Research map / Image generation / Fast diffusion sampling
Identity-Consistent Diffusion Network for Grading Knee Osteoarthritis Progression in Radiographic Imaging
Wenhua Wu, Kun Hu, Wenxi Yue, Wei Li, Milena Simic, Changyang Li, Wei Xiang, Zhiyong Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add identity prior module to diffusion generator (ablation) | IC-RDN · OAI KOA progression grading (VGG-16) | accuracy (%): 61.6 -> 66.8 | Improved |
| add identity prior module (ablation) | IC-RDN · OAI KOA progression grading (DenseNet-121) | accuracy (%): 62.5 -> 64.4 | Improved |
| add identity prior module (ablation) | IC-RDN · OAI generated X-ray quality | inception score: 1.72 -> 1.98 | Improved |
| add identity prior module on ResNet-18 (ablation) | IC-RDN · OAI KOA progression grading (ResNet-18) | accuracy (%): 60.2 -> 61.1 | No clear effect |
| use I2I diffusion generated scan alongside baseline instead of baseline image only | progression grading with VGG-16 · OAI KOA progression grading (VGG-16) | accuracy (%): 66.3 -> 62.4 | Hurt |
| add IC-RDN generated 12-month scan to the baseline scan | progression grading with VGG-16 · OAI KOA progression grading (VGG-16) | accuracy (%): 66.3 -> 66.8 | Improved |
| use Cycle GAN generated scans for progression grading | progression grading · OAI KOA progression grading | accuracy (%): VGG-16 66.3 -> 62.5; VGG-19 63.3 -> 64.3 | Mixed |
| I2I diffusion vs IC-RDN on inception score | generator image quality · OAI generated X-ray quality | inception score: 2.02 vs 1.98 | No clear effect |
Closest papers by meaning
- From Representation Space to Prognostic Insights: Whole Slide Image Generation with Hierarchical Diffusion Model for Survival Prediction (AAAI 2025 · similarity 0.80)
- VidSole: A Multimodal Dataset for Joint Kinetics Quantification and Disease Detection with Deep Learning (AAAI 2025 · similarity 0.80)
- Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis (CVPR 2025 · similarity 0.80)
- Trade-Offs in Fine-Tuned Diffusion Models between Accuracy and Interpretability (AAAI 2024 · similarity 0.80)
- Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI (NeurIPS 2024 · similarity 0.80)
- Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers? (CVPR 2025 · similarity 0.80)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
