![Representative curved multiplanar and volume rendered CT images of three coronary plaques corresponding to specific invasive and radionuclide imaging markers of plaque vulnerability. (A) A coronary lesion which scored the lowest on fractal box counting dimension of high attenuation voxels (component 30 when discretizing to 32 equally sized bins) which was indicative of attenuated plaque on IVUS [AUC: 0.72 (0.65-0.78)]. (B) Depicts a coronary plaque which scored the lowest on fractal box counting dimension of high attenuation voxels (component 8 when discretizing to eight equally sized bins) which was suggestive of OCT-TCFA [AUC: 0.80 (0.72-0.88)]. (C) A coronary lesion which had a high surface of high attenuation voxels (component 8 when discretizing to eight equally sized bins) which was the best parameter to identify NaF 18 -PET positivity [AUC: 0.87 (0.82-0.91)]. AUC, area under the curve; IVUS, intravascular ultrasound; NaF 18 -PET, NaF 18 -positron emission tomography; OCT-TCFA, optical coherence tomography identified thin-cap fibroatheroma. a Component 30 when discretizing to 32 equally sized bins. b Component 8 when discretizing to eight equally sized bins.](https://www.researchgate.net/profile/Marton-Kolossvary-2/publication/331574866/figure/fig4/AS:788902730285057@1565100476345/Representative-curved-multiplanar-and-volume-rendered-CT-images-of-three-coronary-plaques_Q320.jpg)
Content uploaded by Márton Kolossváry
Author content
All content in this area was uploaded by Márton Kolossváry on Aug 06, 2019
Content may be subject to copyright.
Identification of invasive and radionuclide
imaging markers of coronary plaque
vulnerability using radiomic analysis of coronary
computed tomography angiography
Ma´rton Kolossva´ry
1
, Jonghanne Park
2
, Ji-In Bang
3
, Jinlong Zhang
2
, Joo Myung Lee
4
,
Jin Chul Paeng
3
,Be´la Merkely
1
, Jagat Narula
5
, Takashi Kubo
6
, Takashi Akasaka
6
,
Bon-Kwon Koo
2
*, and Pa´l Maurovich-Horvat
1
1
Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, 68. Varosmajor street, 1122 Budapest, Hungary;
2
Department of Internal Medicine and
Cardiovascular Center, Seoul National University Hospital, 101 Daehang-ro, Chongno-gu, Seoul 03080, Republic of Korea;
3
Department of Nuclear Medicine, Seoul National
University Hospital, 101 Daehang-ro, Chongo-gu, Seoul 03080, Republic of Korea;
4
Department of Internal Medicine and Cardiovascular Center, Samsung Medical Center,
Sungkyunkwan University School of Medicine, Gangnam-gu, Irwon-dong, Seoul 135710, Republic of Korea;
5
Icahn School of Medicine at Mount Sinai Hospital, 1 Gustave L. Levy Place,
New York, NY 10029, USA; and
6
Department of Cardiovascular Medicine, Wakayama Medical University, 811-1 Kimiidera, Wakayama, Wakayama Prefecture 641-8509, Japan
Received 17 October 2018; editorial decision 5 Febr uary 2019; accepted 13 February 2019
Aims Identification of invasive and radionuclide imaging markers of coronary plaque vulnerability by a single, widely avail-
able non-invasive technique may provide the opportunity to identify vulnerable plaques and vulnerable patients
in broad populations. Our aim was to assess whether radiomic analysis outperforms conventional assessment of
coronary computed tomography angiography (CTA) images to identify invasive and radionuclide imaging markers
of plaque vulnerability.
........................................................................ ............. ............. ............. .................. ..................................................................
Methods
and results
We prospectively included patients who underwent coronary CTA, sodium-fluoride positron emission tomography
(NaF
18
-PET), intravascular ultrasound (IVUS), and optical coherence tomography (OCT). We assessed seven
conventional plaque features and calculated 935 radiomic parameters from CTA images. In total, 44 plaques of
25 patients were analysed. The best radiomic parameters significantly outperformed the best conventional CT
parameters to identify attenuated plaque by IVUS [fractal box counting dimension of high attenuation voxels vs.
non-calcified plaque volume, area under the curve (AUC): 0.72, confidence interval (CI): 0.65–0.78 vs. 0.59, CI:
0.57–0.62; P< 0.001], thin-cap fibroatheroma by OCT (fractal box counting dimension of high attenuation voxels
vs. presence of low attenuation voxels, AUC: 0.80, CI: 0.72–0.88 vs. 0.66, CI: 0.58–0.73; P< 0.001), and NaF
18
-posi-
tivity (surface of high attenuation voxels vs. presence of two high-risk features, AUC: 0.87, CI: 0.82–0.91 vs. 0.65,
CI: 0.64–0.66; P< 0.001).
........................................................................ ............. ............. ............. .................. ..................................................................
Conclusion Coronary CTA radiomics identified invasive and radionuclide imaging markers of plaque vulnerability with good to
excellent diagnostic accuracy, significantly outperforming conventional quantitative and qualitative high-risk plaque
features. Coronary CTA radiomics may provide a more accurate tool to identify vulnerable plaques compared
with conventional methods. Further larger population studies are warranted.
䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏䊏
Keywords radiomics •coronary CT angiography •intravascular ultrasound •optical coherence tomography •sodium-
fluoride positron emission tomography
* Corresponding author. Tel: þ82 (2) 2072 2062; Fax: þ82 (2) 3675 0805. E-mail: bkkoo@snu.ac.kr
V
CThe Author(s) 2019. Published by Oxford University Press on behalf of the European Society of Cardiology.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/),
which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact
journals.permissions@oup.com
European Heart Journal - Cardiovascular Imaging (2019) 00, 1–9
doi:10.1093/ehjci/jez033
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
Introduction
Several imaging markers of plaque vulnerability have been linked to
acute coronary events.
1,2
Invasive imaging modalities, such as intra-
vascular ultrasound (IVUS) and optical coherence tomography
(OCT) are capable of depicting distinct morphologic markers of pla-
que vulnerability, which have been validated by histology and clinical
investigations.
3–6
Recently, sodium-fluoride positron emission tomography (NaF
18
-
PET) has been introduced as a radionuclide imaging modality to iden-
tify inflammation and microcalcifications in coronary atherosclerotic
plaques which are hallmarks of plaque vulnerability.
2,7
It would be de-
sirable to have a widely available non-invasive imaging modality, cap-
able of identifying invasive, and/or radionuclide imaging markers of
plaque vulnerability.
Coronary computed tomography angiography (CTA) is an estab-
lished non-invasive imaging modality capable of depicting plaque
morphology and composition.
8
However, visually detectable adverse
plaque characteristics based on coronary CTA show only a modest
correlation with IVUS, OCT, or NaF
18
-PET derived features.
9
CT
datasets contain more information than what is comprehensible by
visual inspection.
10
This extra information can be extracted using
radiomics: the process of obtaining quantitative metrics from
radiological images to create big-data datasets, where each lesion is
characterized by hundreds of different parameters.
11
This technique
has been shown to identify complex qualitative morphologies such
as the napkin-ring sign on coronary CTA datasets with excellent
diagnostic accuracy.
12
However, there is no information on whether
coronary CTA derived radiomic features could identify invasive
and radionuclide imaging markers. Identification of these imaging
biomarkers non-invasively by a single, widely available non-invasive
technique may provide an opportunity to identify vulnerable plaques
and vulnerable patients in daily clinical practice. Therefore, we sought
to assess whether coronary CTA radiomics could outperform con-
ventional quantitative and qualitative markers of plaque vulnerability
to identify invasive and radionuclide imaging markers of high-risk
plaques described by IVUS, OCT, and NaF
18
-PET (Figure 1).
Methods
Study population
Our patient population is a substudy of a previous investigation
assessing the correlation between NaF
18
-PET activity and invasive
imaging biomarkers of high-risk lesions.
9
The current study is a post
hoc retrospective analysis of patients who have also undergone
Figure 1 Schematic illustration of the applied methods to compare conventional vs. radiomic CT parameters to identify invasive and radionuclide
imaging markers of plaque vulnerability. CT, computed tomography; IVUS, intravascular ultrasound; NaF
18
-PET, sodium-fluoride positron emission
tomography; OCT, optical coherence tomography.
2M. Kolossva´ry et al.
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
coronary CTA due to suspected coronary artery disease between
March and October of 2015 within 90days prior to invasive angiog-
raphy. In total, 27 patients with at least one moderate (40–70%) sten-
osis on the proximal or mid-portion of any major coronary artery
were included in our study. All patients underwent NaF
18
-PET
and invasive coronary angiography. During the invasive procedure,
both IVUS and OCT was performed. Two patients were excluded
due to inadequate image quality of imaging procedures. Overall,
44 plaques of 25 patients using all four imaging modalities
were investigated (Figure 2). The study protocol was approved
by the institutional review board and was in accordance with
the Declaration of Helsinki. All patients provided written
informed consent before enrolment (ClinicalTrials.gov Identifier:
NCT02388412). The authors had full access to all the data in the
study and take responsibility for its integrity and analysis. The ana-
lysis of each imaging modality was done by a single-experienced
specialist from each core laboratory.
Qualitative coronary CTA analysis
Coronary CTA images were obtained in accordance with the Society
of Cardiovascular Computed Tomography Guidelines, with a 64-de-
tector row scanner platform (Somatom Definition; Siemens Medical
Solutions, Forchheim, Germany).
13
The following conventional mor-
phologic adverse plaque characteristics were reported by a core lab
(Severance Cardiovascular Hospital, Seoul, Republic of Korea)
blinded to all other results: low attenuation plaque (density <_30 HU),
positive remodelling (remodelling index >_1.1), spotty calcification
(density >130 HU and diameter <3 mm), and napkin-ring sign
(ring-like attenuation pattern with peripheral high attenuation
tissue surrounding a central lower attenuation area).
8,14
Lesions
with at least two of the four morphologic adverse plaque charac-
teristics were regarded as two-feature positive high-risk plaque
on coronary CTA.
9
Quantitative coronary CTA analysis
Each coronary plaque was segmented blinded to other imaging mo-
dality results using a semi-automated software tool (QAngioCT
Research Edition; Medis medical imaging systems bv, Leiden, The
Netherlands) at a designated core laboratory (Semmelweis
University, Budapest, Hungary). Lumen and vessel contours were
manually adjusted if necessary. Using the segmented datasets, voxels
containing plaque were exported as a DICOM image (QAngioCT 3D
workbench, Medis medical imaging systems bv, Leiden, The
Netherlands). Based on the Hounsfield units (HU) values, the volume
of low attenuation non-calcified plaque (<30 HU), non-calcified pla-
que (30–130 HU), and calcified plaque volume (>130 HU) was
calculated.
