AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback

Shenghuan Sun, Gregory Goldgof, Atul Butte, Ahmed Alaa

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
finetune the diffusion model with pathologist feedback via reward modelconditional diffusion model · clinical plausibility of 400 synthetic imagesfraction plausible: 0.21 to 0.75Improved
finetune with pathologist feedback vs no feedbackconditional diffusion model · Precision, Recall, Coveragefidelity and diversityImproved
use automatic classifier-guidance feedback instead of pathologist feedback (ablation)conditional diffusion model · cell classification with synthetic training dataaccuracyNo clear effect
add real data augmentation to the reward model training (D_s + D_r) (ablation)reward model · cell classification with synthetic training dataaccuracyImproved
train classifier on synthetic data with pathologist feedback vs withoutResNeXt-50 classifier · 16-class cell classification on real test dataaccuracyImproved
increase pathologist-labeled images from 0% to 10%, 50%, 100% of 3,936 (ablation)reward model · cell classification with synthetic training dataaccuracyImproved
replace conditional diffusion with conditional GAN as base generator (ablation)generative model · cell classification on real test dataAUC: 0.929482 -> 0.413551Hurt
replace conditional diffusion with latent diffusion as base generator (ablation)generative model · cell classification on real test dataAUC: 0.929482 -> 0.566388Hurt
add band and segmented Neutrophil subtype annotations to the rewardfinetuned diffusion model · Neutrophil subtype classificationaccuracy: 71.88Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy