Affordable Access

deepdyve-link
Publisher Website

Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties.

Authors
  • Godefroy, Guillaume1
  • Arnal, Bastien1
  • Bossy, Emmanuel1
  • 1 Univ. Grenoble Alpes, CNRS, LIPhy, 38000 Grenoble, France. , (France)
Type
Published Article
Journal
Photoacoustics
Publication Date
Mar 01, 2021
Volume
21
Pages
100218–100218
Identifiers
DOI: 10.1016/j.pacs.2020.100218
PMID: 33364161
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

Conventional photoacoustic imaging may suffer from the limited view and bandwidth of ultrasound transducers. A deep learning approach is proposed to handle these problems and is demonstrated both in simulations and in experiments on a multi-scale model of leaf skeleton. We employed an experimental approach to build the training and the test sets using photographs of the samples as ground truth images. Reconstructions produced by the neural network show a greatly improved image quality as compared to conventional approaches. In addition, this work aimed at quantifying the reliability of the neural network predictions. To achieve this, the dropout Monte-Carlo procedure is applied to estimate a pixel-wise degree of confidence on each predicted picture. Last, we address the possibility to use transfer learning with simulated data in order to drastically limit the size of the experimental dataset. © 2020 The Authors.

Report this publication

Statistics

Seen <100 times