15,16
Figure 2 A study flowchart. Median intervals from NaF
18
-PET and coronary CTA to invasive coronary angiography were 0 and 45 days, respective-
ly. CTA, computed tomography angiography; IVUS, intravascular ultrasound; NaF
18
-PET, sodium-fluoride positron emission tomography; OCT, op-
tical coherence tomography.
Radiomics to identify plaque vulnerability 3
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
Radiomic coronary CTA analysis
Four different classes of radiomic features were used in our analysis.
First-order statistics discard all spatial information and calculate
parameters which describe different aspects of the distribution of
HU values. Grey level co-occurrence matrices (GLCM) enumerate
the frequency of similar value voxels co-occurring next to each other
in the given lesion, while grey level run length matrices (GLRLM) de-
scribe how often a given number of similar value voxels are situated
next to one another.
17,18
For these calculations, similar value voxels
need to be grouped together. This is done through discretization of
HU values to a given number of bins. In our analysis, we discretized
the lesions into 2, 8, 32 equally sized (range of values were equally
wide) bins creating three replicas of the image. All GLCM and
GLRLM metrics were calculated using all three types of binning.
Geometry-based statistics were calculated on the original image, as
well as each discretized component.
Radiomic features were analysed at a core facility (Semmelweis
University, Budapest, Hungary). Overall 935 different radiomic
parameters were calculated using the RadiomicsImage Analysis (RIA)
software package in the R environment.
19
Of these parameters, 44
were first-order statistics; 342 were statistics calculated from GLCM;
33 were statistics extracted from GLRLM, while 516 were geometry-
based statistical parameters.
12
The median time to calculate all 935
parameters for each plaque was: 7.3 (range: 3.8–12.6) min.
NaF
18
-PET analysis
All patients underwent NaF
18
-PET before invasive angiography.
Electrocardiography-gated NaF
18
-PET images were obtained using a
dedicated PET/CT scanner (Biograph 40 TruePoint; Siemens
Healthcare, Germany) 60 min after the injection of 3 MBq/kg of
NaF
18
. Images were reconstructed in four frames and fused with the
non-enhanced CT images. Diastolic phases (frames of 50–75% and
75–100% of the R–R intervals) were evaluated blinded to all other
results at a core facility (Seoul National University Hospital—
Nuclear Medicine, Seoul, Republic of Korea). Maximum standard up-
take value was measured and corrected for blood pool activity meas-
ured in the inferior vena cava to provide tissue-to-background ratio
measurements. The highest tissue-to-background ratio value meas-
ured on two diastolic-phase images was adopted for the final analysis.
Plaques with NaF
18
uptakes higher than 25% were considered as
NaF
18
-positive lesions.
2,9
Invasive coronary angiography and
intracoronary imaging
Selective invasive coronary angiography was performed utilizing
standard techniques. IVUS images were acquired according to the
American College of Cardiology Clinical Expert Consensus
Document on Standards for Acquisition, Measurement, and
Reporting of Intravascular Ultrasound Studies.
20,21
The presence of
echo attenuation (hypoechoic plaque with deep ultrasound attenu-
ation) was analysed blindly at a core lab (Seoul National University
Hospital—CV Research Institute, Seoul, Republic of Korea). All OCT
data were assessed blindly at a core laboratory for the presence of
thin-cap fibroatheroma (TCFA).
9
Statistical analysis
Continuous variables are presented as medians and interquartile
ranges, whereas categorical variables are reported as frequencies and
percentages. Calculating diagnostic accuracy on the whole dataset,
would be overly optimistic and ungeneralizable to other datasets.
Therefore, we conducted a stratified five-fold cross-validation with
1000 repeats, which decreases the bias of overfitting and provides a
robust estimate of the expected performance in real life.
22
A receiver
operating characteristics (ROC) curve was calculated for each repeat
resulting in overall 1000 ROC curves. These ROC curves were aver-
aged to model the diagnostic performance on the whole population.
Area under the curve (AUC) was calculated as an overall measure of
diagnostic accuracy. To compare the diagnostic accuracy of conven-
tional and radiomic coronary CTA features, we calculated the two-
sided Wilcoxon signed-rank test to compare the distribution of AUC
values resulting from the repeated cross-validations. We calculated
confidence intervals (CIs) as the 2.5 and 97.5 percentile of the AUC
distribution resulting from the repeated cross-validations. All statis-
tical calculations were done in the python environment using the
Scikit-learn package.
