Evaluation of a projection-domain lung nodule insertion technique in thoracic CT

Chi Ma, Baiyu Chen, Chi Wan Koo, Edwin A. Takahashi, Joel Garland Fletcher, Cynthia H McCollough, David L. Levin, Ronald S Kuzo, Lyndsay D. Viers, Stephanie A. Vincent Sheldon, Shuai Leng, Lifeng Yu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Task-based assessment of computed tomography (CT) image quality requires a large number of cases with ground truth. Inserting lesions into existing cases to simulate positive cases is a promising alternative approach. The aim of this study was to evaluate a recently-developed raw-data based lesion insertion technique in thoracic CT. Lung lesions were segmented from patient CT images, forward projected, and reinserted into the same patient CT projection data. In total, 32 nodules of various attenuations were segmented from 21 CT cases. Two experienced radiologists and 2 residents blinded to the process independently evaluated these inserted nodules in two sub-studies. First, the 32 inserted and the 32 original nodules were presented in a randomized order and each received a rating score from 1 to 10 (1=absolutely artificial to 10=absolutely realistic). Second, the inserted and the corresponding original lesions were presented side-by-side to each reader, who identified the inserted lesion and provided a confidence score (1=no confidence to 5=completely certain). For the randomized evaluation, discrimination of real versus artificial nodules was poor with areas under the receiver operative characteristic curves being 0.69 (95% CI: 0.58-0.78), 0.57 (95% CI: 0.46-0.68), and 0.62 (95% CI: 0.54-0.69) for the 2 radiologists, 2 residents, and all 4 readers, respectively. For the side-by-side evaluation, although all 4 readers correctly identified inserted lesions in 103/128 pairs, the confidence score was moderate (2.6). Our projection-domain based lung nodule insertion technique provides a robust method to artificially generate clinical cases that prove to be difficult to differentiate from real cases.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016: Physics of Medical Imaging
PublisherSPIE
Volume9783
ISBN (Electronic)9781510600188
DOIs
StatePublished - 2016
EventMedical Imaging 2016: Physics of Medical Imaging - San Diego, United States
Duration: Feb 28 2016Mar 2 2016

Other

OtherMedical Imaging 2016: Physics of Medical Imaging
CountryUnited States
CitySan Diego
Period2/28/163/2/16

Fingerprint

nodules
lungs
lesions
Tomography
insertion
Thorax
tomography
projection
Lung
evaluation
readers
confidence
ground truth
Image quality
ratings
discrimination
receivers
attenuation
curves
Radiologists

Keywords

  • Image quality assessment
  • lesion insertion
  • lesion simulation
  • lung nodules
  • observer study
  • radiation dose reduction
  • thoracic CT

ASJC Scopus subject areas

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

Cite this

Ma, C., Chen, B., Koo, C. W., Takahashi, E. A., Fletcher, J. G., McCollough, C. H., ... Yu, L. (2016). Evaluation of a projection-domain lung nodule insertion technique in thoracic CT. In Medical Imaging 2016: Physics of Medical Imaging (Vol. 9783). [97835Y] SPIE. https://doi.org/10.1117/12.2217009

Evaluation of a projection-domain lung nodule insertion technique in thoracic CT. / Ma, Chi; Chen, Baiyu; Koo, Chi Wan; Takahashi, Edwin A.; Fletcher, Joel Garland; McCollough, Cynthia H; Levin, David L.; Kuzo, Ronald S; Viers, Lyndsay D.; Vincent Sheldon, Stephanie A.; Leng, Shuai; Yu, Lifeng.

Medical Imaging 2016: Physics of Medical Imaging. Vol. 9783 SPIE, 2016. 97835Y.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ma, C, Chen, B, Koo, CW, Takahashi, EA, Fletcher, JG, McCollough, CH, Levin, DL, Kuzo, RS, Viers, LD, Vincent Sheldon, SA, Leng, S & Yu, L 2016, Evaluation of a projection-domain lung nodule insertion technique in thoracic CT. in Medical Imaging 2016: Physics of Medical Imaging. vol. 9783, 97835Y, SPIE, Medical Imaging 2016: Physics of Medical Imaging, San Diego, United States, 2/28/16. https://doi.org/10.1117/12.2217009
Ma C, Chen B, Koo CW, Takahashi EA, Fletcher JG, McCollough CH et al. Evaluation of a projection-domain lung nodule insertion technique in thoracic CT. In Medical Imaging 2016: Physics of Medical Imaging. Vol. 9783. SPIE. 2016. 97835Y https://doi.org/10.1117/12.2217009
Ma, Chi ; Chen, Baiyu ; Koo, Chi Wan ; Takahashi, Edwin A. ; Fletcher, Joel Garland ; McCollough, Cynthia H ; Levin, David L. ; Kuzo, Ronald S ; Viers, Lyndsay D. ; Vincent Sheldon, Stephanie A. ; Leng, Shuai ; Yu, Lifeng. / Evaluation of a projection-domain lung nodule insertion technique in thoracic CT. Medical Imaging 2016: Physics of Medical Imaging. Vol. 9783 SPIE, 2016.
@inproceedings{37c4d4b94638455887c50b6010b698de,
title = "Evaluation of a projection-domain lung nodule insertion technique in thoracic CT",
abstract = "Task-based assessment of computed tomography (CT) image quality requires a large number of cases with ground truth. Inserting lesions into existing cases to simulate positive cases is a promising alternative approach. The aim of this study was to evaluate a recently-developed raw-data based lesion insertion technique in thoracic CT. Lung lesions were segmented from patient CT images, forward projected, and reinserted into the same patient CT projection data. In total, 32 nodules of various attenuations were segmented from 21 CT cases. Two experienced radiologists and 2 residents blinded to the process independently evaluated these inserted nodules in two sub-studies. First, the 32 inserted and the 32 original nodules were presented in a randomized order and each received a rating score from 1 to 10 (1=absolutely artificial to 10=absolutely realistic). Second, the inserted and the corresponding original lesions were presented side-by-side to each reader, who identified the inserted lesion and provided a confidence score (1=no confidence to 5=completely certain). For the randomized evaluation, discrimination of real versus artificial nodules was poor with areas under the receiver operative characteristic curves being 0.69 (95{\%} CI: 0.58-0.78), 0.57 (95{\%} CI: 0.46-0.68), and 0.62 (95{\%} CI: 0.54-0.69) for the 2 radiologists, 2 residents, and all 4 readers, respectively. For the side-by-side evaluation, although all 4 readers correctly identified inserted lesions in 103/128 pairs, the confidence score was moderate (2.6). Our projection-domain based lung nodule insertion technique provides a robust method to artificially generate clinical cases that prove to be difficult to differentiate from real cases.",
keywords = "Image quality assessment, lesion insertion, lesion simulation, lung nodules, observer study, radiation dose reduction, thoracic CT",
author = "Chi Ma and Baiyu Chen and Koo, {Chi Wan} and Takahashi, {Edwin A.} and Fletcher, {Joel Garland} and McCollough, {Cynthia H} and Levin, {David L.} and Kuzo, {Ronald S} and Viers, {Lyndsay D.} and {Vincent Sheldon}, {Stephanie A.} and Shuai Leng and Lifeng Yu",
year = "2016",
doi = "10.1117/12.2217009",
language = "English (US)",
volume = "9783",
booktitle = "Medical Imaging 2016: Physics of Medical Imaging",
publisher = "SPIE",

