- Academic Editors
†These authors contributed equally.
Background: The noninvasive computed tomography angiography–derived
fractional flow reserve (CT-FFR) can be used to diagnose coronary ischemia. With
advancements in associated software, the diagnostic capability of CT-FFR may have
evolved. This study evaluates the effectiveness of a novel deep learning-based
software in predicting coronary ischemia through CT-FFR. Methods: In
this prospective study, 138 subjects with suspected or confirmed coronary artery
disease were assessed. Following indication of 30%–90% stenosis on coronary computed tomography (CT)
angiography, participants underwent invasive coronary angiography and fractional flow reserve (FFR)
measurement. The diagnostic performance of the CT-FFR was determined using the
FFR as the reference standard. Results: With a threshold of
0.80, the CT-FFR displayed an impressive diagnostic accuracy, sensitivity,
specificity, area under the receiver operating characteristic curve (AUC),
positive predictive value (PPV), and negative predictive value (NPV) of 97.1%,
96.2%, 97.7%, 0.98, 96.2%, and 97.7%, respectively. At a 0.75 threshold, the
CT-FFR showed a diagnostic accuracy, sensitivity, specificity, AUC, PPV, and NPV
of 84.1%, 78.8%, 85.7%, 0.95, 63.4%, and 92.8%, respectively. The
Bland–Altman analysis revealed a direct correlation between the CT-FFR and FFR
(p
While invasive coronary angiography (ICA) provides limited anatomical information on the coronary artery, the results often form the basis for the decision to perform percutaneous coronary intervention (PCI) [1]. This reliance on ICA results in undesired outcomes, such as unnecessary PCI for functionally insignificant lesions or improper delays in PCI for functionally significant lesions [1]. An alternative method, the fractional flow reserve (FFR), serves as a hemodynamic correlation criterion that enhances the benefits of revascularization, improves event-free survival, and reduces health costs [2]. Despite its advantages, the invasive nature of FFR measurement, its need for expensive equipment, and the potential complications it may cause to the coronary artery limit its routine use in clinical practice.
For patients with low or moderate risk coronary artery disease (CAD), noninvasive tests such as the anatomy-based coronary computed tomography angiography (CCTA) can be attempted prior to more invasive testing [3, 4]. While CCTA is considered the first-line approach [4], with strengths including a high sensitivity (87%–99%) and moderate specificity (61%–83%) [5], the relatively high false-positive rate may lead to an increase in the need for ICA. More concerning is CCTA’s inability to assess the physiological function of the coronary artery based on the severity of coronary anatomical stenosis alone.
A promising solution to these limitations is the noninvasive computed tomography angiography–derived FFR (CT-FFR) [6]. This method can assess lesion-specific ischemia via computational fluid dynamics (CFD) without requiring changes to the CCTA data collection protocol, additional imaging, or drugs [6]. Impressively, CT-FFR has demonstrated an overall accuracy of 85% sensitivity and 82% specificity in pinpointing lesion-specific ischemia [6]. To streamline the integration of CT-FFR into clinical workflows and improve diagnostic accuracy, new software and algorithms have been created. These innovations facilitate cost-effective CT-FFR analyses on a standard workstation, eliminating the need for unnecessary ICA.
Machine learning-based flow assessments using artificial intelligence algorithms have recently been introduced to perform CT-FFR analysis. Coenen et al. [7] and Qiao et al. [8] suggested a supervised learning approach that involved training with diverse features from different anatomies and degrees of CAD, utilizing reduced-order CFD to compute CT-FFR values. In this prospective study, we assessed the diagnostic characteristics of CT-FFR by employing new deep learning software specifically designed for coronary lesion-specific ischemia analysis. This novel software package consists of two components: the Coronary Scope, a deep learning tool for evaluating the physiological function of the coronary artery, and the Compute Unified Device Architecture (CUDA) accelerated CFD software, tailored for analyzing incompressible fluid flow equations. These clinical experiments were conducted to evaluate the ability of the CT-FFR to identify coronary ischemia at FFR thresholds of 0.80 and 0.75, providing insights into its effectiveness and potential applications in CAD diagnosis.
