Semi-automated pulmonary nodule interval segmentation using the NLST data

Yoganand Balagurunathan, Andrew Beers, Jayashree Kalpathy-Cramer, Michael Mcnitt-Gray, Lubomir Hadjiiski, Bensheng Zhao, Jiangguo Zhu, Hao Yang, Stephen S.F. Yip, Hugo J.W.L. Aerts, Sandy Napel, Dmitrii Cherezov, Kenny Cha, Heang Ping Chan, Carlos Flores, Alberto Garcia, Robert Gillies, Dmitry Goldgof

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Purpose: To study the variability in volume change estimates of pulmonary nodules due to segmentation approaches used across several algorithms and to evaluate these effects on the ability to predict nodule malignancy. Methods: We obtained 100 patient image datasets from the National Lung Screening Trial (NLST) that had a nodule detected on each of two consecutive low dose computed tomography (LDCT) scans, with an equal proportion of malignant and benign cases (50 malignant, 50 benign). Information about the nodule location for the cases was provided by a screen capture with a bounding box and its axial location was indicated. Five participating quantitative imaging network (QIN) institutions performed nodule segmentation using their preferred semi-automated algorithms with no manual correction; teams were allowed to provide additional manually corrected segmentations (analyzed separately). The teams were asked to provide segmentation masks for each nodule at both time points. From these masks, the volume was estimated for the nodule at each time point; the change in volume (absolute and percent change) across time points was estimated as well. We used the concordance correlation coefficient (CCC) to compare the similarity of computed nodule volumes (absolute and percent change) across algorithms. We used Logistic regression model on the change in volume (absolute change and percent change) of the nodules to predict the malignancy status, the area under the receiver operating characteristic curve (AUROC) and confidence intervals were reported. Because the size of nodules was expected to have a substantial effect on segmentation variability, analysis of change in volumes was stratified by lesion size, where lesions were grouped into those with a longest diameter of <8 mm and those with longest diameter ≥ 8 mm. Results: We find that segmentation of the nodules shows substantial variability across algorithms, with the CCC ranging from 0.56 to 0.95 for change in volume (percent change in volume range was [0.15 to 0.86]) across the nodules. When examining nodules based on their longest diameter, we find the CCC had higher values for large nodules with a range of [0.54 to 0.93] among the algorithms, while percent change in volume was [0.3 to 0.95]. Compared to that of smaller nodules which had a range of [-0.0038 to 0.69] and percent change in volume was [-0.039 to 0.92]. The malignancy prediction results showed fairly consistent results across the institutions, the AUC using change in volume ranged from 0.65 to 0.89 (Percent change in volume was 0.64 to 0.86) for entire nodule range. Prediction improves for large nodule range (≥ 8 mm) with AUC range 0.75 to 0.90 (percent change in volume was 0.74 to 0.92). Compared to smaller nodule range (<8 mm) with AUC range 0.57 to 0.78 (percent change in volume was 0.59 to 0.77). Conclusions: We find there is a fairly high concordance in the size measurements for larger nodules (≥8 mm) than the lower sizes (<8 mm) across algorithms. We find the change in nodule volume (absolute and percent change) were consistent predictors of malignancy across institutions, despite using different segmentation algorithms. Using volume change estimates without corrections shows slightly lower predictability (for two teams).

Original languageEnglish (US)
JournalMedical Physics
DOIs
StateAccepted/In press - Jan 1 2018
Externally publishedYes

Fingerprint

Lung
Area Under Curve
Masks
Neoplasms
Logistic Models
ROC Curve
Tomography
Confidence Intervals

Keywords

  • Change in volume segmentation
  • CT lung
  • Lung nodule segmentation
  • Volume estimate

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Balagurunathan, Y., Beers, A., Kalpathy-Cramer, J., Mcnitt-Gray, M., Hadjiiski, L., Zhao, B., ... Goldgof, D. (Accepted/In press). Semi-automated pulmonary nodule interval segmentation using the NLST data. Medical Physics. https://doi.org/10.1002/mp.12766

Semi-automated pulmonary nodule interval segmentation using the NLST data. / Balagurunathan, Yoganand; Beers, Andrew; Kalpathy-Cramer, Jayashree; Mcnitt-Gray, Michael; Hadjiiski, Lubomir; Zhao, Bensheng; Zhu, Jiangguo; Yang, Hao; Yip, Stephen S.F.; Aerts, Hugo J.W.L.; Napel, Sandy; Cherezov, Dmitrii; Cha, Kenny; Chan, Heang Ping; Flores, Carlos; Garcia, Alberto; Gillies, Robert; Goldgof, Dmitry.