23
Results
Distribution of individual IVUS, OCT, and
NaF
18
-PET imaging markers of plaque
vulnerability
Overall, 44 plaques were analysed (Table 1); 30/44 (68.2%) plaques
showed attenuation on IVUS, 7/44 (15.9%) showed TCFA on OCT,
Table 1 Patient and lesion characteristics
Patient characteristics
Age (years) 62 (IQR: 59–69)
Male 23 (92)
Body mass index (kg/m
2
) 25 (IQR: 22–27)
Cardiovascular risk factors
Hypertension 12 (48.0)
Diabetes mellitus 8 (32.0)
Hypercholesterolaemia 18 (72.0)
Current smoker 6 (24.0)
Lesion characteristics
Lesion locations
Left main to LAD 34 (77.3)
LCx 3 (6.8)
RCA 7 (15.9)
Quantitative coronary angiography
Reference vessel diameter (mm) 3.3 (IQR: 2.9–3.6)
Minimal lumen diameter (mm) 1.7 (IQR: 1.4–2.3)
Diameter stenosis (%) 45 (IQR: 33–52)
Lesion length (mm) 11.2 (IQR: 7.9–14.5)
Continuous variables are presented as median and interquartile ranges, whereas
categorical parameters are shown as frequencies and percentages.
IQR, interquartile range; LAD, left anterior descending artery; LCx, left circum-
flex artery; RCA, right coronary artery.
4M. Kolossva´ry et al.
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
and in 11/44 (25.0%) cases >25% NaF
18
uptake was present. All pla-
ques which were TCFA by OCT also showed attenuation on IVUS.
Out of the 30 attenuated plaques 8/30 (26.7%) showed radionuclide
uptake on NaF
18
-PET; however, none of the TCFA plaques showed
>25% NaF
18
uptake.
Diagnostic accuracy radiomic features to
identify attenuated plaques on IVUS
Among radiomic metrics, 35/935 (3.7%) had AUC values between
0.70 and 0.79 and 311/935 (33.3%) had values between 0.60 and 0.69
to identify IVUS-attenuated plaque. Among radiomic metrics fractal
box counting dimension of high attenuation (component 30 when
discretizing to 32 equally sized bins) voxels showed the best diagnos-
tic accuracy to identify attenuated plaques on IVUS (AUC: 0.72; CI:
0.65–0.78), whereas among the conventional CT metrics, non-
calcified plaque volume showed the best discriminatory value (AUC:
0.59; CI: 0.57–0.62), P<0.001(Figure 3and Table 2).
Diagnostic accuracy of radiomic features
to identify OCT-TCFA
Overall, 1/935 (0.1%) of all radiomic parameters had AUC values be-
tween 0.80 and 0.89, 44/935 (4.7%) between 0.70 and 0.79 and 219/
935 (23.4%) had values between 0.60 and 0.69 to identify OCT-
TCFA. Fractal box counting dimension of high attenuation
....................................................................................................................................................................................................................
Table 2 Diagnostic accuracy of best conventional and radiomic feature to identify invasive and radionuclide imaging
markers of plaque vulnerability
Outcomes Best conventional and radiomic parameter AUC P-value
IVUS-attenuated plaque Conventional: non-calcified plaque volume 0.59 (0.57–0.62) P< 0.001
Radiomics: fractal box counting dimension of high attenuation voxels
a
0.72 (0.65–0.78)
OCT-TCFA Conventional: presence of low attenuation 0.66 (0.58–0.73) P<0.001
Radiomics: fractal box counting dimension of high attenuation voxels
b
0.80 (0.72–0.88)
NaF
18
-PET positivity Conventional: presence of two high-risk features 0.65 (0.64–0.66) P< 0.001
Radiomics: surface of high attenuation voxels
b
0.87 (0.82–0.91)
Values in parenthesis indicate confidence intervals.
AUC, area under the curve; IVUS, intravascular ultrasound; NaF
18
-PET, NaF
18
-positron emission tomography; OCT-TCFA, optical coherence tomography identified thin-cap
fibroatheroma.
a
Component 30 when discretizing to 32 equally sized bins.
b
Component 8 when discretizing to eight equally sized bins.
Figure 3 Diagnostic evaluation of radiomics and conventional CT parameters to identify attenuated plaques on IVUS. (A) Average receiver operat-
ing characteristic curves of the best radiomic (pink): fractal box counting dimension of high attenuation voxels (component 30 when discretizing to
32 equally sized bins); and the best conventional (blue) parameter: non-calcified plaque volume, which were calculated by averaging the receiver
operating characteristic curves after 1000 repeats of the five-fold cross-validation process. (B) Distribution of the AUC values calculated during the
five-foldcross-validationprocess repeated 1000times. Dashed lines indicate the means of the AUC distributions. Results are based on the analysis of
44 plaques of 25 patients. (C) Manhattan-plot of radiomic features’ AUC values. Radiomic parameters are situated in consecutive order on the xaxis,
while their corresponding AUC values to identify attenuated plaques on IVUS are shown on the yaxis. AUC, area under the curve; GLCM, grey level
co-occurrence matrix; GLRLM, grey level run length matrix.
Radiomics to identify plaque vulnerability 5
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
(component 8 when discretizing to eight equally sized bins) voxels
had the best diagnostic accuracy to identify OCT-TCFA (AUC: 0.80;
CI: 0.72–0.88), while the presence of low attenuation plaque showed
the best discriminatory power among conventional metrics (AUC:
0.66; CI: 0.58–0.73), P< 0.001 (Figure 4and Table 2).