This prospective trial evaluated the diagnostic characteristics of the CT-FFR with a novel software research prototype (coronary artery physiological function assessment software: Coronary Scope V1.0, Shenzhen Yueying Technology Co., Ltd., Shenzhen, China) to diagnose lesion-specific ischemia in subjects with suspected or known CAD. The CT-FFR was evaluated for stenosis in one target vessel per patient. This study protocol was approved by the Institutional Audit Committee of Shaanxi Provincial People’s Hospital. Informed written consent was obtained from all participants.
The study included patients with known or suspected CAD who underwent ICA and
FFR measurement after CCTA from 1 December 2019 to 30 June 2020. The selection
criteria included patients aged
Flowchart of patient recruitment. CAD, coronary artery disease; CCTA, coronary computed tomography angiography; FFR, fractional flow reserve; ICA, invasive coronary angiography.
CCTA was performed in each hospital using a variety of computed tomography scanner platforms with a minimum of 64 detector rows (Aquilion Vision, Toshiba, Otawara, Japan; GE Revolution, GE Healthcare, Milwaukee, Wisconsin; uCT960+, United imaging, Shanghai, China; Somatom Force and Definition Flash, Siemens, Forchheim, Germany). During the collection process, an intravenous infusion of 80–100 mL iodized contrast medium was administered. Image acquisition was performed using either prospective triggering or retrospective gating. Images were acquired of areas including the left ventricle, coronary arteries, and proximal ascending aorta.
Two blinded, experienced CT cardiologists analyzed the CCTA images as described
in previous studies [9]. The two CT cardiologists analyzed the CCTA images
independently, and any disagreements were reconciled through consensus. A three-dimensional (3D)
image analysis workstation was used to assess the CCTA images. Coronary artery
stenosis was defined as the maximum stenosis identified in all segments within
the vascular distribution. Coronary lesions were categorized based on the reduced
diameter as a percentage of obstruction into 0%, 1%–29%, 30%–49%,
50%–69%, 70%–90%, subtotally (
CT-FFR calculations were conducted based on regular CCTA data; there was no need to change the data collection protocol, acquire additional images, or administer drugs. The prototype coronary artery physiological function assessment software (Coronary Scope, Shenzhen Yueying Technology Co., Ltd., Shenzhen, Guangdong, China) was installed on a regular workstation of the independent core laboratory (Shenzhen Yueying Technology Co., Ltd., Shenzhen, Guangdong, China). The CT-FFR software was based on NVIDIA’s CUDA-accelerated CFD solver, which divides the solution of the incompressible fluid flow equation into distinct CUDA kernels and suggests a unique implementation that exploits the memory hierarchy of the CUDA programming model. Hence, the CT-FFR software overcomes the highly computationally intensive and time-consuming problem of traditional CT-FFR software.
This CT-FFR algorithm simulates coronary blood flow and patient-specific limit
conditions of the hyperemic state established by CFD. The heart rate, diastolic
pressure, and systolic pressure of patients are integrated and modified to
incorporate the effect of maximal hyperemia to mimic decreases induced by
pharmacological stress in microvascular resistance. The CT-FFR was calculated
according to the patient’s specific three-dimensional mesh and contour
conditions. The patient’s diastolic pressure and systolic pressure of the
brachial artery and heart rate were measured before CCTA, and entered into the
software. The CT-FFR, at each point of the coronary shaft, was calculated using a
three-dimensional color-coded mesh. The CT-FFR is calculated as the mean coronary
blood pressure as distal to the pathology as possible divided by the mean
arterial blood pressure calculated when simulating maximum congestion. In brief,
The no-new-Net (nnU-Net) deep learning architecture was used to complete automated segmentation of the coronary artery tree. The CT-FFR is based on CUDA-accelerated CFD analysis, which can calculate results with low running time on standard hardware. The nnU-Net is the first segmentation framework to contend with the dataset diversity found in this domain, and is capable of automatically designing and executing a successful network training pipeline for new datasets based on the analysis of existing datasets. Relying on a simple U-Net architecture, nnU-Net can automatically make necessary adjustments to parameters such as preprocessing, batch size, patch size, and inference setting factors that influence several other hyperparameters in the pipeline. Hence, nnU-Net can improve the segmentation accuracy without any manual hyperparameter tuning between different datasets. This process required approximately 5–10 min per case, depending on the quality of CCTA images and the load of atherosclerotic plaque.
