al.
Publicado: (2023) -
SARS-CoV-2 receptor-binding domain deep mutational AlphaFold2 structures
por: Kilim, Oz, et al.
Publicado: (2023) -
Impact Evaluation of Score Classes and Annotation Regions in Deep Learning-Based Dairy Cow Body Condition Prediction
por: Nagy, Sára Ágnes, et al.
Publicado: (2023) -
Detecting and classifying lesions in mammograms with Deep Learning
por: Ribli, Dezső, et al.
Publicado: (2018) -
Countrywide population movement monitoring using mobile devices generated (big) data during the COVID-19 crisis
por: Szocska, Miklos, et al.
Publicado: (2021)