Diagnostic accuracy of radiomic features
to identify increased NaF
18
uptake
Overall, 30/935 (3.2%) of the radiomic parameters had AUC values
between 0.80 and 0.89, 331/935 (35.4%) had values between 0.70
and 0.79 and 232/935 (24.8%) had values between 0.60 and 0.69 to
identify NaF
18
-positivity. Out of the radiomic parameters, the surface
of high attenuation (component 8 when discretizing to eight equally
sized bins) voxels had the best diagnostic accuracy (AUC: 0.87; CI:
0.82–0.91), while the presence of two high-risk features on CTA had
the best discriminatory power (AUC: 0.65; CI: 0.64–0.66) among
conventional parameters to identify marked radionuclide uptake
using NaF
18
-PET, P< 0.001 (Figure 5and Table 2).
Representative volume rendered CT images of coronary plaques
showing attenuation on IVUS, TCFA on OCT, and positivity on
NaF
18
-PET can be found in Figure 6.
Discussion
We demonstrated that radiomics can increase the diagnostic accur-
acy of coronary CTA to identify specific invasive and radionuclide
imaging markers of plaque vulnerability. Coronary CTA radiomics
showed a good diagnostic accuracy to identify IVUS-attenuated pla-
ques and excellent diagnostic accuracy to identify OCT-TCFA and
NaF
18
-positivity (AUC: 0.72, 0.80, and 0.87, respectively).
Furthermore, radiomics outperformed conventional CT metrics to
identify these invasive and radionuclide imaging markers (P<0.001
all).
It seems that by utilizing radiomics, the amount of information ac-
cessible in CT images can be greatly increased. Radiological examina-
tions are evaluated mostly by visual inspection in current clinical care.
As opposed to this practice, in the current project, we treated radio-
logical images as 3D datasets and extracted hundreds of quantitative
parameters from coronary plaques. This strategy resulted in signifi-
cantly better discriminatory power to identify invasive and radio-
nuclide markers of plaque vulnerability. Radiomics utilizes texture
and geometrical analysis to derive novel imaging biomarkers. By
measuring how many times a given value voxel pairs occur next to
each other, or how many times similar values occur next to each
other in a given direction, probability matrices can be calculated
which resemble the spatial distribution of the voxel values. The ana-
lysis of these matrices leads to new imaging biomarkers, such as het-
erogeneity, contrast, or spatial fragmentation. Based on our results, it
seems that these parameters have a better discriminative capability
to identify invasive and radionuclide markers of plaque vulnerability
than visual inspection and conventional quantitative assessment.
Coronary CTA for many years was regarded as a rule-out test for
obstructive coronary artery disease due to its excellent negative pre-
dictive value.
24,25
However, its unique ability to non-invasively image
atherosclerotic lesions holds great potential to identify high-risk pla-
ques. With the newest guidelines promoting coronary CTA as the
first-line test in the management of patients with stable chest pain,
the number of examinations will further increase.
26
Therefore, the
next challenge will be to correctly identify high-risk lesions to
Figure 4 Diagnostic evaluation of radiomics and conventional CT parameters to identify OCT-TCFA. (A) Average receiver operating characteris-
tic curves ofthe best radiomic (pink): fractal box counting dimension of high attenuation voxels (component 8 when discretizing to eight equally sized
bins); and the best conventional (blue)parameter: presence of low attenuation, which were calculated by averaging the receiver operating character-
istic curves after 1000 repeats of the five-fold cross-validation process. Panel b: distribution of the AUC values calculated during the five-fold cross-
validation process repeated 1000 times. Dashed lines indicate the means of the AUC distributions. Results are based on the analysis of 44 plaques of
25 patients. (C) Manhattan-plot of radiomic features’ AUC values. Radiomic parameters are situated in consecutive order on the xaxis, while their
corresponding AUC values to identify OCT-TCFA are shown on the yaxis. AUC, area under the curve; GLCM, grey level co-occurrence matrix;
GLRLM, grey level run length matrix.
6M. Kolossva´ry et al.
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
improve patient risk assessment. Invasive and radionuclide imaging
techniques can identify high-risk lesions; however, their invasive na-
ture and their costs preclude the use of these techniques in daily rou-
tine. While CT might not have sufficient spatial resolution, its
capability to acquire isotropic 3D data non-invasively creates a
unique opportunity to analyse complex spatial image patterns using
radiomics.
Invasive imaging modalities with sub-millimetre spatial resolution
allow the morphological assessment of coronary plaques. Specific
IVUS and OCT imaging markers have been linked to histology and
patient outcomes. Our results are in line with previous findings that
conventional assessment of coronary CTA only allows identification
of invasive imaging markers of plaque vulnerability with moderate ac-
curacy.
27
However, in the current study, we showed that radiomic
features significantly outperformed conventional metrics, therefore,
potentially allowing the non-invasive identification of invasive imaging
markers plaque vulnerability.
For both IVUS-attenuated plaque and OCT-TCFA fractal box
counting dimension of high attenuation voxels had the highest AUC
values. Attenuated plaques based onIVUS are resembled by a hypoe-
choic plaque area with low ultrasound attenuation indicating the
presence of lipids. TCFA-s identified using OCT have a similar spatial
pattern; however, the superior spatial resolution of OCT allows the
assessment of fibrous-cap thickness, therefore, allowing the identifi-
cation of TCFA. While the spatial resolution of state-of-the-art cor-
onary CTA-s preclude the identification of the fibrous-cap, the large
lipid pools of these lesions have low CT attenuation. As the low at-
tenuation voxels of the lipid pools are situated in the central portion
of the plaque, next to each other, the remaining higher attenuation
voxels (relative to other voxel values in the plaque, but not
necessarily representing calcification) are limited in number and oc-
cupy limited space. On the other hand, plaques that do not exhibit
large lipid pools have more high attenuation voxels, which can oc-
cupy any position inside the plaque in a complex spatial pattern,
which can be described using fractal dimensions. Fractal dimensions
quantify the spatial complexity of structures. Fractal dimensions are
calculated by magnifying the image and assessing how many voxels
the given abnormality occupies in relation to the degree of zoom.
