Effects of alterations in positron emission tomography imaging parameters on radiomics features

Rachel B. Ger, Joseph G. Meier, Raymond B. Pahlka, Skylar Gay, Raymond Mumme, Clifton D. Fuller, Heng Li, Rebecca M. Howell, Rick R. Layman, R. Jason Stafford, Shouhao Zhou, Osama Mawlawi, Laurence E. Court

Research output: Contribution to journalArticle

Abstract

Radiomics studies require large patient cohorts, which often include patients imaged using different imaging protocols. We aimed to determine the impact of variability in imaging protocol parameters and interscanner variability using a phantom that produced feature values similar to those of patients. Positron emission tomography (PET) scans of a Hoffman brain phantom were acquired on GE Discovery 710, Siemens mCT, and Philips Vereos scanners. A standard-protocol scan was acquired on each machine, and then each parameter that could be changed was altered individually. The phantom was contoured with 10 regions of interest (ROIs). Values for 45 features with 2 different preprocessing techniques were extracted for each image. To determine the impact of each parameter on the reliability of each radiomics feature, the intraclass correlation coefficient (ICC) was calculated with the ROIs as the subjects and the parameter values as the raters. For interscanner comparisons, we compared the standard deviation of each radiomics feature value from the standard-protocol images to the standard deviation of the same radiomics feature from PET scans of 224 patients with non-small cell lung cancer. When the pixel size was resampled prior to feature extraction, all features had good reliability (ICC > 0.75) for the field of view and matrix size. The time per bed position had excellent reliability (ICC > 0.9) on all features. When the filter cutoff was restricted to values below 6 mm, all features had good reliability. Similarly, when subsets and iterations were restricted to reasonable values used in clinics, almost all features had good reliability. The average ratio of the standard deviation of features on the phantom scans to that of the NSCLC patient scans was 0.73 using fixed-bin-width preprocessing and 0.92 using 64-level preprocessing. Most radiomics feature values had at least good reliability when imaging protocol parameters were within clinically used ranges. However, interscanner variability was about equal to interpatient variability; therefore, caution must be used when combining patients scanned on equipment from different vendors in radiomics data sets.

Original languageEnglish (US)
Article numbere0221877
JournalPloS one
Volume14
Issue number9
DOIs
StatePublished - Jan 1 2019

Fingerprint

positron-emission tomography
Positron emission tomography
Positron-Emission Tomography
image analysis
Imaging techniques
bins (containers)
scanners
Bins
lung neoplasms
Non-Small Cell Lung Carcinoma
Feature extraction
Brain
Pixels
Cells
brain
Equipment and Supplies

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Ger, R. B., Meier, J. G., Pahlka, R. B., Gay, S., Mumme, R., Fuller, C. D., ... Court, L. E. (2019). Effects of alterations in positron emission tomography imaging parameters on radiomics features. PloS one, 14(9), [e0221877]. https://doi.org/10.1371/journal.pone.0221877
Ger, Rachel B. ; Meier, Joseph G. ; Pahlka, Raymond B. ; Gay, Skylar ; Mumme, Raymond ; Fuller, Clifton D. ; Li, Heng ; Howell, Rebecca M. ; Layman, Rick R. ; Jason Stafford, R. ; Zhou, Shouhao ; Mawlawi, Osama ; Court, Laurence E. / Effects of alterations in positron emission tomography imaging parameters on radiomics features. In: PloS one. 2019 ; Vol. 14, No. 9.
@article{777ed4399e3b42edbfe2892038e95660,
title = "Effects of alterations in positron emission tomography imaging parameters on radiomics features",
abstract = "Radiomics studies require large patient cohorts, which often include patients imaged using different imaging protocols. We aimed to determine the impact of variability in imaging protocol parameters and interscanner variability using a phantom that produced feature values similar to those of patients. Positron emission tomography (PET) scans of a Hoffman brain phantom were acquired on GE Discovery 710, Siemens mCT, and Philips Vereos scanners. A standard-protocol scan was acquired on each machine, and then each parameter that could be changed was altered individually. The phantom was contoured with 10 regions of interest (ROIs). Values for 45 features with 2 different preprocessing techniques were extracted for each image. To determine the impact of each parameter on the reliability of each radiomics feature, the intraclass correlation coefficient (ICC) was calculated with the ROIs as the subjects and the parameter values as the raters. For interscanner comparisons, we compared the standard deviation of each radiomics feature value from the standard-protocol images to the standard deviation of the same radiomics feature from PET scans of 224 patients with non-small cell lung cancer. When the pixel size was resampled prior to feature extraction, all features had good reliability (ICC > 0.75) for the field of view and matrix size. The time per bed position had excellent reliability (ICC > 0.9) on all features. When the filter cutoff was restricted to values below 6 mm, all features had good reliability. Similarly, when subsets and iterations were restricted to reasonable values used in clinics, almost all features had good reliability. The average ratio of the standard deviation of features on the phantom scans to that of the NSCLC patient scans was 0.73 using fixed-bin-width preprocessing and 0.92 using 64-level preprocessing. Most radiomics feature values had at least good reliability when imaging protocol parameters were within clinically used ranges. However, interscanner variability was about equal to interpatient variability; therefore, caution must be used when combining patients scanned on equipment from different vendors in radiomics data sets.",
author = "Ger, {Rachel B.} and Meier, {Joseph G.} and Pahlka, {Raymond B.} and Skylar Gay and Raymond Mumme and Fuller, {Clifton D.} and Heng Li and Howell, {Rebecca M.} and Layman, {Rick R.} and {Jason Stafford}, R. and Shouhao Zhou and Osama Mawlawi and Court, {Laurence E.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0221877",
language = "English (US)",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "9",

