Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom

Mingdong Fan; Zhongxing Zhou; Thomas Vrieze; Jia Wang; Cynthia McCollough; Lifeng Yu

doi:10.1117/12.2612414

Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom

Mingdong Fan, Zhongxing Zhou, Thomas Vrieze, Jia Wang, Cynthia McCollough, Lifeng Yu

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

Abstract

Channelized Hotelling observer (CHO), which has been shown to be well correlated with human observer performance in many clinical CT tasks, has a great potential to become the method of choice for objective image quality assessment. However, its use has been quite limited in routine CT practice due to lack of efficient implementation. In this work, a CHO model optimized for the most widely used ACR CT accreditation phantom was applied to evaluate the low-contrast detectability of a deep-learning based reconstruction (DLIR) equipped on a GE Revolution scanner. The commercially available DLIR reconstruction method showed consistent increase in low-contrast detectability over the FBP and the IR method at routine dose levels, which suggests potential dose reduction to the FBP reconstruction by up to 27.5%.

Original language	English (US)
Title of host publication	Medical Imaging 2022
Subtitle of host publication	Physics of Medical Imaging
Editors	Wei Zhao, Lifeng Yu
Publisher	SPIE
ISBN (Electronic)	9781510649378
DOIs	https://doi.org/10.1117/12.2612414
State	Published - 2022
Event	Medical Imaging 2022: Physics of Medical Imaging - Virtual, Online Duration: Mar 21 2022 → Mar 27 2022

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	12031
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2022: Physics of Medical Imaging
City	Virtual, Online
Period	3/21/22 → 3/27/22

Keywords

Image quality assessment
channelized Hotelling observer (CHO)
protocol optimization
radiation dose reduction

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Atomic and Molecular Physics, and Optics
Biomaterials
Radiology Nuclear Medicine and imaging

Access to Document

10.1117/12.2612414

Cite this

Fan, M., Zhou, Z., Vrieze, T., Wang, J., McCollough, C., & Yu, L. (2022). Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom. In W. Zhao, & L. Yu (Eds.), Medical Imaging 2022: Physics of Medical Imaging Article 1203118 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12031). SPIE. https://doi.org/10.1117/12.2612414

Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom. / Fan, Mingdong; Zhou, Zhongxing; Vrieze, Thomas et al.
Medical Imaging 2022: Physics of Medical Imaging. ed. / Wei Zhao; Lifeng Yu. SPIE, 2022. 1203118 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 12031).

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

Fan, M, Zhou, Z, Vrieze, T, Wang, J, McCollough, C & Yu, L 2022, Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom. in W Zhao & L Yu (eds), Medical Imaging 2022: Physics of Medical Imaging., 1203118, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 12031, SPIE, Medical Imaging 2022: Physics of Medical Imaging, Virtual, Online, 3/21/22. https://doi.org/10.1117/12.2612414

Fan M, Zhou Z, Vrieze T, Wang J, McCollough C , Yu L. Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom. In Zhao W, Yu L, editors, Medical Imaging 2022: Physics of Medical Imaging. SPIE. 2022. 1203118. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2612414

Fan, Mingdong ; Zhou, Zhongxing ; Vrieze, Thomas et al. / Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom. Medical Imaging 2022: Physics of Medical Imaging. editor / Wei Zhao ; Lifeng Yu. SPIE, 2022. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).

@inproceedings{78d07babe323476ca653ed8776cf37b2,

title = "Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom",

abstract = "Channelized Hotelling observer (CHO), which has been shown to be well correlated with human observer performance in many clinical CT tasks, has a great potential to become the method of choice for objective image quality assessment. However, its use has been quite limited in routine CT practice due to lack of efficient implementation. In this work, a CHO model optimized for the most widely used ACR CT accreditation phantom was applied to evaluate the low-contrast detectability of a deep-learning based reconstruction (DLIR) equipped on a GE Revolution scanner. The commercially available DLIR reconstruction method showed consistent increase in low-contrast detectability over the FBP and the IR method at routine dose levels, which suggests potential dose reduction to the FBP reconstruction by up to 27.5%.",

keywords = "Image quality assessment, channelized Hotelling observer (CHO), protocol optimization, radiation dose reduction",

author = "Mingdong Fan and Zhongxing Zhou and Thomas Vrieze and Jia Wang and Cynthia McCollough and Lifeng Yu",

note = "Publisher Copyright: {\textcopyright} 2022 SPIE.; Medical Imaging 2022: Physics of Medical Imaging ; Conference date: 21-03-2022 Through 27-03-2022",

year = "2022",

doi = "10.1117/12.2612414",

language = "English (US)",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Wei Zhao and Lifeng Yu",

booktitle = "Medical Imaging 2022",

}

TY - GEN

T1 - Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom

AU - Fan, Mingdong

AU - Zhou, Zhongxing

AU - Vrieze, Thomas

AU - Wang, Jia

AU - McCollough, Cynthia

AU - Yu, Lifeng

PY - 2022

Y1 - 2022

N2 - Channelized Hotelling observer (CHO), which has been shown to be well correlated with human observer performance in many clinical CT tasks, has a great potential to become the method of choice for objective image quality assessment. However, its use has been quite limited in routine CT practice due to lack of efficient implementation. In this work, a CHO model optimized for the most widely used ACR CT accreditation phantom was applied to evaluate the low-contrast detectability of a deep-learning based reconstruction (DLIR) equipped on a GE Revolution scanner. The commercially available DLIR reconstruction method showed consistent increase in low-contrast detectability over the FBP and the IR method at routine dose levels, which suggests potential dose reduction to the FBP reconstruction by up to 27.5%.

AB - Channelized Hotelling observer (CHO), which has been shown to be well correlated with human observer performance in many clinical CT tasks, has a great potential to become the method of choice for objective image quality assessment. However, its use has been quite limited in routine CT practice due to lack of efficient implementation. In this work, a CHO model optimized for the most widely used ACR CT accreditation phantom was applied to evaluate the low-contrast detectability of a deep-learning based reconstruction (DLIR) equipped on a GE Revolution scanner. The commercially available DLIR reconstruction method showed consistent increase in low-contrast detectability over the FBP and the IR method at routine dose levels, which suggests potential dose reduction to the FBP reconstruction by up to 27.5%.

KW - Image quality assessment

KW - channelized Hotelling observer (CHO)

KW - protocol optimization

KW - radiation dose reduction

UR - http://www.scopus.com/inward/record.url?scp=85131189384&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85131189384&partnerID=8YFLogxK

U2 - 10.1117/12.2612414

DO - 10.1117/12.2612414

M3 - Conference contribution

AN - SCOPUS:85131189384

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2022

A2 - Zhao, Wei

A2 - Yu, Lifeng

PB - SPIE

T2 - Medical Imaging 2022: Physics of Medical Imaging

Y2 - 21 March 2022 through 27 March 2022

ER -

Efficient evaluation of low-contrast detectability of deep-CNN-based CT reconstruction using channelized Hotelling observer on the ACR accreditation phantom

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this