Medical Image Classification on BraTS HGG/LGG 2019 (test)
71AccuracyMulti-Scale Reward Learning (Ours)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Multi-Scale Reward Learning (Ours)Backbone=3D ResNet-50, Data Source=RL fine-tuned diffusion model (2000 volumes per class), Training=Pre-trained on RL synthetic then fine-tuned on real data, Evaluation Protocol=Mean ± standard deviation over three independent runs2026.03 | 71 | 71 | 74 | |
| Standard SyntheticBackbone=3D ResNet-50, Data Source=Standard diffusion models, Training=Pre-trained on synthetic data then fine-tuned on real data, Evaluation Protocol=Mean ± standard deviation over three independent runs2026.03 | 62 | 68 | 65 | |
| Real Data OnlyBackbone=3D ResNet-50, Training=Fine-tuned on real training dataset, Evaluation Protocol=Mean ± standard deviation over three independent runs2026.03 | 59 | 67 | 65 |