Empirical Study of Quality Image Assessment for Synthesis of Fetal Head Ultrasound Imaging with DCGANs
This addresses dataset limitations for medical imaging researchers, but it is incremental as it applies existing methods to a specific domain.
The study tackled the scarcity of fetal head ultrasound datasets by empirically evaluating DCGANs for image synthesis, finding that FID and LBPv metrics correlate strongly with clinical quality scores.
In this work, we present an empirical study of DCGANs, including hyperparameter heuristics and image quality assessment, as a way to address the scarcity of datasets to investigate fetal head ultrasound. We present experiments to show the impact of different image resolutions, epochs, dataset size input, and learning rates for quality image assessment on four metrics: mutual information (MI), Fréchet inception distance (FID), peak-signal-to-noise ratio (PSNR), and local binary pattern vector (LBPv). The results show that FID and LBPv have stronger relationship with clinical image quality scores. The resources to reproduce this work are available at \url{https://github.com/budai4medtech/miua2022}.