11
In case of plaques with large lipid pool, the high attenuation voxels
are relatively few in number and have limited space to occupy.
Therefore, these plaques have low value of fractal box counting di-
mension of high attenuation voxels. On the other hand, stable pla-
ques, which do not restrict the spatial distribution of high attenuation
voxels have higher values for this radiomic parameter. These charac-
teristics might explain that the fractal box counting dimension of high
attenuation voxels resulted a good discriminatory power to identify
invasive markers of plaque vulnerability.
Even though coronary CTA is an anatomical imaging modality, it
seems that radiomics can identify plaques with inflammation and
microcalcifications identified using NaF
18
-PET (AUC = 0.87), both of
which are currently regarded as undetectable using coronary CTA.
Visual assessment might not be sufficientto distinguish these features.
However, it was recently demonstrated that by using simple quantita-
tive metrics it is indeed possible to quantify vascular inflammation
using CT, which previously was thought impossible.
28
Importantly
microscopic calcium formations are too small to be identified using
conventional CTA techniques. However, it seems that radiomics can
identify unique spatial patterns specific for sodium-fluoride uptake.
Among the calculated radiomics parameters the surface of high at-
tenuationvoxels (relative to other voxel values in the plaque, but not
Figure 5 Diagnostic evaluation of radiomics and conventional CT parameters to identify radionuclide activity on NaF
18
-PET. (A) Receiver operat-
ing characteristic curves of the best radiomic (pink): surface of high attenuation voxels (component 8 when discretizing to eight equally sized bins);
and the best conventional (blue) parameter: presence of two high-risk features, which were calculated by averaging the receiver operating character-
istic curves after 1000 repeats of the five-fold cross-validation process. (B) Distribution of the AUC values calculated during the five-fold cross-valid-
ation process repeated 1000 times. Dashed lines indicate the means of the AUC distributions. Results are based on the analysis of 44 plaques of 25
patients. (C) Manhattan-plot of radiomic features’ AUC values. Radiomic parameters are situated in consecutive order on the xaxis, while their corre-
sponding AUC values to identify radionuclide activity on NaF
18
-PET are shown on the yaxis. AUC, area under the curve; GLCM, grey level co-occur-
rence matrix; GLRLM, grey level run length matrix.
Radiomics to identify plaque vulnerability 7
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
necessarily voxel values above the calcification threshold) had the
highest AUC value to identify increased radionuclide uptake. Even
though the spatial resolution of CTA images precludes the identifica-
tion of microcalcifications, voxels containing microcalcifications may
have higher HU values. Furthermore, these high CT number voxels
have large surfaces, since they are not grouped in one cluster as
opposed to calcified plaques, which also contain high attenuation
voxels but overall have smaller surfaces since the voxels are next to
each other. These characteristics may have resulted in the excellent
diagnostic accuracy of surface of high attenuation voxels to identify
increased radionuclide uptake. As there are no plaques showing both
invasive and radionuclide imaging markers of plaque vulnerability, the
capability of coronary CTA radiomics to identify NaF
18
-positive is in-
dependent of its ability to identify morphologic vulnerability.
A limitation of our study is the relatively small sample size, which
might lead to overly optimistic diagnostic results. However, consider-
ing that four different imaging techniques were utilized in all patients,
we believe that our patient cohort is unique and the sample size is
reasonable. To compensate for the limited sample size, we calculated
all diagnostic scores using a five-fold cross-validation with 1000
repeats. This technique explicitly simulates the population’s AUC
value of each parameter and provides a robust estimate of diagnostic
accuracy. Furthermore, our results are based on a single centre study
setting where the results were analysed in a core lab. Therefore, the
application of our results to general populations is limited as studies
have shown that image acquisition, reconstruction, and analysis may
have a significant effect on the reproducibility of radiomic features.
29–
32
However, further investigations are necessary for radiomics to be
applicable to clinical care. Larger sample size prospective studies are
needed, where the number of patients would allow to build multi-
parametric machine learning models, which could robustly identify
imaging markers of plaque vulnerability. Furthermore, multi-centre
longitudinal studies are warranted to assess the prognostic value of
radiomic image markers.
In conclusion, our results suggest that radiomics may be able to
identify invasive and radionuclide imaging markers of plaque
Figure 6 Representative curved multiplanar and volume rendered CT images of three coronary plaques corresponding to specific invasive
and radionuclide imaging markers of plaque vulnerability. (A) A coronary lesion which scored the lowest on fractal box counting dimension of high at-
tenuation voxels (component 30 when discretizing to 32 equally sized bins) which was indicative of attenuated plaque on IVUS [AUC: 0.72
(0.65–0.78)]. (B) Depicts a coronary plaque which scored the lowest on fractal box counting dimension of high attenuation voxels (component
8 when discretizing to eight equally sized bins) which was suggestive of OCT-TCFA [AUC: 0.80 (0.72–0.88)]. (C) A coronary lesion which had a
high surface of high attenuation voxels (component 8 when discretizing to eight equally sized bins) which was the best parameter to identify NaF
18
-
PET positivity [AUC: 0.87 (0.82–0.91)]. AUC, area under the curve; IVUS, intravascular ultrasound; NaF
18
-PET, NaF
18
-positron emission tomography;
OCT-TCFA, optical coherence tomography identified thin-cap fibroatheroma.
a
Component 30 when discretizing to 32 equally sized bins.
b
Component 8 when discretizing to eight equally sized bins.
