Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction

Odysseas Pappas; Jonathan Mamou; Adrian Basarab; Denis Kouamé; Alin Achim

doi:10.1109/ICASSP49660.2025.10889680

Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction

Odysseas Pappas, Jonathan Mamou, Adrian Basarab, Denis Kouamé, Alin Achim

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

3 Downloads (Pure)

Abstract

Quantitative Acoustic Microscopy (QAM) is an imaging technology utilising high frequency ultrasound to produce quantitative two-dimensional (2D) maps of acoustical and mechanical properties of biological tissue at microscopy scale. Increased frequency QAM allows for finer resolution at the expense of increased acquisition times and data storage cost. Compressive sampling (CS) methods have been employed to produce QAM images from a reduced sample set, with recent state of the art utilising Approximate Message Passing (AMP) methods. In this paper we investigate the use of AMP-Net, a deep unfolded model for AMP, for the CS reconstruction of QAM parametric maps. Results indicate that AMP-Net can offer superior reconstruction performance even in its stock configuration trained on natural imagery (up to 63% in terms of PSNR), while avoiding the emergence of sampling pattern related artefacts.

Original language	English
Title of host publication	ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-5
Number of pages	5
ISBN (Electronic)	9798350368741
ISBN (Print)	9798350368758
DOIs	https://doi.org/10.1109/ICASSP49660.2025.10889680
Publication status	Published - 7 Mar 2025
Event	2025 International Conference on Acoustics, Speech, and Signal Processing - Hyderabad, India Duration: 6 Apr 2025 → 11 Apr 2025 https://2025.ieeeicassp.org/

Publication series

Name	International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Publisher	IEEE
Volume	2025
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	2025 International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP 2025
Country/Territory	India
City	Hyderabad
Period	6/04/25 → 11/04/25
Internet address	https://2025.ieeeicassp.org/

Bibliographical note

Publisher Copyright:
© 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

Keywords

Training
Time-frequency analysis
Ultrasonic imaging
Quadrature amplitude modulation
Microscopy
Message passing
Two-dimensional displays
Acoustics
Speech processing
Image reconstruction
Approximate message passing (AMP)
deep unfolding
quantitative acoustic microscopy (QAM)
compressive sensing (CS)

Access to Document

10.1109/ICASSP49660.2025.10889680

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM) of the article which has been made Open Access under the University of Bristol's Scholarly Works Policy. The final published version (Version of Record) can be found on the publisher's website. The copyright of any third-party content, such as images, remains with the copyright holder.
Accepted author manuscript, 4.97 MBLicence: CC BY

Handle.net

Persistent link

Cite this

Pappas, O., Mamou, J., Basarab, A., Kouamé, D., & Achim, A. (2025). Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction. In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). (International Conference on Acoustics, Speech, and Signal Processing (ICASSP); Vol. 2025). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP49660.2025.10889680

Pappas, Odysseas ; Mamou, Jonathan ; Basarab, Adrian et al. / Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers (IEEE), 2025. pp. 1-5 (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)).

@inproceedings{fc655abd998a4e13bcb40f01dc90a5e3,

title = "Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction",

abstract = "Quantitative Acoustic Microscopy (QAM) is an imaging technology utilising high frequency ultrasound to produce quantitative two-dimensional (2D) maps of acoustical and mechanical properties of biological tissue at microscopy scale. Increased frequency QAM allows for finer resolution at the expense of increased acquisition times and data storage cost. Compressive sampling (CS) methods have been employed to produce QAM images from a reduced sample set, with recent state of the art utilising Approximate Message Passing (AMP) methods. In this paper we investigate the use of AMP-Net, a deep unfolded model for AMP, for the CS reconstruction of QAM parametric maps. Results indicate that AMP-Net can offer superior reconstruction performance even in its stock configuration trained on natural imagery (up to 63\% in terms of PSNR), while avoiding the emergence of sampling pattern related artefacts.",

keywords = "Training, Time-frequency analysis, Ultrasonic imaging, Quadrature amplitude modulation, Microscopy, Message passing, Two-dimensional displays, Acoustics, Speech processing, Image reconstruction, Approximate message passing (AMP), deep unfolding, quantitative acoustic microscopy (QAM), compressive sensing (CS)",