Experienced invasive cardiologists performed ICA via a femoral or radial approach. Two experienced invasive cardiologists assessed coronary stenosis on site. Nitroglycerin was administered intracoronary before FFR measurement. A guide cable for pressure monitoring (PressureWire Certus, St. Jude Medical, Inc., Minneapolis, MN, USA) was used. Continuous intravenous (IV) infusion of adenosine (140 µg/kg/min) through the femoral vein. The FFR was obtained automatically as previously described [10]. The gray area of ischemic stenosis recognized by the FFR measurement method was between 0.75 and 0.80.
Categorical variables are presented as frequencies and percentages. Continuous
variables are presented as the means
The study population included a total of 138 patients (age 62.4
Parameter | All (n = 138) | CT-FFR | CT-FFR | |||
Mean age, yrs | 62.4 |
60.6 |
63.5 |
60.8 |
62.9 | |
Male | 89 (64.5%) | 37 (69.8%) | 52 (61.2%) | 26 (78.8%) | 63 (60.0%) | |
BMI, kg/m |
24.6 |
24.2 |
24.8 |
24.1 |
24.7 | |
Hypertension | 69 (50.0%) | 23 (43.4%) | 46 (54.1%) | 12 (36.4%) | 57 (54.3%) | |
Hyperlipidemia† | 29 (21.0%) | 14 (26.4%) | 15 (17.6%) | 11 (33.3%) | 18 (17.1%) | |
Diabetes mellitus | 35 (25.4%) | 12 (22.6%) | 23 (27.1%) | 5 (15.2%) | 30 (28.6%) | |
Smoking | ||||||
Former smokers | 14 (10.1%) | 7 (13.2%) | 7 (8.2%) | 5 (15.2%) | 9 (8.6%) | |
Current smokers | 31 (22.5%) | 16 (30.2%) | 15 (17.6%) | 10 (30.3%) | 21 (20.0%) | |
Never smokers | 93 (67.4%) | 30 (56.6%) | 63 (74.1%) | 18 (54.5%) | 75 (71.4%) | |
Cardiovascular history | ||||||
Prior myocardial infarction | 2 (1.4%) | 0 (0.0%) | 2 (2.4%) | 0 (0.0%) | 2 (1.9%) | |
Peripheral vascular diseases | 8 (5.8%) | 2 (3.8%) | 6 (7.1%) | 1 (3.0%) | 7 (6.7%) | |
Angina type | ||||||
Typical | 99 (71.7%) | 40 (75.5%) | 59 (69.4%) | 27 (81.8%) | 72 (68.6%) | |
Atypical | 39 (28.3%) | 13 (24.5%) | 26 (30.6%) | 6 (18.2%) | 33 (31.4%) | |
Laboratory measures | ||||||
White blood cell count, ×10 |
6.3 |
6.3 |
6.3 |
6.7 |
6.2 | |
Red blood cell count, ×10 |
4.5 |
4.6 |
4.5 |
4.6 |
4.5 | |
Blood platelet count, ×10 |
200.6 |
206.5 |
196.9 |
215.2 |
196.0 | |
Hemoglobin, g/L | 138.8 |
140.1 |
138.1 |
141.3 |
138.0 | |
Creatinine, µmol/L | 74.2 |
75.1 |
73.6 |
74.8 |
74.0 | |
Serum urea, mmol/L | 5.5 |
5.6 |
5.5 |
5.3 |
5.6 | |
Interval between CT-FFR and FFR measurement, days | 1.8 |
2.2 |
1.5 |
1.7 |
1.8 |
Data are expressed as the mean
The CCTA scan parameters are presented in Table 2. The mean tube current and
dose length product were 341.0
Parameter | All (n = 138) | CT-FFR | CT-FFR | |||
Vital signs | ||||||
