Abstract

In our recent work [1], we proposed a Bayesian uncertainty quantification method for large scale imaging inverse problems. It aims to analyse the confidence in specific structures observed in maximum a posteriori (MAP) estimates (e.g., lesions in medical imaging, celestial sources in astronomical imaging), assuming a log-concave Bayesian model. This information can subsequently be used as evidence to inform decisions and conclusions. We propose to perform a hypothesis test on the structures of interest, to assert their uncertainty. The test is formulated as a convex minimisation problem, enabling the use of advanced optimisation algorithms. In this abstract we summarise the proposed Bayesian Uncertainty Quantification by Optimisation (BUQO) method and we provide results obtained on real data in the context of radio-astronomical imaging.
Original languageEnglish
Number of pages1
Publication statusPublished - Feb 2019
EventInternational BASP Frontiers workshop 2019 - Villars sur Ollon, Switzerland
Duration: 3 Feb 20198 Feb 2019
http://www.baspfrontiers.org

Workshop

WorkshopInternational BASP Frontiers workshop 2019
CountrySwitzerland
CityVillars sur Ollon
Period3/02/198/02/19
Internet address

Fingerprint

Imaging techniques
Medical imaging
Inverse problems
Uncertainty

Cite this

Repetti, A., Pereyra, M. A., & Wiaux, Y. (2019). Uncertainty Quantification in Astro-Imaging by Optimisation. Paper presented at International BASP Frontiers workshop 2019, Villars sur Ollon, Switzerland.
Repetti, Audrey ; Pereyra, Marcelo A. ; Wiaux, Yves. / Uncertainty Quantification in Astro-Imaging by Optimisation. Paper presented at International BASP Frontiers workshop 2019, Villars sur Ollon, Switzerland.1 p.
@conference{a304dc289a844cd0949cc3303983daf2,
title = "Uncertainty Quantification in Astro-Imaging by Optimisation",
abstract = "In our recent work [1], we proposed a Bayesian uncertainty quantification method for large scale imaging inverse problems. It aims to analyse the confidence in specific structures observed in maximum a posteriori (MAP) estimates (e.g., lesions in medical imaging, celestial sources in astronomical imaging), assuming a log-concave Bayesian model. This information can subsequently be used as evidence to inform decisions and conclusions. We propose to perform a hypothesis test on the structures of interest, to assert their uncertainty. The test is formulated as a convex minimisation problem, enabling the use of advanced optimisation algorithms. In this abstract we summarise the proposed Bayesian Uncertainty Quantification by Optimisation (BUQO) method and we provide results obtained on real data in the context of radio-astronomical imaging.",
author = "Audrey Repetti and Pereyra, {Marcelo A.} and Yves Wiaux",
year = "2019",
month = "2",
language = "English",
note = "International BASP Frontiers workshop 2019 ; Conference date: 03-02-2019 Through 08-02-2019",
url = "http://www.baspfrontiers.org",

}

Repetti, A, Pereyra, MA & Wiaux, Y 2019, 'Uncertainty Quantification in Astro-Imaging by Optimisation' Paper presented at International BASP Frontiers workshop 2019, Villars sur Ollon, Switzerland, 3/02/19 - 8/02/19, .

Uncertainty Quantification in Astro-Imaging by Optimisation. / Repetti, Audrey; Pereyra, Marcelo A.; Wiaux, Yves.

2019. Paper presented at International BASP Frontiers workshop 2019, Villars sur Ollon, Switzerland.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Uncertainty Quantification in Astro-Imaging by Optimisation

AU - Repetti, Audrey

AU - Pereyra, Marcelo A.

AU - Wiaux, Yves

PY - 2019/2

Y1 - 2019/2

N2 - In our recent work [1], we proposed a Bayesian uncertainty quantification method for large scale imaging inverse problems. It aims to analyse the confidence in specific structures observed in maximum a posteriori (MAP) estimates (e.g., lesions in medical imaging, celestial sources in astronomical imaging), assuming a log-concave Bayesian model. This information can subsequently be used as evidence to inform decisions and conclusions. We propose to perform a hypothesis test on the structures of interest, to assert their uncertainty. The test is formulated as a convex minimisation problem, enabling the use of advanced optimisation algorithms. In this abstract we summarise the proposed Bayesian Uncertainty Quantification by Optimisation (BUQO) method and we provide results obtained on real data in the context of radio-astronomical imaging.

AB - In our recent work [1], we proposed a Bayesian uncertainty quantification method for large scale imaging inverse problems. It aims to analyse the confidence in specific structures observed in maximum a posteriori (MAP) estimates (e.g., lesions in medical imaging, celestial sources in astronomical imaging), assuming a log-concave Bayesian model. This information can subsequently be used as evidence to inform decisions and conclusions. We propose to perform a hypothesis test on the structures of interest, to assert their uncertainty. The test is formulated as a convex minimisation problem, enabling the use of advanced optimisation algorithms. In this abstract we summarise the proposed Bayesian Uncertainty Quantification by Optimisation (BUQO) method and we provide results obtained on real data in the context of radio-astronomical imaging.

M3 - Paper

ER -

Repetti A, Pereyra MA, Wiaux Y. Uncertainty Quantification in Astro-Imaging by Optimisation. 2019. Paper presented at International BASP Frontiers workshop 2019, Villars sur Ollon, Switzerland.