author = "Odysseas Pappas and Jonathan Mamou and Adrian Basarab and Denis Kouam{\'e} and Alin Achim",

note = "Publisher Copyright: {\textcopyright} 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.; 2025 International Conference on Acoustics, Speech, and Signal Processing<br/>, ICASSP 2025 ; Conference date: 06-04-2025 Through 11-04-2025",

year = "2025",

month = mar,

day = "7",

doi = "10.1109/ICASSP49660.2025.10889680",

language = "English",

isbn = "9798350368758",

series = "International Conference on Acoustics, Speech, and Signal Processing (ICASSP)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1--5",

booktitle = "ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

url = "https://2025.ieeeicassp.org/",

}

Pappas, O, Mamou, J, Basarab, A, Kouamé, D & Achim, A 2025, Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction. in ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2025, Institute of Electrical and Electronics Engineers (IEEE), pp. 1-5, 2025 International Conference on Acoustics, Speech, and Signal Processing
, Hyderabad, India, 6/04/25. https://doi.org/10.1109/ICASSP49660.2025.10889680

Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction. / Pappas, Odysseas; Mamou, Jonathan; Basarab, Adrian et al.
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers (IEEE), 2025. p. 1-5 (International Conference on Acoustics, Speech, and Signal Processing (ICASSP); Vol. 2025).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction

AU - Pappas, Odysseas

AU - Mamou, Jonathan

AU - Basarab, Adrian

AU - Kouamé, Denis

AU - Achim, Alin

PY - 2025/3/7

Y1 - 2025/3/7

N2 - Quantitative Acoustic Microscopy (QAM) is an imaging technology utilising high frequency ultrasound to produce quantitative two-dimensional (2D) maps of acoustical and mechanical properties of biological tissue at microscopy scale. Increased frequency QAM allows for finer resolution at the expense of increased acquisition times and data storage cost. Compressive sampling (CS) methods have been employed to produce QAM images from a reduced sample set, with recent state of the art utilising Approximate Message Passing (AMP) methods. In this paper we investigate the use of AMP-Net, a deep unfolded model for AMP, for the CS reconstruction of QAM parametric maps. Results indicate that AMP-Net can offer superior reconstruction performance even in its stock configuration trained on natural imagery (up to 63% in terms of PSNR), while avoiding the emergence of sampling pattern related artefacts.

AB - Quantitative Acoustic Microscopy (QAM) is an imaging technology utilising high frequency ultrasound to produce quantitative two-dimensional (2D) maps of acoustical and mechanical properties of biological tissue at microscopy scale. Increased frequency QAM allows for finer resolution at the expense of increased acquisition times and data storage cost. Compressive sampling (CS) methods have been employed to produce QAM images from a reduced sample set, with recent state of the art utilising Approximate Message Passing (AMP) methods. In this paper we investigate the use of AMP-Net, a deep unfolded model for AMP, for the CS reconstruction of QAM parametric maps. Results indicate that AMP-Net can offer superior reconstruction performance even in its stock configuration trained on natural imagery (up to 63% in terms of PSNR), while avoiding the emergence of sampling pattern related artefacts.

KW - Training

KW - Time-frequency analysis

KW - Ultrasonic imaging

KW - Quadrature amplitude modulation

KW - Microscopy

KW - Message passing

KW - Two-dimensional displays

KW - Acoustics

KW - Speech processing

KW - Image reconstruction

KW - Approximate message passing (AMP)

KW - deep unfolding

KW - quantitative acoustic microscopy (QAM)

KW - compressive sensing (CS)

U2 - 10.1109/ICASSP49660.2025.10889680

DO - 10.1109/ICASSP49660.2025.10889680

M3 - Conference Contribution (Conference Proceeding)

SN - 9798350368758

T3 - International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

SP - 1

EP - 5

BT - ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2025 International Conference on Acoustics, Speech, and Signal Processing<br/>

Y2 - 6 April 2025 through 11 April 2025

ER -

Pappas O, Mamou J, Basarab A, Kouamé D, Achim A. Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction. In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers (IEEE). 2025. p. 1-5. (International Conference on Acoustics, Speech, and Signal Processing (ICASSP)). doi: 10.1109/ICASSP49660.2025.10889680

Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this