Systolic blood pressure, mmHg | 129.0 |
128.1 |
129.6 |
127.8 |
129.4 | |
Diastolic blood pressure, mmHg | 78.2 |
80.1 |
77.1 |
80.8 |
77.4 | |
Heart rate, beats/min | 73.1 |
74.4 |
72.3 |
73.5 |
73.0 | |
Tube voltage | ||||||
70 kV | 13 (9.4%) | 6 (11.3%) | 7 (8.2%) | 5 (15.2%) | 8 (7.6%) | |
80 kV | 8 (5.8%) | 3 (5.7%) | 5 (5.9%) | 1 (3.0%) | 7 (6.7%) | |
100 kV | 60 (43.5%) | 24 (45.3%) | 36 (42.4%) | 13 (39.4%) | 47 (44.8%) | |
120 kV | 56 (40.6%) | 19 (35.8%) | 37 (43.5%) | 14 (42.4%) | 42 (40.0%) | |
140 kV | 1 (0.7%) | 1 (1.9%) | 0 (0.0%) | 0 (0.0%) | 1 (1.0%) | |
Tube current (mAs) | 341.0 |
321.7 |
353.1 |
348.4 |
338.7 | |
Dose length product (mGy-cm) | 369.1 |
406.2 |
346.1 |
370.9 |
368.6 |
Data are expressed as the mean
Of the 138 evaluated lesions, two vessels (1.4%) had a left main lesion, 99 vessels (71.7%) had a left anterior descending lesion, 28 vessels (20.3%) had a right coronary artery lesion, and nine vessels (6.5%) had a left circumflex lesion. Thirty-six vessels had 30%–49% stenosis, 64 vessels had 50%–69% stenosis, and 38 vessels had 70%–90% stenosis. Detailed data for vessel and lesion characteristics are shown in Table 3. Lesion-specific ischemia as a function of stenosis category is presented in Table 4.
Parameter | All (n = 138) | CT-FFR | CT-FFR | |||
Target vessel | ||||||
Left main artery | 2 (1.4%) | 1 (1.9%) | 1 (1.2%) | 1 (3.0%) | 1 (1.0%) | |
Left anterior descending | 99 (71.7%) | 44 (83.0%) | 55 (64.7%) | 25 (75.8%) | 74 (70.5%) | |
Right coronary artery | 28 (20.3%) | 8 (15.1%) | 20 (23.5%) | 7 (21.2%) | 21 (20.0%) | |
Left circumflex | 9 (6.5%) | 0 (0.0%) | 9 (10.6%) | 0 (0.0%) | 9 (8.6%) | |
Stenosis category | ||||||
30%–49% | 36 (26.1%) | 5 (9.4%) | 31 (36.5%) | 4 (12.1%) | 32 (30.5%) | |
50%–69% | 64 (46.4%) | 27 (50.9%) | 35 (41.2%) | 13 (39.4%) | 51 (48.6%) | |
70%–90% | 38 (27.5%) | 21 (39.6%) | 17 (20.0%) | 16 (48.5%) | 22 (21.0%) | |
Plaque features | ||||||
Noncalcified plaque | 46 (33.3%) | 19 (35.8%) | 27 (31.8%) | 15 (45.5%) | 31 (29.5%) | |
Calcified plaque | 92 (66.7%) | 34 (64.2%) | 58 (68.2%) | 18 (54.5%) | 74 (70.5%) |
Data are presented as percentages (%). CT-FFR, computed tomography angiography-derived FFR; FFR, fractional flow reserve.
Stenosis Category | CT-FFR |
CT-FFR |
FFR |
FFR |
30%–49% (n = 36) | 5 (17.7%) | 4 (11.1%) | 7 (19.4%) | 6 (16.7%) |
50%–69% (n = 64) | 27 (42.2%) | 13 (20.3%) | 25 (39.1%) | 16 (25.0%) |
70%–90% (n = 38) | 21 (55.3%) | 26 (68.4%) | 21 (55.3%) | 19 (50.0%) |
Data are presented as percentages (%). CT-FFR, computed tomography angiography-derived FFR; FFR, fractional flow reserve.
