Diff-Lung: Diffusion-Based Texture Synthesis for Enhanced Pathological Tissue Segmentation in Lung CT Scans

TL;DR

This paper introduces Diff-Lung, a diffusion-based data augmentation method that improves lung tissue segmentation accuracy in CT scans by generating realistic synthetic pathological patches, especially for underrepresented classes.

Contribution

The paper presents a novel diffusion model for augmenting training data with realistic pathological tissue patches, enhancing segmentation of rare lung abnormalities.

Findings

Improved segmentation accuracy across all tissue types.

Significant enhancement for rare pathological patterns.

Better clinical decision support through reliable automated analysis.

Abstract

Accurate quantification of the extent of lung pathological patterns (fibrosis, ground-glass opacity, emphysema, consolidation) is prerequisite for diagnosis and follow-up of interstitial lung diseases. However, segmentation is challenging due to the significant class imbalance between healthy and pathological tissues. This paper addresses this issue by leveraging a diffusion model for data augmentation applied during training an AI model. Our approach generates synthetic pathological tissue patches while preserving essential shape characteristics and intricate details specific to each tissue type. This method enhances the segmentation process by increasing the occurence of underrepresented classes in the training data. We demonstrate that our diffusion-based augmentation technique improves segmentation accuracy across all pathological tissue types, particularly for the less common patterns. This advancement contributes to more reliable automated analysis of lung CT scans, potentially improving clinical decision-making and patient outcomes