In: Medical Physics, 01.01.2018.

Research output: Contribution to journalArticle

Balagurunathan, Y, Beers, A, Kalpathy-Cramer, J, Mcnitt-Gray, M, Hadjiiski, L, Zhao, B, Zhu, J, Yang, H, Yip, SSF, Aerts, HJWL, Napel, S, Cherezov, D, Cha, K, Chan, HP, Flores, C, Garcia, A, Gillies, R & Goldgof, D 2018, 'Semi-automated pulmonary nodule interval segmentation using the NLST data', Medical Physics. https://doi.org/10.1002/mp.12766
Balagurunathan Y, Beers A, Kalpathy-Cramer J, Mcnitt-Gray M, Hadjiiski L, Zhao B et al. Semi-automated pulmonary nodule interval segmentation using the NLST data. Medical Physics. 2018 Jan 1. https://doi.org/10.1002/mp.12766
Balagurunathan, Yoganand ; Beers, Andrew ; Kalpathy-Cramer, Jayashree ; Mcnitt-Gray, Michael ; Hadjiiski, Lubomir ; Zhao, Bensheng ; Zhu, Jiangguo ; Yang, Hao ; Yip, Stephen S.F. ; Aerts, Hugo J.W.L. ; Napel, Sandy ; Cherezov, Dmitrii ; Cha, Kenny ; Chan, Heang Ping ; Flores, Carlos ; Garcia, Alberto ; Gillies, Robert ; Goldgof, Dmitry. / Semi-automated pulmonary nodule interval segmentation using the NLST data. In: Medical Physics. 2018.
@article{68c5ccf505ad42039b893dce17865aba,
title = "Semi-automated pulmonary nodule interval segmentation using the NLST data",
abstract = "Purpose: To study the variability in volume change estimates of pulmonary nodules due to segmentation approaches used across several algorithms and to evaluate these effects on the ability to predict nodule malignancy. Methods: We obtained 100 patient image datasets from the National Lung Screening Trial (NLST) that had a nodule detected on each of two consecutive low dose computed tomography (LDCT) scans, with an equal proportion of malignant and benign cases (50 malignant, 50 benign). Information about the nodule location for the cases was provided by a screen capture with a bounding box and its axial location was indicated. Five participating quantitative imaging network (QIN) institutions performed nodule segmentation using their preferred semi-automated algorithms with no manual correction; teams were allowed to provide additional manually corrected segmentations (analyzed separately). The teams were asked to provide segmentation masks for each nodule at both time points. From these masks, the volume was estimated for the nodule at each time point; the change in volume (absolute and percent change) across time points was estimated as well. We used the concordance correlation coefficient (CCC) to compare the similarity of computed nodule volumes (absolute and percent change) across algorithms. We used Logistic regression model on the change in volume (absolute change and percent change) of the nodules to predict the malignancy status, the area under the receiver operating characteristic curve (AUROC) and confidence intervals were reported. Because the size of nodules was expected to have a substantial effect on segmentation variability, analysis of change in volumes was stratified by lesion size, where lesions were grouped into those with a longest diameter of <8 mm and those with longest diameter ≥ 8 mm. Results: We find that segmentation of the nodules shows substantial variability across algorithms, with the CCC ranging from 0.56 to 0.95 for change in volume (percent change in volume range was [0.15 to 0.86]) across the nodules. When examining nodules based on their longest diameter, we find the CCC had higher values for large nodules with a range of [0.54 to 0.93] among the algorithms, while percent change in volume was [0.3 to 0.95]. Compared to that of smaller nodules which had a range of [-0.0038 to 0.69] and percent change in volume was [-0.039 to 0.92]. The malignancy prediction results showed fairly consistent results across the institutions, the AUC using change in volume ranged from 0.65 to 0.89 (Percent change in volume was 0.64 to 0.86) for entire nodule range. Prediction improves for large nodule range (≥ 8 mm) with AUC range 0.75 to 0.90 (percent change in volume was 0.74 to 0.92). Compared to smaller nodule range (<8 mm) with AUC range 0.57 to 0.78 (percent change in volume was 0.59 to 0.77). Conclusions: We find there is a fairly high concordance in the size measurements for larger nodules (≥8 mm) than the lower sizes (<8 mm) across algorithms. We find the change in nodule volume (absolute and percent change) were consistent predictors of malignancy across institutions, despite using different segmentation algorithms. Using volume change estimates without corrections shows slightly lower predictability (for two teams).",
keywords = "Change in volume segmentation, CT lung, Lung nodule segmentation, Volume estimate",
author = "Yoganand Balagurunathan and Andrew Beers and Jayashree Kalpathy-Cramer and Michael Mcnitt-Gray and Lubomir Hadjiiski and Bensheng Zhao and Jiangguo Zhu and Hao Yang and Yip, {Stephen S.F.} and Aerts, {Hugo J.W.L.} and Sandy Napel and Dmitrii Cherezov and Kenny Cha and Chan, {Heang Ping} and Carlos Flores and Alberto Garcia and Robert Gillies and Dmitry Goldgof",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/mp.12766",
language = "English (US)",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",

