AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910053527715840 |
|---|---|
| author | Heidari, Maryam Anantrasirichai, Nantheera Walker, Steven Bhatnagar, Rahul Achim, Alin |
| author_facet | Heidari, Maryam Anantrasirichai, Nantheera Walker, Steven Bhatnagar, Rahul Achim, Alin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03125 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis Heidari, Maryam Anantrasirichai, Nantheera Walker, Steven Bhatnagar, Rahul Achim, Alin Computer Vision and Pattern Recognition 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. |
| title | AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.03125 |