CVJun 28, 2025

Inpainting is All You Need: A Diffusion-based Augmentation Method for Semi-supervised Medical Image Segmentation

arXiv:2506.23038v11 citationsh-index: 6
Originality Incremental advance
AI Analysis

This addresses the challenge of expensive pixel-level labeling in medical imaging, though it is an incremental improvement over existing diffusion-based methods adapted for inpainting.

The paper tackles the problem of limited labeled data for medical image segmentation by introducing AugPaint, a diffusion-based augmentation method that generates synthetic image-label pairs through inpainting, which improved segmentation performance across four medical datasets and outperformed state-of-the-art label-efficient methods.

Collecting pixel-level labels for medical datasets can be a laborious and expensive process, and enhancing segmentation performance with a scarcity of labeled data is a crucial challenge. This work introduces AugPaint, a data augmentation framework that utilizes inpainting to generate image-label pairs from limited labeled data. AugPaint leverages latent diffusion models, known for their ability to generate high-quality in-domain images with low overhead, and adapts the sampling process for the inpainting task without need for retraining. Specifically, given a pair of image and label mask, we crop the area labeled with the foreground and condition on it during reversed denoising process for every noise level. Masked background area would gradually be filled in, and all generated images are paired with the label mask. This approach ensures the accuracy of match between synthetic images and label masks, setting it apart from existing dataset generation methods. The generated images serve as valuable supervision for training downstream segmentation models, effectively addressing the challenge of limited annotations. We conducted extensive evaluations of our data augmentation method on four public medical image segmentation datasets, including CT, MRI, and skin imaging. Results across all datasets demonstrate that AugPaint outperforms state-of-the-art label-efficient methodologies, significantly improving segmentation performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes