Skip to Main content Skip to Navigation
Journal articles

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

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.
Complete list of metadata

https://hal-cnrs.archives-ouvertes.fr/hal-03739735
Contributor : Bastien ARNAL Connect in order to contact the contributor
Submitted on : Thursday, July 28, 2022 - 10:26:19 AM
Last modification on : Wednesday, August 3, 2022 - 3:08:39 AM

File

mainSI_DL.pdf
Files produced by the author(s)

Identifiers

Collections

UGA | CNRS | LIPHY

Citation

Guillaume Godefroy, Bastien Arnal, Emmanuel Bossy. Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties. Photoacoustics, Elsevier, 2020, 21, pp.100218. ⟨10.1016/j.pacs.2020.100218⟩. ⟨hal-03739735⟩

Share

Metrics

Record views

0

Files downloads

0