Using denoising diffusion probabilistic models to enhance quality of limited-view photoacoustic tomography

Bruno De Santi*, Navchetan Awasthi, Srirang Manohar

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

In photoacoustic tomography (PAT), a limited angle of detector coverage around the object affects PAT image quality. Consequently, PAT images can become challenging to interpret accurately. Although deep learning methods, such as convolutional neural networks (CNNs), have shown promising results in recovering high-quality images from limited-view data, these methods suffer from loss of fine image details. Recently, denoising diffusion probabilistic models (DDPM) are gaining interest in image generation applications. Here we explore the potential of conditional denoising diffusion probabilistic models (cDDPM) to enhance quality of limited-view PAT images. The OADAT dataset consisting of 2D PAT images of healthy forearms acquired with a semicircle array of 256 ultrasound elements is used. PAT images are reconstructed using the full array (256 elements) and also the central 128, 64 and 32 elements for limited-view. The approach showed to be able to filter out limited-view streak artifacts, accurately recover shapes of vascular structures, and preserve fine-detailed texture. Conditional DDPMs show potential in improving quality of limited-view PAT reconstructions, however, they require higher computational cost compared to conventional CNNs. Future works will include the reduction of computational time and further evaluations on different datasets and array geometries.

Original languageEnglish
Title of host publicationPhotons Plus Ultrasound
Subtitle of host publicationImaging and Sensing 2024
EditorsAlexander A. Oraevsky, Lihong V. Wang
PublisherSPIE
ISBN (Electronic)9781510669437
DOIs
Publication statusPublished - 12 Mar 2024
EventPhotons Plus Ultrasound: Imaging and Sensing 2024 - San Francisco, United States
Duration: 28 Jan 202431 Jan 2024

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume12842
ISSN (Print)1605-7422

Conference

ConferencePhotons Plus Ultrasound: Imaging and Sensing 2024
Country/TerritoryUnited States
CitySan Francisco
Period28/01/2431/01/24

Keywords

  • 2024 OA procedure
  • Diffusion models
  • Limited-view
  • Photoacoustic
  • Deep learning

Fingerprint

Dive into the research topics of 'Using denoising diffusion probabilistic models to enhance quality of limited-view photoacoustic tomography'. Together they form a unique fingerprint.

Cite this