Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising

Michael Green; Edith M. Marom; Eli Konen; Nahum Kiryati; Arnaldo Mayer

doi:10.1109/ISBI.2019.8759323

Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising

Michael Green, Edith M. Marom, Eli Konen, Nahum Kiryati, Arnaldo Mayer

Tel Aviv University

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

Abstract

Lung cancer CT screening programs are continuously reducing patient exposure to radiation at the expense of image quality. State-of-the-art denoising algorithms are instrumental in preserving the diagnostic value of these images. In this work, a novel neural denoising scheme is proposed for ULD chest CT. The proposed method aggregates multi-scale features that provide rich information for the computation of a perceptive loss. The loss is further optimized for chest CT data by using denoising auto-encoders on real CT images to build the feature extracting network instead of using an existing network trained on natural images. The proposed method was validated on co-registered pairs of real ULD and normal dose scans and compared favorably with published state-of-the-art denoising networks both qualitatively and quantitatively.

Original language	American English
Title of host publication	ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Pages	1635-1638
Number of pages	4
ISBN (Electronic)	9781538636411
DOIs	https://doi.org/10.1109/ISBI.2019.8759323
State	Published - 1 Apr 2019
Event	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy Duration: 8 Apr 2019 → 11 Apr 2019

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2019-April

Conference

Conference	16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
Country/Territory	Italy
City	Venice
Period	8/04/19 → 11/04/19

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Convolutional neural networks
Features aggregation
Image denoising
Perceptual loss
Ultra-low-dose CT

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2019.8759323

Cite this

Green, M., Marom, E. M., Konen, E., Kiryati, N., & Mayer, A. (2019). Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 1635-1638). Article 8759323 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April). https://doi.org/10.1109/ISBI.2019.8759323

@inproceedings{ec145585f3ff4a09baa3d20f5541b997,

title = "Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising",

abstract = "Lung cancer CT screening programs are continuously reducing patient exposure to radiation at the expense of image quality. State-of-the-art denoising algorithms are instrumental in preserving the diagnostic value of these images. In this work, a novel neural denoising scheme is proposed for ULD chest CT. The proposed method aggregates multi-scale features that provide rich information for the computation of a perceptive loss. The loss is further optimized for chest CT data by using denoising auto-encoders on real CT images to build the feature extracting network instead of using an existing network trained on natural images. The proposed method was validated on co-registered pairs of real ULD and normal dose scans and compared favorably with published state-of-the-art denoising networks both qualitatively and quantitatively.",

keywords = "Convolutional neural networks, Features aggregation, Image denoising, Perceptual loss, Ultra-low-dose CT",

author = "Michael Green and Marom, {Edith M.} and Eli Konen and Nahum Kiryati and Arnaldo Mayer",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

year = "2019",

month = apr,

day = "1",

doi = "10.1109/ISBI.2019.8759323",

language = "American English",

series = "Proceedings - International Symposium on Biomedical Imaging",

pages = "1635--1638",

booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

}

Green, M, Marom, EM, Konen, E, Kiryati, N & Mayer, A 2019, Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759323, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, pp. 1635-1638, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 8/04/19. https://doi.org/10.1109/ISBI.2019.8759323

Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising. / Green, Michael; Marom, Edith M.; Konen, Eli et al.
ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. 2019. p. 1635-1638 8759323 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

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

TY - GEN

T1 - Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising

AU - Green, Michael

AU - Marom, Edith M.

AU - Konen, Eli

AU - Kiryati, Nahum

AU - Mayer, Arnaldo

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Lung cancer CT screening programs are continuously reducing patient exposure to radiation at the expense of image quality. State-of-the-art denoising algorithms are instrumental in preserving the diagnostic value of these images. In this work, a novel neural denoising scheme is proposed for ULD chest CT. The proposed method aggregates multi-scale features that provide rich information for the computation of a perceptive loss. The loss is further optimized for chest CT data by using denoising auto-encoders on real CT images to build the feature extracting network instead of using an existing network trained on natural images. The proposed method was validated on co-registered pairs of real ULD and normal dose scans and compared favorably with published state-of-the-art denoising networks both qualitatively and quantitatively.

AB - Lung cancer CT screening programs are continuously reducing patient exposure to radiation at the expense of image quality. State-of-the-art denoising algorithms are instrumental in preserving the diagnostic value of these images. In this work, a novel neural denoising scheme is proposed for ULD chest CT. The proposed method aggregates multi-scale features that provide rich information for the computation of a perceptive loss. The loss is further optimized for chest CT data by using denoising auto-encoders on real CT images to build the feature extracting network instead of using an existing network trained on natural images. The proposed method was validated on co-registered pairs of real ULD and normal dose scans and compared favorably with published state-of-the-art denoising networks both qualitatively and quantitatively.

KW - Convolutional neural networks

KW - Features aggregation

KW - Image denoising

KW - Perceptual loss

KW - Ultra-low-dose CT

UR - http://www.scopus.com/inward/record.url?scp=85073904947&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759323

DO - 10.1109/ISBI.2019.8759323

M3 - Conference contribution

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1635

EP - 1638

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

T2 - 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019

Y2 - 8 April 2019 through 11 April 2019

ER -

Feature aggregation in perceptual loss for ultra low-dose (ULD) CT denoising

Abstract

Publication series

Conference

UN SDGs

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this