The mean CT-FFR was 0.81
Measure | CT-FFR |
CT-FFR |
Accuracy (%) | 97.1 (92.7–99.2) | 84.1 (76.9–89.7) |
Sensitivity (%) | 96.2 (87.0–99.5) | 78.8 (61.1–91.0) |
Specificity (%) | 97.7 (91.8–99.7) | 85.7 (77.5–91.8) |
PPV (%) | 96.2 (86.6–99.0) | 63.4 (51.2–74.1) |
NPV (%) | 97.7 (91.4–99.4) | 92.8 (86.9–96.1) |
Positive likelihood ratio | 40.9 (10.4–161.0) | 5.5 (3.3–9.1) |
Negative likelihood ratio | 0.04 (0.01–0.15) | 0.25 (0.13–0.48) |
CT-FFR, computed tomography angiography-derived FFR; FFR, fractional flow reserve; NPV, negative predictive value; PPV, positive predictive value.
Distribution of CT-FFR and FFR. CT-FFR, computed tomography angiography-derived FFR; FFR, fractional flow reserve.
AUC of CT-FFR
CT-FFR is related to FFR. A good Pearson’s correlation
coefficient of 0.83 was obtained, p
Bland–Altman plot comparing the FFR and CT-FFR shows no systematic differences (average difference –0.019; 95% agreement limits –0.27 to 0.23). CT-FFR, computed tomography angiography-derived FFR; FFR, fractional flow reserve.
This prospective study revealed that the new CT-FFR deep learning software exhibits a strong direct correlation with FFR and is effective in diagnosing lesion-specific ischemia. Furthermore, we confirmed the efficacy of CT-FFR to detect coronary artery ischemia with stenosis ranging from 30%–90% prior to an ICA referral.
Building on the findings of our study, FFR has emerged as a critical reference
for managing coronary artery stenosis, allowing physicians to determine whether
revascularization or drug therapy alone is the best course of action. It’s worth
noting that the gray area of ischemic stenosis recognized by FFR ranges between
0.75 and 0.80. The well-known DEFER (Deferral versus Performance of Percutaneous Coronary Intervention of Functionally Nonsignificant Coronary Stenosis) and DEFER-DES (Proper Fractional Flow Reserve Criteria for Intermediate Lesions in the Era of Drug-eluting Stent) studies used the lower limit of
the gray area (0.75) for decision-making regarding lesion ischemia [11, 12].
Notably, the DEFER randomized controlled study found delayed PCI based on an FFR
The well-known FAME (Fractional Flow Reserve Versus Angiography for Multivessel Evaluation) and FAME 2 trials, which used the upper limit of the gray
area (0.80) for FFR, brought interesting insights into the management of coronary
artery stenosis [13, 14]. The FAME trial at one year of follow-up and the FAME 2
study at three years of follow-up reported that FFR-guided PCI reduced major
cardiovascular events when the FFR was
CCTA is an established noninvasive modality increasingly used to detect suspicious CAD. However, its inability to assess the hemodynamic effects of lesions and a high false-positive rate result in an overall overestimation of coronary artery stenosis. Even when ICA confirms obstructive coronary lesions diagnosed by CCTA, only a minority lead to coronary ischemia. Therefore, for moderate coronary stenosis determined by CCTA, a functional test is now recommended prior to ICA referral [16].
The need for a validated noninvasive diagnostic method is clear, and the CT-FFR,
based on CFD, presents a promising solution. It
can accurately identify the hemodynamic effects of lesions and has the potential
to significantly reduce unnecessary ICA. A prospective multicenter trial
demonstrated the feasibility of CT-FFR, showing a reduction of up to 61% of
potential ICA procedures [17]. Furthermore, stable CAD patients with a negative
CT-FFR (
We investigated novel prototype software for deriving the CT-FFR from CCTA data,
which we then compared with the FFR. Previous CT-FFR studies have used a 0.80
threshold to detect lesion-specific ischemia in comparisons with the FFR [19, 20, 21, 22, 23].
Our study revealed that the CT-FFR threshold of 0.80 provided good diagnostic
accuracy, sensitivity, and specificity (97.1%, 96.2%, and 97.7% respectively),
with an AUC of 0.98, exceeding results from previous studies (Table 6, Ref.