}

Ger, RB, Meier, JG, Pahlka, RB, Gay, S, Mumme, R, Fuller, CD, Li, H, Howell, RM, Layman, RR, Jason Stafford, R, Zhou, S, Mawlawi, O & Court, LE 2019, 'Effects of alterations in positron emission tomography imaging parameters on radiomics features', PloS one, vol. 14, no. 9, e0221877. https://doi.org/10.1371/journal.pone.0221877

Effects of alterations in positron emission tomography imaging parameters on radiomics features. / Ger, Rachel B.; Meier, Joseph G.; Pahlka, Raymond B.; Gay, Skylar; Mumme, Raymond; Fuller, Clifton D.; Li, Heng; Howell, Rebecca M.; Layman, Rick R.; Jason Stafford, R.; Zhou, Shouhao; Mawlawi, Osama; Court, Laurence E.

In: PloS one, Vol. 14, No. 9, e0221877, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Effects of alterations in positron emission tomography imaging parameters on radiomics features

AU - Ger, Rachel B.

AU - Meier, Joseph G.

AU - Pahlka, Raymond B.

AU - Gay, Skylar

AU - Mumme, Raymond

AU - Fuller, Clifton D.

AU - Li, Heng

AU - Howell, Rebecca M.

AU - Layman, Rick R.

AU - Jason Stafford, R.

AU - Zhou, Shouhao

AU - Mawlawi, Osama

AU - Court, Laurence E.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Radiomics studies require large patient cohorts, which often include patients imaged using different imaging protocols. We aimed to determine the impact of variability in imaging protocol parameters and interscanner variability using a phantom that produced feature values similar to those of patients. Positron emission tomography (PET) scans of a Hoffman brain phantom were acquired on GE Discovery 710, Siemens mCT, and Philips Vereos scanners. A standard-protocol scan was acquired on each machine, and then each parameter that could be changed was altered individually. The phantom was contoured with 10 regions of interest (ROIs). Values for 45 features with 2 different preprocessing techniques were extracted for each image. To determine the impact of each parameter on the reliability of each radiomics feature, the intraclass correlation coefficient (ICC) was calculated with the ROIs as the subjects and the parameter values as the raters. For interscanner comparisons, we compared the standard deviation of each radiomics feature value from the standard-protocol images to the standard deviation of the same radiomics feature from PET scans of 224 patients with non-small cell lung cancer. When the pixel size was resampled prior to feature extraction, all features had good reliability (ICC > 0.75) for the field of view and matrix size. The time per bed position had excellent reliability (ICC > 0.9) on all features. When the filter cutoff was restricted to values below 6 mm, all features had good reliability. Similarly, when subsets and iterations were restricted to reasonable values used in clinics, almost all features had good reliability. The average ratio of the standard deviation of features on the phantom scans to that of the NSCLC patient scans was 0.73 using fixed-bin-width preprocessing and 0.92 using 64-level preprocessing. Most radiomics feature values had at least good reliability when imaging protocol parameters were within clinically used ranges. However, interscanner variability was about equal to interpatient variability; therefore, caution must be used when combining patients scanned on equipment from different vendors in radiomics data sets.

AB - Radiomics studies require large patient cohorts, which often include patients imaged using different imaging protocols. We aimed to determine the impact of variability in imaging protocol parameters and interscanner variability using a phantom that produced feature values similar to those of patients. Positron emission tomography (PET) scans of a Hoffman brain phantom were acquired on GE Discovery 710, Siemens mCT, and Philips Vereos scanners. A standard-protocol scan was acquired on each machine, and then each parameter that could be changed was altered individually. The phantom was contoured with 10 regions of interest (ROIs). Values for 45 features with 2 different preprocessing techniques were extracted for each image. To determine the impact of each parameter on the reliability of each radiomics feature, the intraclass correlation coefficient (ICC) was calculated with the ROIs as the subjects and the parameter values as the raters. For interscanner comparisons, we compared the standard deviation of each radiomics feature value from the standard-protocol images to the standard deviation of the same radiomics feature from PET scans of 224 patients with non-small cell lung cancer. When the pixel size was resampled prior to feature extraction, all features had good reliability (ICC > 0.75) for the field of view and matrix size. The time per bed position had excellent reliability (ICC > 0.9) on all features. When the filter cutoff was restricted to values below 6 mm, all features had good reliability. Similarly, when subsets and iterations were restricted to reasonable values used in clinics, almost all features had good reliability. The average ratio of the standard deviation of features on the phantom scans to that of the NSCLC patient scans was 0.73 using fixed-bin-width preprocessing and 0.92 using 64-level preprocessing. Most radiomics feature values had at least good reliability when imaging protocol parameters were within clinically used ranges. However, interscanner variability was about equal to interpatient variability; therefore, caution must be used when combining patients scanned on equipment from different vendors in radiomics data sets.

UR - http://www.scopus.com/inward/record.url?scp=85071779953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071779953&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0221877

DO - 10.1371/journal.pone.0221877

M3 - Article

C2 - 31487307

AN - SCOPUS:85071779953

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 9

M1 - e0221877

ER -