Achieving Multisite Generalization for CNN-Based Disease Diagnosis Models by Mitigating Shortcut Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3193700
Abstract: When a learned model has high accuracy under familiar settings (internal testing) and a big drop in accuracy under slightly different circumstances (external testing) we suspect it is using shortcuts to make decisions. This problem… read more here.
Keywords: disease diagnosis; diagnosis; drop; shortcut ... See more keywords
Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement
Sign Up to like & getrecommendations! Published in 2022 at "PLoS ONE"
DOI: 10.1371/journal.pone.0274098
Abstract: In response to the COVID-19 global pandemic, recent research has proposed creating deep learning based models that use chest radiographs (CXRs) in a variety of clinical tasks to help manage the crisis. However, the size… read more here.
Keywords: feature disentanglement; ray; learning models; deep learning ... See more keywords