Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets

Medical image datasets frequently exhibit significant class imbalance, a challenge that is further amplified by the inherently limited sample sizes that characterize clinical imaging data._Using human embryo time-lapse imaging (TLI) as a primary case study and cross validating on tilapia images, this work investigates how generative adversarial networks (GANs) can be optimized for small datasets to generate realistic and diagnostically meaningful images. Based on systematic experiments with R3GAN, we established effective training strategies and designed an optimized configuration for $256 \times 256$ resolution datasets, featuring a full burn-in phase and a low, gradually increasing $\gamma$ range $(5 \rightarrow 40)$. The generated samples were used to balance an imbalanced embryo dataset, leading to substantial improvement in classification performance. The recall and F1-score of $\boldsymbol{t} \boldsymbol{3}$ increased from 0.06 to 0.69 and 0.11 to 0.60, respectively, without compromising other classes. These results demonstrate that tailored R3GAN training strategies can effectively alleviate data scarcity and improve model robustness in small-scale medical imaging tasks.