针对小样本医学图像生成，优化R3GAN提升诊断准确性
Beyond Data Scarcity Optimizing R3GAN for Medical Image Generation from Small Datasets
- 采用全烧入阶段与渐增伽马范围（5到40）训练策略
- 三细胞期识别召回率从0.06提升至0.69，F1-score达0.60
- 适合处理类不平衡的小样本医学图像生成任务
医学图像数据集常存在严重类别不平衡，且临床影像数据本身样本量有限。以人类胚胎时间拉伸成像（TLI）为例，本文研究如何优化生成对抗网络（GAN）在小样本下的表现，生成真实且具有诊断意义的图像。基于对R3GAN的系统实验，提出适用于256x256分辨率数据集的优化训练策略：包含完整烧入阶段与低且逐步增加的伽马范围（5至40）。生成样本用于平衡不平衡胚胎数据集，显著提升分类性能：三细胞期（t3）类别的召回率由0.06升至0.69，F1-score由0.11增至0.60，且未影响其他类别性能。结果表明，定制化的R3GAN训练策略可有效缓解数据稀缺问题，增强小规模医学影像任务中的模型鲁棒性。
原文摘要 · Abstract (English)
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 case study, 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 256x256-resolution datasets, featuring a full burn-in phase and a low, gradually increasing gamma range (5 to 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 the three-cell (t3) class increased from 0.06 to 0.69 and from 0.11 to 0.60, respectively, without compromising the performance of 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。