Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis

Maryam Heidari, Nantheera Anantrasirichai, Steven Walker, Rahul Bhatnagar, Alin Achim

TL;DR

A trous Wavelet Diffusion (AWDiff) is proposed, a diffusion based augmentation framework that integrates the a trous wavelet transform to preserve fine-scale structures while avoiding destructive downsampling on a LUS dataset.

Abstract

Lung ultrasound (LUS) is a safe and portable imaging modality, but the scarcity of data limits the development of machine learning methods for image interpretation and disease monitoring. Existing generative augmentation methods, such as Generative Adversarial Networks (GANs) and diffusion models, often lose subtle diagnostic cues due to resolution reduction, particularly B-lines and pleural irregularities. We propose A trous Wavelet Diffusion (AWDiff), a diffusion based augmentation framework that integrates the a trous wavelet transform to preserve fine-scale structures while avoiding destructive downsampling. In addition, semantic conditioning with BioMedCLIP, a vision language foundation model trained on large scale biomedical corpora, enforces alignment with clinically meaningful labels. On a LUS dataset, AWDiff achieved lower distortion and higher perceptual quality compared to existing methods, demonstrating both structural fidelity and clinical diversity.

AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis

TL;DR

A trous Wavelet Diffusion (AWDiff) is proposed, a diffusion based augmentation framework that integrates the a trous wavelet transform to preserve fine-scale structures while avoiding destructive downsampling on a LUS dataset.

Abstract

Lung ultrasound (LUS) is a safe and portable imaging modality, but the scarcity of data limits the development of machine learning methods for image interpretation and disease monitoring. Existing generative augmentation methods, such as Generative Adversarial Networks (GANs) and diffusion models, often lose subtle diagnostic cues due to resolution reduction, particularly B-lines and pleural irregularities. We propose A trous Wavelet Diffusion (AWDiff), a diffusion based augmentation framework that integrates the a trous wavelet transform to preserve fine-scale structures while avoiding destructive downsampling. In addition, semantic conditioning with BioMedCLIP, a vision language foundation model trained on large scale biomedical corpora, enforces alignment with clinically meaningful labels. On a LUS dataset, AWDiff achieved lower distortion and higher perceptual quality compared to existing methods, demonstrating both structural fidelity and clinical diversity.
Paper Structure (11 sections, 13 equations, 4 figures, 1 table)

This paper contains 11 sections, 13 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. AWDiff: Proposed Method
  3. Problem Formulation
  4. A trous–Wavelet Encoder
  5. Semantic Conditioning with BioMedCLIP
  6. Conditional Sampling
  7. Loss Functions
  8. Experimental Results
  9. Dataset and Training Setup
  10. Evaluation and Analysis
  11. Conclusion

Figures (4)

  • Figure 1: Overview of the proposed AWDiff framework. In the forward diffusion stage, the input image is decomposed by a multi-scale a trous wavelet encoder into wavelet planes (wps) that preserve fine anatomical detail. These wavelet features are then fused with BioMedCLIP embeddings during the reverse diffusion process.
  • Figure 2: Comparison of AWDiff, SinDDM, and SinGAN on four training images, with three generated samples per method. AWDiff more faithfully preserves B-line structures compared to SinDDM and SinGAN.
  • Figure 3: LPIPS score for AWDiff, SinDDM, and SinGAN.
  • Figure 4: CW-SSIM comparison between à trous and DWT.