[19, 20, 21, 23, 24, 25, 26, 27, 28]). This advancement may be attributed to improvements in the
CT-FFR algorithm, the incorporation of deep learning analysis, and unique
boundary conditions applied to the new software research prototype. Furthermore,
the CT-FFR threshold of 0.75 also exhibited solid diagnostic accuracy,
sensitivity, and specificity (84.1%, 78.8%, and 85.7% respectively), with an
AUC of 0.95. A direct correlation between CT-FFR and FFR was established
(p
Study | CT-FFR software | Cut-off value | Accuracy | Sensitivity | Specificity | AUC |
Koo et al. [19] | HeartFlow V1.0 | 84.3% | 87.9% | 82.2% | 0.90 | |
Min et al. [25] | HeartFlow V1.2 | - | 80% | 61% | - | |
Nørgaard et al. [26] | HeartFlow V1.4 | 86% | 84% | 86% | 0.93 | |
Renker et al. [27] | Siemens cFFR V1.4 | - | 85% | 85% | 0.92 | |
Wardziak et al. [21] | Siemens cFFR V2.1 | 74% | 76% | 72% | 0.835 | |
Röther et al. [20] | Siemens cFFR V3.0 | 93% | 91% | 96% | 0.94 | |
Ko et al. [28] | Toshiba Medical Systems | 83.9% | 77.8% | 86.8% | 0.88 | |
Fujimoto et al. [24] | Canon Medical Systems | 83.7% | 90.9% | 78.3% | 0.85 | |
Peper et al. [23] | IntelliSpace Portal Version 9.0 | 85.2% | 91.2% | 81.4% | 0.91 |
CT-FFR, computed tomography angiography-derived FFR; FFR, fractional flow reserve; cFFR, computed fractional flow reserve; AUC, area under the receiver operating characteristic curve.
While the study yielded promising insights, several limitations and unaddressed areas must be acknowledged. First, the relatively low number of samples could influence the robustness of the findings. The inclusion criteria, including 30%–90% coronary artery stenosis, may have introduced selection bias, potentially skewing the results. Furthermore, specific patient conditions, such as previous coronary artery bypass surgery (CABG) and stent implantation, were excluded from the study. This leaves the diagnostic value of the CT-FFR of such patients an open question that requires further examination. Finally, we did not report any clinical outcome observations for CT-FFR–guided revascularization, leaving an area for future exploration.
In this prospective trial, we utilized novel CT-FFR software to analyze CCTA data, comparing its findings with the established FFR. The key results include a strong direct correlation between the CT-FFR and FFR, along with high diagnostic performance for lesion-specific ischemia, particularly within a stenosis rate of 30%–90%. This study highlights the accuracy and clinical value of the CT-FFR, particularly when leveraging deep learning analysis. However, the findings are subject to certain limitations, notably the specificity of the inclusion and exclusion criteria, making them applicable only to specific patients and types of coronary stenosis. Consequently, the general applicability of the current conclusions require further study. Additionally, future studies should evaluate the novel CT-FFR software’s impact on CAD patients’ prognosis and compare it with other CT-FFR software solutions.
The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.
HW, WH, ZY, JQ, JD and YT contributed in the data collection, statistical analysis and manuscript drafting. HW, LL, XS and HC participated in data collection and manuscript revision. HW, LL, FQ, XS and HC was responsible for the study design, manuscript revision and consultation. All authors contributed to editorial changes in the manuscript. All authors read and approved the final manuscript. All authors have participated sufficiently in the work and agreed to be accountable for all aspects of the work.
The study was conducted in accordance with the Declaration of Helsinki, and the protocol was approved by the Ethics Committee of Shaanxi Provincial People’s Hospital (Approval No. 2019-X005). All subjects gave their informed consent for inclusion before they participated in the study.
Not applicable.
This research was partially supported by the Research and Development Program of Shaanxi Province (No. 2022ZDLSF02-03) and the Science and Technology Talent Support Program of Shaanxi Provincial People’s Hospital (No. 2021LJ-09, 2021JY-24).
The authors declare no conflict of interest.
Publisher’s Note: IMR Press stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.