8M. Kolossva´ry et al.
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
vulnerability with good to excellent diagnostic accuracy. It seems that
there is minimal overlap between anatomical vulnerability features of
invasive imaging modalities and NaF
18
-positivity, which is also
reflected by our findings that different radiomic parameters were
predictive for these features. Advanced texture analysis of CT images
holds magnitudes more information than currently perceivable by
clinical visual assessment. These CT radiomic information may allow
to identify invasive and radionuclide imaging markers from conven-
tional CT images. Identification of these vulnerability markers by a sin-
gle, widely available non-invasive technique may provide an
opportunity to identify vulnerable plaques and vulnerable patients in
broad populations without invasive procedures or costly radio-
nuclide tests. Further studies are warranted to assess the true poten-
tial of radiomics to aid precisionphenotyping of coronary disease.
Funding
The study was supported by a grant of the Ministry of Health & Welfare,
Republic of Korea (grant number: HI14C1277) and was also was sup-
ported by the National Research, Development and Innovation Office of
Hungary (NKFIA; NVKP-16-1-2016-0017). Furthermore, the research
was financed by the Higher Education Institutional Excellence Program of
the Ministry of Human Capacities in Hungary, within the framework of
the Therapeutic Development thematic programme of the Semmelweis
University.
Conflict of interest: M.K. is the creator and developer of the free
open-source Radiomics Image Analysis (RIA) software package which
was used for radiomic analysis. All remaining authors have declared no
conflicts of interest.
References
1. Stone GW, Maehara A, Lansky AJ, de Bruyne B, Cristea E, Mintz GS et al. A pro-
spective natural-history study of coronary atherosclerosis. N Engl J Med 2011;
364:226–35.
2. Joshi NV, Vesey AT, Williams MC, Shah AS, Calvert PA, Craighead FH et al.
18
F-
fluoride positron emission tomography for identification of ruptured and high-
risk coronary atherosclerotic plaques: a prospective clinical trial. Lancet 2014;
383:705–13.
3. Koskinas KC, Ughi GJ, Windecker S, Tearney GJ, Raber L. Intracoronary imaging
of coronary atherosclerosis: validation for diagnosis, prognosis and treatment.
Eur Heart J 2016;37:524–35a-c.
4. Tearney GJ, Regar E, Akasaka T, Adriaenssens T, Barlis P, Bezerra HG et al.
Consensus standards for acquisition, measurement, and reporting of intravascu-
lar optical coherence tomography studies: a report from the International
Working Group for Intravascular Optical Coherence Tomography
Standardization and Validation. J Am Coll Cardiol 2012;59:1058–72.
5. Calvert PA, Obaid DR, O’Sullivan M, Shapiro LM, McNab D, Densem CG et al.
Association between IVUS findings and adverse outcomes in patients with cor-
onary artery disease: the VIVA (VH-IVUS in Vulnerable Atherosclerosis) Study.
JACC Cardiovasc Imaging 2011;4:894–901.
6. Cheng JM, Garcia-Garcia HM, de Boer SP, Kardys I, Heo JH, Akkerhuis KM et al.
In vivo detection of high-risk coronary plaques by radiofrequency intravascular
ultrasound and cardiovascular outcome: results of the ATHEROREMO-IVUS
study. Eur Heart J 2014;35:639–47.
7. Dweck MR, Chow MW, Joshi NV, Williams MC, Jones C, Fletcher AM et al.
Coronary arterial
18
F-sodium fluoride uptake: a novel marker of plaque biology. J
Am Coll Cardiol 2012;59:1539–48.
8. Kolossva´ry M, Szilveszter B, Merkely B, Maurovich-Horvat P. Plaque imaging with
CT—a comprehensive review on coronary CT angiography based risk assess-
ment. Cardiovasc Diagn Ther 2017;7:489–506.
9. Lee JM, Bang JI, Koo BK, Hwang D, Park J, Zhang J et al. Clinical relevance of
(18)F-sodium fluoride positron-emission tomography in noninvasive identification
of high-risk plaque in patients with coronary artery disease. Circ Cardiovasc
Imaging 2017;10:e006704.
10. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they
are data. Radiology 2016;278:563–77.
11. Kolossvary M, Kellermayer M, Merkely B, Maurovich-Horvat P. Cardiac com-
puted tomography radiomics: a comprehensive review on radiomic techniques. J
Thorac Imaging 2018;33:26–34.
12. Kolossvary M, Karady J, Szilveszter B, Kitslaar P, Hoffmann U, Merkely B et al.
Radiomic features are superior to conventional quantitative computed tomo-
graphic metrics to identify coronary plaques with napkin-ring sign. Circ Cardiovasc
Imaging 2017;10:e006843.