}

TY - JOUR

T1 - Semi-automated pulmonary nodule interval segmentation using the NLST data

AU - Balagurunathan, Yoganand

AU - Beers, Andrew

AU - Kalpathy-Cramer, Jayashree

AU - Mcnitt-Gray, Michael

AU - Hadjiiski, Lubomir

AU - Zhao, Bensheng

AU - Zhu, Jiangguo

AU - Yang, Hao

AU - Yip, Stephen S.F.

AU - Aerts, Hugo J.W.L.

AU - Napel, Sandy

AU - Cherezov, Dmitrii

AU - Cha, Kenny

AU - Chan, Heang Ping

AU - Flores, Carlos

AU - Garcia, Alberto

AU - Gillies, Robert

AU - Goldgof, Dmitry

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Purpose: To study the variability in volume change estimates of pulmonary nodules due to segmentation approaches used across several algorithms and to evaluate these effects on the ability to predict nodule malignancy. Methods: We obtained 100 patient image datasets from the National Lung Screening Trial (NLST) that had a nodule detected on each of two consecutive low dose computed tomography (LDCT) scans, with an equal proportion of malignant and benign cases (50 malignant, 50 benign). Information about the nodule location for the cases was provided by a screen capture with a bounding box and its axial location was indicated. Five participating quantitative imaging network (QIN) institutions performed nodule segmentation using their preferred semi-automated algorithms with no manual correction; teams were allowed to provide additional manually corrected segmentations (analyzed separately). The teams were asked to provide segmentation masks for each nodule at both time points. From these masks, the volume was estimated for the nodule at each time point; the change in volume (absolute and percent change) across time points was estimated as well. We used the concordance correlation coefficient (CCC) to compare the similarity of computed nodule volumes (absolute and percent change) across algorithms. We used Logistic regression model on the change in volume (absolute change and percent change) of the nodules to predict the malignancy status, the area under the receiver operating characteristic curve (AUROC) and confidence intervals were reported. Because the size of nodules was expected to have a substantial effect on segmentation variability, analysis of change in volumes was stratified by lesion size, where lesions were grouped into those with a longest diameter of <8 mm and those with longest diameter ≥ 8 mm. Results: We find that segmentation of the nodules shows substantial variability across algorithms, with the CCC ranging from 0.56 to 0.95 for change in volume (percent change in volume range was [0.15 to 0.86]) across the nodules. When examining nodules based on their longest diameter, we find the CCC had higher values for large nodules with a range of [0.54 to 0.93] among the algorithms, while percent change in volume was [0.3 to 0.95]. Compared to that of smaller nodules which had a range of [-0.0038 to 0.69] and percent change in volume was [-0.039 to 0.92]. The malignancy prediction results showed fairly consistent results across the institutions, the AUC using change in volume ranged from 0.65 to 0.89 (Percent change in volume was 0.64 to 0.86) for entire nodule range. Prediction improves for large nodule range (≥ 8 mm) with AUC range 0.75 to 0.90 (percent change in volume was 0.74 to 0.92). Compared to smaller nodule range (<8 mm) with AUC range 0.57 to 0.78 (percent change in volume was 0.59 to 0.77). Conclusions: We find there is a fairly high concordance in the size measurements for larger nodules (≥8 mm) than the lower sizes (<8 mm) across algorithms. We find the change in nodule volume (absolute and percent change) were consistent predictors of malignancy across institutions, despite using different segmentation algorithms. Using volume change estimates without corrections shows slightly lower predictability (for two teams).

