Quality metrics of synthetic radiomics data do not predict improvement under simulated external validation: an ecologica

OBJECTIVES: To investigate whether established synthetic data quality metrics predict when deep generative augmentation improves performance under simulated external validation in radiomics. MATERIALS AND METHODS: Three conditional generators (WGAN-GP, CVAE, TabDDPM) were trai...

• Source: European Radiology (PRIMARY)
• Type: Research

RadPigeon summaries are original and for information only. They are not clinical advice.