13. Leipsic J, Abbara S, Achenbach S, Cury R, Earls JP, Mancini GJ et al. SCCT guide-
lines for the interpretation and reporting of coronary CT angiography: a report
of the Society of Cardiovascular Computed Tomography Guidelines Committee.
J Cardiovasc Comput Tomogr 2014;8:342–58.
14. Maurovich-Horvat P, Schlett CL, Alkadhi H, Nakano M, Otsuka F, Stolzmann P
et al. The napkin-ring sign indicates advanced atherosclerotic lesions in coronary
CT angiography. JACC Cardiovasc Imaging 2012;5:1243–52.
15. Karolyi M, Szilveszter B, Kolossvary M, Takx RA, Celeng C, Bartykowszki A et al.
Iterative model reconstruction reduces calcified plaque volume in coronary CT
angiography. Eur J Radiol 2017;87:83–9.
16. Hoffmann U, Moselewski F, Nieman K, Jang IK, Ferencik M, Rahman AM et al.
Noninvasive assessment of plaque morphology and composition in culprit and
stable lesions in acute coronary syndrome and stable lesions in stable angina by
multidetector computed tomography. J Am Coll Cardiol 2006;47:1655–62.
17. Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification.
IEEE Trans Syst, Man, Cybern 1973;SMC-3:610–21.
18. Galloway MM. Texture analysis using gray level run lengths. Comput Graph Image
Process 1975;4:172–9.
19. Kolossva´ry M. RIA: Radiomics Image Analysis Toolbox for Grayscale Images. 2017.
https://CRAN.R-project.org/package=RIA (22 February 2019, date last accessed).
20. Maehara A, Mintz GS, Bui AB, Walter OR, Castagna MT, Canos D et al.
Morphologic and angiographic features of coronary plaque rupture detected by
intravascular ultrasound. J Am Coll Cardiol 2002;40:904–10.
21. Mintz GS, Nissen SE, Anderson WD, Bailey SR, Erbel R, Fitzgerald PJ et al.
American College of Cardiology Clinical Expert Consensus Document on
Standards for Acquisition, Measurement and Reporting of Intravascular
Ultrasound Studies (IVUS). A report of the American College of Cardiology
Task Force on Clinical Expert Consensus Documents. J Am Coll Cardiol 2001;37:
1478–92.
22. Kim JH. Estimating classification error rate: repeated cross-validation, repeated
hold-out and bootstrap. Comput Stat Data Anal 2009;53:3735–45.
23. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O et al.
Scikit-learn: machine learning in python. J Mach Learn Res 2011;12:2825–30.
24. Marwick TH, Cho I, O
´Hartaigh B, Min JK. Finding the gatekeeper to the cardiac
catheterization laboratory: coronary CT angiography or stress testing? J Am Coll
Cardiol 2015;65:2747–56.
25. Yang L, Zhou T, Zhang R, Xu L, Peng Z, Ding J et al. Meta-analysis: diagnostic ac-
curacy of coronary CT angiography with prospective ECG gating based on step-
and-shoot, Flash and volume modes for detection of coronary artery disease. Eur
Radiol 2014;24:2345–52.
26. National Institute for Health and Care Excellence (NICE). Chest Pain of Recent
Onset: Assessment and Diagnosis [CG95]. 2016. https://www.nice.org.uk/guid
ance/cg95/chapter/recommendations (23 February 2019, date last accessed).
27. Maurovich-Horvat P, Schlett CL, Alkadhi H, Nakano M, Stolzmann P, Vorpahl M
et al. Differentiation of early from advanced coronary atherosclerotic lesions: system-
atic comparison of CT, intravascular US, and optical frequency domain imaging with
histopathologic examination in ex vivo human hearts. Radiology 2012;265:393–401.
28. Antonopoulos AS, Sanna F, Sabharwal N, Thomas S, Oikonomou EK, Herdman L
et al. Detecting human coronary inflammation by imaging perivascular fat. Sci
Transl Med 2017;9:eaal2658.
29. Berenguer R, Pastor-Juan MDR, Canales-Vazquez J, Castro-Garcia M, Villas MV,
Mansilla Legorburo F et al. Radiomics of CT features may be nonreproducible
and redundant: influence of CT acquisition parameters. Radiology 2018;288:
407–15.
30. Altazi BA, Zhang GG, Fernandez DC, Montejo ME, Hunt D, Werner J et al.
Reproducibility of F18-FDG PET radiomic features for different cervical tumor
segmentation methods, gray-level discretization, and reconstruction algorithms. J
Appl Clin Med Phys 2017;18:32–48.
31. Shafiq-Ul-Hassan M, Zhang GG, Latifi K, Ullah G, Hunt DC, Balagurunathan Y
et al. Intrinsic dependencies of CT radiomic features on voxel size and number
of gray levels. Med Phys 2017;44:1050–62.
32. Kolossvary M, Szilveszter B, Karady J, Drobni ZD, Merkely B, Maurovich-Horvat P.
Effect of image reconstruction algorithms on volumetric and radiomic para meters of
coronary plaques. J Cardiovasc Comput Tomogr 2018;doi:10.1016/j.jcct.2018.11.004.
Radiomics to identify plaque vulnerability 9
Downloaded from https://academic.oup.com/ehjcimaging/advance-article-abstract/doi/10.1093/ehjci/jez033/5369799 by Johns Hopkins University user on 09 May 2019
