Dynamic Range-Invariant GAN Reconstruction via Optimized Target Training in Medical Ultrasound Imaging

Ultrasound imaging is sensitive to operatordependent parameters such as dynamic range (DR), when considering 8-bit reconstructed images, which can compromise both clinical interpretation and the reliability of artificial intelligence (AI)-based reconstruction pipelines. This work validates an automatic dynamic range optimization (autoDR) method as a standardized training reference for Generative Adversarial Network (GAN) models. By evaluating GAN robustness to DR variability, we demonstrate that autoDR enables consistent, high-quality reconstructions across diverse acquisition settings, outperforming classical enhancement techniques. These findings highlight autoDR as a practical solution for reducing operator dependence, improving reproducibility, and a robust reference standard for GAN-based ultrasound image reconstruction when there is no access to raw radiofrequency data.