AB - Purpose: To study the variability in volume change estimates of pulmonary nodules due to segmentation approaches used across several algorithms and to evaluate these effects on the ability to predict nodule malignancy. Methods: We obtained 100 patient image datasets from the National Lung Screening Trial (NLST) that had a nodule detected on each of two consecutive low dose computed tomography (LDCT) scans, with an equal proportion of malignant and benign cases (50 malignant, 50 benign). Information about the nodule location for the cases was provided by a screen capture with a bounding box and its axial location was indicated. Five participating quantitative imaging network (QIN) institutions performed nodule segmentation using their preferred semi-automated algorithms with no manual correction; teams were allowed to provide additional manually corrected segmentations (analyzed separately). The teams were asked to provide segmentation masks for each nodule at both time points. From these masks, the volume was estimated for the nodule at each time point; the change in volume (absolute and percent change) across time points was estimated as well. We used the concordance correlation coefficient (CCC) to compare the similarity of computed nodule volumes (absolute and percent change) across algorithms. We used Logistic regression model on the change in volume (absolute change and percent change) of the nodules to predict the malignancy status, the area under the receiver operating characteristic curve (AUROC) and confidence intervals were reported. Because the size of nodules was expected to have a substantial effect on segmentation variability, analysis of change in volumes was stratified by lesion size, where lesions were grouped into those with a longest diameter of <8 mm and those with longest diameter ≥ 8 mm. Results: We find that segmentation of the nodules shows substantial variability across algorithms, with the CCC ranging from 0.56 to 0.95 for change in volume (percent change in volume range was [0.15 to 0.86]) across the nodules. When examining nodules based on their longest diameter, we find the CCC had higher values for large nodules with a range of [0.54 to 0.93] among the algorithms, while percent change in volume was [0.3 to 0.95]. Compared to that of smaller nodules which had a range of [-0.0038 to 0.69] and percent change in volume was [-0.039 to 0.92]. The malignancy prediction results showed fairly consistent results across the institutions, the AUC using change in volume ranged from 0.65 to 0.89 (Percent change in volume was 0.64 to 0.86) for entire nodule range. Prediction improves for large nodule range (≥ 8 mm) with AUC range 0.75 to 0.90 (percent change in volume was 0.74 to 0.92). Compared to smaller nodule range (<8 mm) with AUC range 0.57 to 0.78 (percent change in volume was 0.59 to 0.77). Conclusions: We find there is a fairly high concordance in the size measurements for larger nodules (≥8 mm) than the lower sizes (<8 mm) across algorithms. We find the change in nodule volume (absolute and percent change) were consistent predictors of malignancy across institutions, despite using different segmentation algorithms. Using volume change estimates without corrections shows slightly lower predictability (for two teams).

KW - Change in volume segmentation

KW - CT lung

KW - Lung nodule segmentation

KW - Volume estimate

UR - http://www.scopus.com/inward/record.url?scp=85042145249&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042145249&partnerID=8YFLogxK

U2 - 10.1002/mp.12766

DO - 10.1002/mp.12766

M3 - Article

C2 - 29363773

AN - SCOPUS:85042145249

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

ER -