mlsanityData to 7 Oct 2026

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

arXiv 2603.03125 ↗First posted 3 Mar 2026cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 18 of its 31 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

18 of 31 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Diffusion Model-based Data Augmentation Method for Fetal Head Ultrasound Segmentation30 Jun
  2. 2025Generative augmentations for improved cardiac ultrasound segmentation using diffusion models27 Feb
  3. 2025Ultrasound Image Generation using Latent Diffusion Models12 Feb
  4. 2025Enhancing Fetal Plane Classification Accuracy with Data Augmentation Using Diffusion Models25 Jan
  5. 2023Using Diffusion Models to Generate Synthetic Labelled Data for Medical Image Segmentation25 Oct
  6. 2023Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis29 May
  7. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Survey14 Nov

Other references · 11

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  4. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 506
  5. 2017NIMA: Neural Image Assessmentcited by 387
  6. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  7. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  8. 2024Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generationcited by 9
  9. 2025FetalFlex: Anatomy-Guided Diffusion Model for Flexible Control on Fetal Ultrasound Image Synthesiscited by 4
  10. 2021Current Advances in Computational Lung Ultrasound Imaging: A Reviewcited by 1
  11. 2022A Semi-supervised Learning Approach for B-line Detection in Lung Ultrasound Imagescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024MEDDAP: Medical Dataset Enhancement via Diversified Augmentation Pipeline
  2. 2024WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis
  3. 2024Multi-Conditioned Denoising Diffusion Probabilistic Model (mDDPM) for Medical Image Synthesis
  4. 2023Fast Sampling generative model for Ultrasound image reconstruction
  5. 2023Single PW takes a shortcut to compound PW in US imaging
  6. 2026Hybrid Diffusion Model for Breast Ultrasound Image Augmentation
  7. 2022Spot the fake lungs: Generating Synthetic Medical Images using Neural Diffusion Models
  8. 2024Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms