DUAL-ENERGY CBCT PRE-SPECTRAL-DECOMPOSITION FILTERING WITH WAVELETSHRINKAGE NETWORKS

Luis Zavala Mondragon

DUAL-ENERGY CBCT PRE-SPECTRAL-DECOMPOSITION FILTERING WITH WAVELETSHRINKAGE NETWORKS

Research output: Contribution to conference › Paper › Academic

Abstract

Convolutional Neural Networks (CNNs) are reshaping sig-nal processing and computer vision by providing data-drivensolutions for inverse problems such as noise reduction. How-ever, their relationship with established signal processingmethods is sometimes unclear and its development not fullyexploiting the existing knowledge. In this paper, rather thanimproving existing CNNs with wavelet transformations asexplored earlier, we improve the wavelet shrinkage approachto noise-reduction with a data-driven solution. The resultingCNN has clear encoding, decoding and processing paths.As application, we perform noise reduction in Dual-EnergyCone-Beam CT. The obtained results were compared to aUNet-like architecture, which reveal better noise-free imageswithout aliasing artifacts. This indicates that that our archi-tecture is able to preserve well the information contained inthe images because the architecture exploits explicitly theunderlying signal representation

Original language	English
Pages	1-6
Number of pages	6
Publication status	Published - 21 Sep 2020
Event	International Workshop on Machine Learning for Signal Processing 2020 - Aalto University Campus, Espoo, Finland Duration: 21 Sep 2020 → 24 Sep 2020 Conference number: 30th https://ieeemlsp.cc/

Conference

Conference	International Workshop on Machine Learning for Signal Processing 2020
Abbreviated title	MLSP 2020
Country	Finland
City	Espoo
Period	21/09/20 → 24/09/20
Internet address	https://ieeemlsp.cc/

Keywords

Convolutional neural networks, wavelets,noise-reduction, computer tomography

Access to Document

https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9231535

Fingerprint Dive into the research topics of 'DUAL-ENERGY CBCT PRE-SPECTRAL-DECOMPOSITION FILTERING WITH WAVELETSHRINKAGE NETWORKS'. Together they form a unique fingerprint.

Cite this

@conference{1ba14fe53c6c4676ab18462c4ae316ee,

title = "DUAL-ENERGY CBCT PRE-SPECTRAL-DECOMPOSITION FILTERING WITH WAVELETSHRINKAGE NETWORKS",

abstract = "Convolutional Neural Networks (CNNs) are reshaping sig-nal processing and computer vision by providing data-drivensolutions for inverse problems such as noise reduction. How-ever, their relationship with established signal processingmethods is sometimes unclear and its development not fullyexploiting the existing knowledge. In this paper, rather thanimproving existing CNNs with wavelet transformations asexplored earlier, we improve the wavelet shrinkage approachto noise-reduction with a data-driven solution. The resultingCNN has clear encoding, decoding and processing paths.As application, we perform noise reduction in Dual-EnergyCone-Beam CT. The obtained results were compared to aUNet-like architecture, which reveal better noise-free imageswithout aliasing artifacts. This indicates that that our archi-tecture is able to preserve well the information contained inthe images because the architecture exploits explicitly theunderlying signal representation",

keywords = "Convolutional neural networks, wavelets,noise-reduction, computer tomography",

author = "{Zavala Mondragon}, Luis",

year = "2020",

month = sep,

day = "21",

language = "English",

pages = "1--6",

note = "International Workshop on Machine Learning for Signal Processing 2020, MLSP 2020 ; Conference date: 21-09-2020 Through 24-09-2020",

url = "https://ieeemlsp.cc/",

}

TY - CONF

T1 - DUAL-ENERGY CBCT PRE-SPECTRAL-DECOMPOSITION FILTERING WITH WAVELETSHRINKAGE NETWORKS

AU - Zavala Mondragon, Luis

N1 - Conference code: 30th

PY - 2020/9/21

Y1 - 2020/9/21

N2 - Convolutional Neural Networks (CNNs) are reshaping sig-nal processing and computer vision by providing data-drivensolutions for inverse problems such as noise reduction. How-ever, their relationship with established signal processingmethods is sometimes unclear and its development not fullyexploiting the existing knowledge. In this paper, rather thanimproving existing CNNs with wavelet transformations asexplored earlier, we improve the wavelet shrinkage approachto noise-reduction with a data-driven solution. The resultingCNN has clear encoding, decoding and processing paths.As application, we perform noise reduction in Dual-EnergyCone-Beam CT. The obtained results were compared to aUNet-like architecture, which reveal better noise-free imageswithout aliasing artifacts. This indicates that that our archi-tecture is able to preserve well the information contained inthe images because the architecture exploits explicitly theunderlying signal representation

AB - Convolutional Neural Networks (CNNs) are reshaping sig-nal processing and computer vision by providing data-drivensolutions for inverse problems such as noise reduction. How-ever, their relationship with established signal processingmethods is sometimes unclear and its development not fullyexploiting the existing knowledge. In this paper, rather thanimproving existing CNNs with wavelet transformations asexplored earlier, we improve the wavelet shrinkage approachto noise-reduction with a data-driven solution. The resultingCNN has clear encoding, decoding and processing paths.As application, we perform noise reduction in Dual-EnergyCone-Beam CT. The obtained results were compared to aUNet-like architecture, which reveal better noise-free imageswithout aliasing artifacts. This indicates that that our archi-tecture is able to preserve well the information contained inthe images because the architecture exploits explicitly theunderlying signal representation

KW - Convolutional neural networks, wavelets,noise-reduction, computer tomography

M3 - Paper

SP - 1

EP - 6

T2 - International Workshop on Machine Learning for Signal Processing 2020

Y2 - 21 September 2020 through 24 September 2020

ER -