Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties - Archive ouverte HAL Access content directly
Journal Articles Photoacoustics Year : 2020

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

(1) , (1) , (1)
1

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.
Fichier principal
Vignette du fichier
mainSI_DL.pdf (1.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03739735 , version 1 (28-07-2022)

Identifiers

Cite

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

Collections

UGA CNRS LIPHY
4 View
7 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More