PET Image Super Resolution using Convolutional Neural Networks

Farnaz Garehdaghi; Saeed Meshgini; Reza Afrouzian; Ali Farzamnia

doi:10.1109/ICSPIS48872.2019.9066120

PET Image Super Resolution using Convolutional Neural Networks

Farnaz Garehdaghi, Saeed Meshgini, Reza Afrouzian, Ali Farzamnia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

Positron Emission Tomography (PET) is a nuclear, in-vivo medical imaging technology which can make 3D images of tissue metabolic act, in which high dose of tracer is needed to obtain a high quality PET image, which affects patients' health. Due to the limitations of using high dose tracer and limitations of physical imaging systems, it is not easy to get an image in desired resolution. Simplest approach to generate a high resolution image is by post processing. Single Image Super Resolution (SISR) is a post processing procedure to retrieve a high resolution image from a low resolution input. We propose a convolutional neural network trained on PET images which can estimate a high resolution PET image from its input low resolution image.

Original language	English
Title of host publication	5th Iranian Conference on Signal Processing and Intelligent Systems, ICSPIS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	5
ISBN (Electronic)	9781728153506
ISBN (Print)	9781728153513
DOIs	https://doi.org/10.1109/ICSPIS48872.2019.9066120
Publication status	Published - 16 Apr 2019
Externally published	Yes
Event	5th Iranian Conference on Signal Processing and Intelligent Systems, - Shahrood, Iran, Islamic Republic of Duration: 18 Dec 2019 → 19 Dec 2019 Conference number: 5

Conference

Conference	5th Iranian Conference on Signal Processing and Intelligent Systems,
Abbreviated title	ICSPIS 2019
Country/Territory	Iran, Islamic Republic of
City	Shahrood
Period	18/12/19 → 19/12/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICSPIS48872.2019.9066120Licence: Unspecified

Cite this

@inproceedings{4a227412bd1c4c07a72b4fb24ec1cb0a,

title = "PET Image Super Resolution using Convolutional Neural Networks",

abstract = "Positron Emission Tomography (PET) is a nuclear, in-vivo medical imaging technology which can make 3D images of tissue metabolic act, in which high dose of tracer is needed to obtain a high quality PET image, which affects patients' health. Due to the limitations of using high dose tracer and limitations of physical imaging systems, it is not easy to get an image in desired resolution. Simplest approach to generate a high resolution image is by post processing. Single Image Super Resolution (SISR) is a post processing procedure to retrieve a high resolution image from a low resolution input. We propose a convolutional neural network trained on PET images which can estimate a high resolution PET image from its input low resolution image.",

keywords = "Position emission tomography, tracer, exposure, single image super resolution",

author = "Farnaz Garehdaghi and Saeed Meshgini and Reza Afrouzian and Ali Farzamnia",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 5th Iranian Conference on Signal Processing and Intelligent Systems, , ICSPIS 2019 ; Conference date: 18-12-2019 Through 19-12-2019",

year = "2019",

month = apr,

day = "16",

doi = "10.1109/ICSPIS48872.2019.9066120",

language = "English",

isbn = "9781728153513",

booktitle = "5th Iranian Conference on Signal Processing and Intelligent Systems, ICSPIS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Garehdaghi, F, Meshgini, S, Afrouzian, R & Farzamnia, A 2019, PET Image Super Resolution using Convolutional Neural Networks. in 5th Iranian Conference on Signal Processing and Intelligent Systems, ICSPIS 2019., 9066120, Institute of Electrical and Electronics Engineers Inc., 5th Iranian Conference on Signal Processing and Intelligent Systems, , Shahrood, Iran, Islamic Republic of, 18/12/19. https://doi.org/10.1109/ICSPIS48872.2019.9066120

PET Image Super Resolution using Convolutional Neural Networks. / Garehdaghi, Farnaz; Meshgini, Saeed; Afrouzian, Reza et al.

5th Iranian Conference on Signal Processing and Intelligent Systems, ICSPIS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9066120.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - PET Image Super Resolution using Convolutional Neural Networks

AU - Garehdaghi, Farnaz

AU - Meshgini, Saeed

AU - Afrouzian, Reza

AU - Farzamnia, Ali

N1 - Conference code: 5

PY - 2019/4/16

Y1 - 2019/4/16

N2 - Positron Emission Tomography (PET) is a nuclear, in-vivo medical imaging technology which can make 3D images of tissue metabolic act, in which high dose of tracer is needed to obtain a high quality PET image, which affects patients' health. Due to the limitations of using high dose tracer and limitations of physical imaging systems, it is not easy to get an image in desired resolution. Simplest approach to generate a high resolution image is by post processing. Single Image Super Resolution (SISR) is a post processing procedure to retrieve a high resolution image from a low resolution input. We propose a convolutional neural network trained on PET images which can estimate a high resolution PET image from its input low resolution image.

AB - Positron Emission Tomography (PET) is a nuclear, in-vivo medical imaging technology which can make 3D images of tissue metabolic act, in which high dose of tracer is needed to obtain a high quality PET image, which affects patients' health. Due to the limitations of using high dose tracer and limitations of physical imaging systems, it is not easy to get an image in desired resolution. Simplest approach to generate a high resolution image is by post processing. Single Image Super Resolution (SISR) is a post processing procedure to retrieve a high resolution image from a low resolution input. We propose a convolutional neural network trained on PET images which can estimate a high resolution PET image from its input low resolution image.

KW - Position emission tomography

KW - tracer

KW - exposure

KW - single image super resolution

UR - http://www.scopus.com/inward/record.url?scp=85084093736&partnerID=8YFLogxK

U2 - 10.1109/ICSPIS48872.2019.9066120

DO - 10.1109/ICSPIS48872.2019.9066120

M3 - Conference contribution

AN - SCOPUS:85084093736

SN - 9781728153513

BT - 5th Iranian Conference on Signal Processing and Intelligent Systems, ICSPIS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th Iranian Conference on Signal Processing and Intelligent Systems,

Y2 - 18 December 2019 through 19 December 2019

ER -

PET Image Super Resolution using Convolutional Neural Networks

Abstract

Conference

UN SDGs

Access to Document

Other files and links

Cite this