}

TY - GEN

T1 - Evaluation of a projection-domain lung nodule insertion technique in thoracic CT

AU - Ma, Chi

AU - Chen, Baiyu

AU - Koo, Chi Wan

AU - Takahashi, Edwin A.

AU - Fletcher, Joel Garland

AU - McCollough, Cynthia H

AU - Levin, David L.

AU - Kuzo, Ronald S

AU - Viers, Lyndsay D.

AU - Vincent Sheldon, Stephanie A.

AU - Leng, Shuai

AU - Yu, Lifeng

PY - 2016

Y1 - 2016

N2 - Task-based assessment of computed tomography (CT) image quality requires a large number of cases with ground truth. Inserting lesions into existing cases to simulate positive cases is a promising alternative approach. The aim of this study was to evaluate a recently-developed raw-data based lesion insertion technique in thoracic CT. Lung lesions were segmented from patient CT images, forward projected, and reinserted into the same patient CT projection data. In total, 32 nodules of various attenuations were segmented from 21 CT cases. Two experienced radiologists and 2 residents blinded to the process independently evaluated these inserted nodules in two sub-studies. First, the 32 inserted and the 32 original nodules were presented in a randomized order and each received a rating score from 1 to 10 (1=absolutely artificial to 10=absolutely realistic). Second, the inserted and the corresponding original lesions were presented side-by-side to each reader, who identified the inserted lesion and provided a confidence score (1=no confidence to 5=completely certain). For the randomized evaluation, discrimination of real versus artificial nodules was poor with areas under the receiver operative characteristic curves being 0.69 (95% CI: 0.58-0.78), 0.57 (95% CI: 0.46-0.68), and 0.62 (95% CI: 0.54-0.69) for the 2 radiologists, 2 residents, and all 4 readers, respectively. For the side-by-side evaluation, although all 4 readers correctly identified inserted lesions in 103/128 pairs, the confidence score was moderate (2.6). Our projection-domain based lung nodule insertion technique provides a robust method to artificially generate clinical cases that prove to be difficult to differentiate from real cases.

AB - Task-based assessment of computed tomography (CT) image quality requires a large number of cases with ground truth. Inserting lesions into existing cases to simulate positive cases is a promising alternative approach. The aim of this study was to evaluate a recently-developed raw-data based lesion insertion technique in thoracic CT. Lung lesions were segmented from patient CT images, forward projected, and reinserted into the same patient CT projection data. In total, 32 nodules of various attenuations were segmented from 21 CT cases. Two experienced radiologists and 2 residents blinded to the process independently evaluated these inserted nodules in two sub-studies. First, the 32 inserted and the 32 original nodules were presented in a randomized order and each received a rating score from 1 to 10 (1=absolutely artificial to 10=absolutely realistic). Second, the inserted and the corresponding original lesions were presented side-by-side to each reader, who identified the inserted lesion and provided a confidence score (1=no confidence to 5=completely certain). For the randomized evaluation, discrimination of real versus artificial nodules was poor with areas under the receiver operative characteristic curves being 0.69 (95% CI: 0.58-0.78), 0.57 (95% CI: 0.46-0.68), and 0.62 (95% CI: 0.54-0.69) for the 2 radiologists, 2 residents, and all 4 readers, respectively. For the side-by-side evaluation, although all 4 readers correctly identified inserted lesions in 103/128 pairs, the confidence score was moderate (2.6). Our projection-domain based lung nodule insertion technique provides a robust method to artificially generate clinical cases that prove to be difficult to differentiate from real cases.

KW - Image quality assessment

KW - lesion insertion

KW - lesion simulation

KW - lung nodules

KW - observer study

KW - radiation dose reduction

KW - thoracic CT

UR - http://www.scopus.com/inward/record.url?scp=84978878062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978878062&partnerID=8YFLogxK

U2 - 10.1117/12.2217009

DO - 10.1117/12.2217009

M3 - Conference contribution

VL - 9783

BT - Medical Imaging 2016: Physics of Medical Imaging

PB - SPIE

ER -