Skip to main content
. 2023 Oct 3;228(Suppl 4):S322–S336. doi: 10.1093/infdis/jiad158

Figure 2.

Figure 2.

Explainable artificial intelligence (AI) methods in medical imaging. Standard deep learning models are uninterpretable and therefore work as a “black box.” Explainable AI methods, such as ablation-based, attention-based, and concept-based methods, provide clinicians and researchers with additional information about how the model forms its predictions. Abbreviation: GGO, ground-glass opacities.