Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms

The goal of this work is to study a preprocessing method for the data measured by a two-dimensional optoacoustic tomograph in order to reduce or eliminate artifacts introduced by the low number of detectors in the experimental setup and their limited bandwidth. A generative adversarial deep neural n...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Montilla, Delfina, González, Martín German, Rey Vega, Leonardo
Formato: Artículo publishedVersion
Lenguaje:Español
Publicado: FIUBA 2023
Materias:
optoacustic tomography
machine learning
GAN
tomografía optoacústica
aprendizaje profundo
Acceso en línea:https://elektron.fi.uba.ar/elektron/article/view/180
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=180_oai
Aporte de:
Repositorio Digital de la Universidad de Buenos Aires (UBA) de Universidad de Buenos Aires
id I28-R145-180_oai
record_format dspace
spelling I28-R145-180_oai2026-02-11 Montilla, Delfina González, Martín German Rey Vega, Leonardo 2023-06-15 The goal of this work is to study a preprocessing method for the data measured by a two-dimensional optoacoustic tomograph in order to reduce or eliminate artifacts introduced by the low number of detectors in the experimental setup and their limited bandwidth. A generative adversarial deep neural network was used to accomplish this task and its performance was compared with a reference U-Net neural network. In most of the test cases carried out, a slight improvement was found by applying the proposed network when measuring the Pearson correlation and the peak signal noise ratio between the reconstructed image product of the data processed by the model and the high-resolution reference image. El objetivo de este trabajo es el estudio de un método de pre-procesamiento de los datos medidos por un tomógrafo optoacústico bidimensional para reducir o eliminar los artefactos introducidos por la escasa cantidad de detectores en el sistema experimental y el acotado ancho de banda de estos. Para esta tarea, se utilizó una red neuronal profunda generativa adversaria y se comparó su rendimiento con una red neuronal de referencia U-Net. En la mayoría de los casos de testeo realizados, se encontró una leve mejora aplicando la red propuesta al medir la correlación de Pearson y la relación señal a ruido piso entre la imagen reconstruida producto de los datos procesados por el modelo y la imagen de alta resolución de referencia. application/pdf text/html https://elektron.fi.uba.ar/elektron/article/view/180 10.37537/rev.elektron.7.1.180.2023 spa FIUBA https://elektron.fi.uba.ar/elektron/article/view/180/323 https://elektron.fi.uba.ar/elektron/article/view/180/331 Derechos de autor 2023 Delfina Montilla, Martín German González, Leonardo Rey Vega Elektron Journal; Vol. 7 No. 1 (2023); 7-18 Revista Elektron; Vol. 7 Núm. 1 (2023); 7-18 Revista Elektron; v. 7 n. 1 (2023); 7-18 2525-0159 2525-0159 optoacustic tomography machine learning GAN tomografía optoacústica aprendizaje profundo GAN Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms Red adversaria generativa aplicada a la eliminación de ruido y artefactos en sinogramas de tomografía optoacústica info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=180_oai
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-145
collection Repositorio Digital de la Universidad de Buenos Aires (UBA)
language Español
orig_language_str_mv spa
topic optoacustic tomography
machine learning
GAN
tomografía optoacústica
aprendizaje profundo
GAN
spellingShingle optoacustic tomography
machine learning
GAN
tomografía optoacústica
aprendizaje profundo
GAN
Montilla, Delfina
González, Martín German
Rey Vega, Leonardo
Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms
topic_facet optoacustic tomography
machine learning
GAN
tomografía optoacústica
aprendizaje profundo
GAN
description The goal of this work is to study a preprocessing method for the data measured by a two-dimensional optoacoustic tomograph in order to reduce or eliminate artifacts introduced by the low number of detectors in the experimental setup and their limited bandwidth. A generative adversarial deep neural network was used to accomplish this task and its performance was compared with a reference U-Net neural network. In most of the test cases carried out, a slight improvement was found by applying the proposed network when measuring the Pearson correlation and the peak signal noise ratio between the reconstructed image product of the data processed by the model and the high-resolution reference image.
format Artículo
publishedVersion
author Montilla, Delfina
González, Martín German
Rey Vega, Leonardo
author_facet Montilla, Delfina
González, Martín German
Rey Vega, Leonardo
author_sort Montilla, Delfina
title Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms
title_short Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms
title_full Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms
title_fullStr Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms
title_full_unstemmed Generative Adversarial Network Applied to the Elimination of Noise and Artifacts in Optoacoustic Tomography Sinograms
title_sort generative adversarial network applied to the elimination of noise and artifacts in optoacoustic tomography sinograms
publisher FIUBA
publishDate 2023
url https://elektron.fi.uba.ar/elektron/article/view/180
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=elektron&d=180_oai
work_keys_str_mv AT montilladelfina generativeadversarialnetworkappliedtotheeliminationofnoiseandartifactsinoptoacoustictomographysinograms
AT gonzalezmartingerman generativeadversarialnetworkappliedtotheeliminationofnoiseandartifactsinoptoacoustictomographysinograms
AT reyvegaleonardo generativeadversarialnetworkappliedtotheeliminationofnoiseandartifactsinoptoacoustictomographysinograms
AT montilladelfina redadversariagenerativaaplicadaalaeliminacionderuidoyartefactosensinogramasdetomografiaoptoacustica
AT gonzalezmartingerman redadversariagenerativaaplicadaalaeliminacionderuidoyartefactosensinogramasdetomografiaoptoacustica
AT reyvegaleonardo redadversariagenerativaaplicadaalaeliminacionderuidoyartefactosensinogramasdetomografiaoptoacustica
_version_ 1859522234960314368

Ejemplares similares