A Partially-Learned Algorithm for Joint Photo-acoustic Reconstruction and Segmentation

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available, when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this article, we propose to jointly acquire the photoacoustic reconstruction and segmentation, by modifying a recently developed partially learned algorithm based on a convolutional neural network. We investigate the stability of the algorithm against changes in initial pressures and photoacoustic system settings. These insights are used to develop an algorithm that is robust to input and system settings. Our approach can easily be applied to other imaging modalities and can be modified to perform other high-level tasks different from segmentation. The method is validated on challenging synthetic and experimental photoacoustic tomography data in limited angle and limited view scenarios. It is computationally less expensive than classical iterative methods and enables higher quality reconstructions and segmentations than the state-of-the-art learned and non-learned methods.

Original languageEnglish
Article number8734097
Pages (from-to)129-139
Number of pages11
JournalIEEE transactions on medical imaging
Volume39
Issue number1
Early online date1 Jun 2019
DOIs
Publication statusPublished - 1 Jan 2020

Fingerprint

Photoacoustic effect
Acoustics
Joints
Pressure
Iterative methods
Image segmentation
Tomography
Blood Vessels
Neural networks
Imaging techniques
Geometry
Processing

Cite this

@article{de0f546d8ad24eeaacbb33db80dbcd7c,
title = "A Partially-Learned Algorithm for Joint Photo-acoustic Reconstruction and Segmentation",
abstract = "In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available, when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this article, we propose to jointly acquire the photoacoustic reconstruction and segmentation, by modifying a recently developed partially learned algorithm based on a convolutional neural network. We investigate the stability of the algorithm against changes in initial pressures and photoacoustic system settings. These insights are used to develop an algorithm that is robust to input and system settings. Our approach can easily be applied to other imaging modalities and can be modified to perform other high-level tasks different from segmentation. The method is validated on challenging synthetic and experimental photoacoustic tomography data in limited angle and limited view scenarios. It is computationally less expensive than classical iterative methods and enables higher quality reconstructions and segmentations than the state-of-the-art learned and non-learned methods.",
author = "Boink, {Yoeri E.} and Srirang Manohar and Christoph Brune",
year = "2020",
month = "1",
day = "1",
doi = "10.1109/TMI.2019.2922026",
language = "English",
volume = "39",
pages = "129--139",
journal = "IEEE transactions on medical imaging",
issn = "0278-0062",
publisher = "IEEE",
number = "1",

}

A Partially-Learned Algorithm for Joint Photo-acoustic Reconstruction and Segmentation. / Boink, Yoeri E.; Manohar, Srirang; Brune, Christoph.

In: IEEE transactions on medical imaging, Vol. 39, No. 1, 8734097, 01.01.2020, p. 129-139.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A Partially-Learned Algorithm for Joint Photo-acoustic Reconstruction and Segmentation

AU - Boink, Yoeri E.

AU - Manohar, Srirang

AU - Brune, Christoph

PY - 2020/1/1

Y1 - 2020/1/1

N2 - In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available, when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this article, we propose to jointly acquire the photoacoustic reconstruction and segmentation, by modifying a recently developed partially learned algorithm based on a convolutional neural network. We investigate the stability of the algorithm against changes in initial pressures and photoacoustic system settings. These insights are used to develop an algorithm that is robust to input and system settings. Our approach can easily be applied to other imaging modalities and can be modified to perform other high-level tasks different from segmentation. The method is validated on challenging synthetic and experimental photoacoustic tomography data in limited angle and limited view scenarios. It is computationally less expensive than classical iterative methods and enables higher quality reconstructions and segmentations than the state-of-the-art learned and non-learned methods.

AB - In an inhomogeneously illuminated photoacoustic image, important information like vascular geometry is not readily available, when only the initial pressure is reconstructed. To obtain the desired information, algorithms for image segmentation are often applied as a post-processing step. In this article, we propose to jointly acquire the photoacoustic reconstruction and segmentation, by modifying a recently developed partially learned algorithm based on a convolutional neural network. We investigate the stability of the algorithm against changes in initial pressures and photoacoustic system settings. These insights are used to develop an algorithm that is robust to input and system settings. Our approach can easily be applied to other imaging modalities and can be modified to perform other high-level tasks different from segmentation. The method is validated on challenging synthetic and experimental photoacoustic tomography data in limited angle and limited view scenarios. It is computationally less expensive than classical iterative methods and enables higher quality reconstructions and segmentations than the state-of-the-art learned and non-learned methods.

UR - http://www.scopus.com/inward/record.url?scp=85077489453&partnerID=8YFLogxK

U2 - 10.1109/TMI.2019.2922026

DO - 10.1109/TMI.2019.2922026

M3 - Article

C2 - 31180846

AN - SCOPUS:85077489453

VL - 39

SP - 129

EP - 139

JO - IEEE transactions on medical imaging

JF - IEEE transactions on medical imaging

SN - 0278-0062

IS - 1

M1 - 8734097

ER -