Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation
By: Fuyou Mao , Beining Wu , Yanfeng Jiang and more
Potential Business Impact:
Helps doctors see tumors more clearly in scans.
Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework that learns voxel-wise distributions while maintaining strong calibration and practical sampling efficiency. PGRD embeds discrete labels as one-hot targets in a continuous space to align segmentation with diffusion modeling. A coarse prior predictor provides step-wise guidance; the diffusion network then learns the residual to the prior, accelerating convergence and improving calibration. A deep diffusion supervision scheme further stabilizes training by supervising intermediate time steps. Evaluated on representative MRI and CT datasets, PGRD achieves higher Dice scores and lower NLL/ECE values than Bayesian, ensemble, Probabilistic U-Net, and vanilla diffusion baselines, while requiring fewer sampling steps to reach strong performance.
Similar Papers
Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models
Machine Learning (Stat)
Makes AI create more detailed and realistic pictures.
Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging
Image and Video Processing
Makes medical scans faster and clearer.
MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shifting
CV and Pattern Recognition
Makes MRI scans clearer and faster.