Radiomic Features Are Superior to Conventional Quantitative Computed Tomographic Metrics to Identify Coronary Plaques with Napkin-Ring Sign

Márton Kolossváry, Júlia Karády, Bálint Szilveszter, Pieter Kitslaar, Udo Hoffmann, B. Merkely, Pál Maurovich-Horvat

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Background - Napkin-ring sign (NRS) is an independent prognostic imaging marker of major adverse cardiac events. However, identification of NRS is challenging because of its qualitative nature. Radiomics is the process of extracting thousands of quantitative parameters from medical images to create big-data data sets that can identify distinct patterns in radiological images. Therefore, we sought to determine whether radiomic analysis improves the identification of NRS plaques. Methods and Results - From 2674 patients referred to coronary computed tomographic angiography caused by stable chest pain, expert readers identified 30 patients with NRS plaques and matched these with 30 non-NRS plaques with similar degree of calcification, luminal obstruction, localization, and imaging parameters. All plaques were segmented manually, and image data information was analyzed using Radiomics Image Analysis package for the presence of 8 conventional and 4440 radiomic parameters. We used the permutation test of symmetry to assess differences between NRS and non-NRS plaques, whereas we calculated receiver-operating characteristics' area under the curve values to evaluate diagnostic accuracy. Bonferroni-corrected P<0.0012 was considered significant. None of the conventional quantitative parameters but 20.6% (916/4440) of radiomic features were significantly different between NRS and non-NRS plaques. Almost half of these (418/916) reached an area under the curve value >0.80. Short- and long-run low gray-level emphasis and surface ratio of high attenuation voxels to total surface had the highest area under the curve values (0.918; 0.894 and 0.890, respectively). Conclusions - A large number of radiomic features are different between NRS and non-NRS plaques and exhibit excellent discriminatory value.

Original languageEnglish
Article numbere006843
JournalCirculation: Cardiovascular Imaging
Volume10
Issue number12
DOIs
Publication statusPublished - Dec 1 2017

Fingerprint

Area Under Curve
Chest Pain
ROC Curve
Angiography
Datasets

Keywords

  • angiography
  • atherosclerosis
  • chest pain
  • coronary artery disease
  • multidetector computed tomography

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine

Cite this

Radiomic Features Are Superior to Conventional Quantitative Computed Tomographic Metrics to Identify Coronary Plaques with Napkin-Ring Sign. / Kolossváry, Márton; Karády, Júlia; Szilveszter, Bálint; Kitslaar, Pieter; Hoffmann, Udo; Merkely, B.; Maurovich-Horvat, Pál.

In: Circulation: Cardiovascular Imaging, Vol. 10, No. 12, e006843, 01.12.2017.

Research output: Contribution to journalArticle

Kolossváry, Márton ; Karády, Júlia ; Szilveszter, Bálint ; Kitslaar, Pieter ; Hoffmann, Udo ; Merkely, B. ; Maurovich-Horvat, Pál. / Radiomic Features Are Superior to Conventional Quantitative Computed Tomographic Metrics to Identify Coronary Plaques with Napkin-Ring Sign. In: Circulation: Cardiovascular Imaging. 2017 ; Vol. 10, No. 12.
@article{55d67a19e3b54942943eaf4f1f99b26c,
title = "Radiomic Features Are Superior to Conventional Quantitative Computed Tomographic Metrics to Identify Coronary Plaques with Napkin-Ring Sign",
abstract = "Background - Napkin-ring sign (NRS) is an independent prognostic imaging marker of major adverse cardiac events. However, identification of NRS is challenging because of its qualitative nature. Radiomics is the process of extracting thousands of quantitative parameters from medical images to create big-data data sets that can identify distinct patterns in radiological images. Therefore, we sought to determine whether radiomic analysis improves the identification of NRS plaques. Methods and Results - From 2674 patients referred to coronary computed tomographic angiography caused by stable chest pain, expert readers identified 30 patients with NRS plaques and matched these with 30 non-NRS plaques with similar degree of calcification, luminal obstruction, localization, and imaging parameters. All plaques were segmented manually, and image data information was analyzed using Radiomics Image Analysis package for the presence of 8 conventional and 4440 radiomic parameters. We used the permutation test of symmetry to assess differences between NRS and non-NRS plaques, whereas we calculated receiver-operating characteristics' area under the curve values to evaluate diagnostic accuracy. Bonferroni-corrected P<0.0012 was considered significant. None of the conventional quantitative parameters but 20.6{\%} (916/4440) of radiomic features were significantly different between NRS and non-NRS plaques. Almost half of these (418/916) reached an area under the curve value >0.80. Short- and long-run low gray-level emphasis and surface ratio of high attenuation voxels to total surface had the highest area under the curve values (0.918; 0.894 and 0.890, respectively). Conclusions - A large number of radiomic features are different between NRS and non-NRS plaques and exhibit excellent discriminatory value.",
keywords = "angiography, atherosclerosis, chest pain, coronary artery disease, multidetector computed tomography",
author = "M{\'a}rton Kolossv{\'a}ry and J{\'u}lia Kar{\'a}dy and B{\'a}lint Szilveszter and Pieter Kitslaar and Udo Hoffmann and B. Merkely and P{\'a}l Maurovich-Horvat",
year = "2017",
month = "12",
day = "1",
doi = "10.1161/CIRCIMAGING.117.006843",
language = "English",
volume = "10",
journal = "Circulation: Cardiovascular Imaging",
issn = "1941-9651",
publisher = "Lippincott Williams and Wilkins",
number = "12",

}

TY - JOUR

T1 - Radiomic Features Are Superior to Conventional Quantitative Computed Tomographic Metrics to Identify Coronary Plaques with Napkin-Ring Sign

AU - Kolossváry, Márton

AU - Karády, Júlia

AU - Szilveszter, Bálint

AU - Kitslaar, Pieter

AU - Hoffmann, Udo

AU - Merkely, B.

AU - Maurovich-Horvat, Pál

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Background - Napkin-ring sign (NRS) is an independent prognostic imaging marker of major adverse cardiac events. However, identification of NRS is challenging because of its qualitative nature. Radiomics is the process of extracting thousands of quantitative parameters from medical images to create big-data data sets that can identify distinct patterns in radiological images. Therefore, we sought to determine whether radiomic analysis improves the identification of NRS plaques. Methods and Results - From 2674 patients referred to coronary computed tomographic angiography caused by stable chest pain, expert readers identified 30 patients with NRS plaques and matched these with 30 non-NRS plaques with similar degree of calcification, luminal obstruction, localization, and imaging parameters. All plaques were segmented manually, and image data information was analyzed using Radiomics Image Analysis package for the presence of 8 conventional and 4440 radiomic parameters. We used the permutation test of symmetry to assess differences between NRS and non-NRS plaques, whereas we calculated receiver-operating characteristics' area under the curve values to evaluate diagnostic accuracy. Bonferroni-corrected P<0.0012 was considered significant. None of the conventional quantitative parameters but 20.6% (916/4440) of radiomic features were significantly different between NRS and non-NRS plaques. Almost half of these (418/916) reached an area under the curve value >0.80. Short- and long-run low gray-level emphasis and surface ratio of high attenuation voxels to total surface had the highest area under the curve values (0.918; 0.894 and 0.890, respectively). Conclusions - A large number of radiomic features are different between NRS and non-NRS plaques and exhibit excellent discriminatory value.

AB - Background - Napkin-ring sign (NRS) is an independent prognostic imaging marker of major adverse cardiac events. However, identification of NRS is challenging because of its qualitative nature. Radiomics is the process of extracting thousands of quantitative parameters from medical images to create big-data data sets that can identify distinct patterns in radiological images. Therefore, we sought to determine whether radiomic analysis improves the identification of NRS plaques. Methods and Results - From 2674 patients referred to coronary computed tomographic angiography caused by stable chest pain, expert readers identified 30 patients with NRS plaques and matched these with 30 non-NRS plaques with similar degree of calcification, luminal obstruction, localization, and imaging parameters. All plaques were segmented manually, and image data information was analyzed using Radiomics Image Analysis package for the presence of 8 conventional and 4440 radiomic parameters. We used the permutation test of symmetry to assess differences between NRS and non-NRS plaques, whereas we calculated receiver-operating characteristics' area under the curve values to evaluate diagnostic accuracy. Bonferroni-corrected P<0.0012 was considered significant. None of the conventional quantitative parameters but 20.6% (916/4440) of radiomic features were significantly different between NRS and non-NRS plaques. Almost half of these (418/916) reached an area under the curve value >0.80. Short- and long-run low gray-level emphasis and surface ratio of high attenuation voxels to total surface had the highest area under the curve values (0.918; 0.894 and 0.890, respectively). Conclusions - A large number of radiomic features are different between NRS and non-NRS plaques and exhibit excellent discriminatory value.

KW - angiography

KW - atherosclerosis

KW - chest pain

KW - coronary artery disease

KW - multidetector computed tomography

UR - http://www.scopus.com/inward/record.url?scp=85038227475&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038227475&partnerID=8YFLogxK

U2 - 10.1161/CIRCIMAGING.117.006843

DO - 10.1161/CIRCIMAGING.117.006843

M3 - Article

C2 - 29233836

AN - SCOPUS:85038227475

VL - 10

JO - Circulation: Cardiovascular Imaging

JF - Circulation: Cardiovascular Imaging

SN - 1941-9651

IS - 12

M1 - e006843

ER -