Feasibility and prognostic role of machine learning-based FFRCT in patients with stent implantation

Tang, Chunbo; Guo, Bang Jun; Schoepf, Joseph; Bayer, Richard R.; Liu, Chun Yu; Qiao, Hong; Zhou, Fan; Lu, Guang Ming; Zhou, Chang Sheng; Zhang, Long Jiang

doi:10.1007/s00330-021-07922-w

Cited by 17 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each vessel was evaluated by two experienced cardiac radiologists (BQ and HZ, with 12 years and 8 years of experience in interpreting cardiac imaging, respectively) who were blinded to the clinical results of the patients. The definition of ISR is recurrent diameter stenosis at the stent segment or its edges (5 mm segments adjacent to the stent) compared to the normal proximal lumen on images orthogonal to the vessel ( 19 ). The stent characteristics, including locations, segments, length, and diameter, were recorded by the radiologists and any disagreement was resolved by consensus.…”

Section: Methodsmentioning

confidence: 99%

The Predictive Value of the Perivascular Adipose Tissue CT Fat Attenuation Index for Coronary In-stent Restenosis

Qin

Zhou

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

ObjectivesTo investigate the association between the perivascular adipose tissue (PVAT) fat attenuation index (FAI) derived from coronary computed tomography angiography (CCTA) and the prevalence of in-stent restenosis (ISR) in patients with coronary stent implantation.MethodsA total of 117 patients with previous coronary stenting referred for invasive coronary angiography (ICA) were enrolled in this retrospective observational analysis. All patients underwent CCTA between July 2016 and November 2021. The deep learning-based (DL-based) method was used to analyze and measure the peri-stent FAI value. Additionally, the relationship between hematological and biochemical parameters collected from all the patients was also explored. The least absolute shrinkage and selection operator (LASSO) method was applied to the most useful feature selection, and binary logistic regression was used to test the association between the selected features and ISR. The predictive performance for ISR of the identified subgroups was evaluated by calculating the area under the curve (AUC) of receiver operator curves plotted for each model. The Pearson correlation coefficient was used to assess the correlation of peri-stent FAI values with degrees of ISR.ResultsThe peri-stent FAI values in the ISR group were significantly higher than those in the non-ISR group (−78.1 ± 6.2 HU vs. −87.2 ± 7.3 HU, p < 0.001). The predictive ISR features based on the LASSO analysis were peri-stent FAI, high-density lipoprotein cholesterol (HDL-C), apolipoprotein A1 (ApoA1), and high-sensitivity c-reactive protein (hs-CRP), with an AUC of 0.849, 0.632, 0.620, and 0.569, respectively. Binary logistic regression analysis determined that peri-stent FAI was uniquely and independently associated with ISR after adjusting for other risk factors (odds ratio [OR] 1.403; 95% CI: 1.211 to 1.625; p < 0.001). In the subgroup analysis, the AUCs of the left anterior descending coronary artery (LAD), left circumflex coronary artery (LCx), and right coronary artery (RCA) stents groups were 0.80, 0.87, and 0.96, respectively. The Pearson's correlation coefficient indicated a term moderately correlation between ISR severity and peri-stent FAI values (r = 0.579, P < 0.001).ConclusionsThe peri-stent FAI can be used as an independently non-invasive biomarker to predict ISR risk and severity after stent implantation.

show abstract

Section: Methodsmentioning

confidence: 99%

The Predictive Value of the Perivascular Adipose Tissue CT Fat Attenuation Index for Coronary In-stent Restenosis

Qin

Zhou

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…Tang and colleagues recruited 33 patients with previous stent implantation from the China CT-FFR study who had undergone invasive FFR and CCTA examinations at least 3 months after stenting to explore the feasibility and prognostic value of CT-FFR in the occurrence of cardiovascular adverse events. They showed that the accuracy of CT-FFR in detecting hemodynamically significant in-stent restenosis was 86% and the change rate of CT-FFR values along with stent length was a major predictor of adverse outcome (HR=1.014, P =0.001) 112. In conclusion, the addition of CT-FFR may contribute to the optimization of follow-up procedures for patients with stent implantation history 107…”

Section: The Clinical Evidence Of Ct-ffrmentioning

confidence: 99%

Coronary Computed Tomography Angiography–derived Fractional Flow Reserve

Zhang

Tang

et al. 2022

Journal of Thoracic Imaging

Self Cite

View full text Add to dashboard Cite

Invasive fractional flow reserve (FFR) measured by a pressure wire is a reference standard for evaluating functional stenosis in coronary artery disease. Coronary computed tomography angiography-derived fractional flow reserve (CT-FFR) uses advanced computational analysis methods to noninvasively obtain FFR results from a single conventional coronary computed tomography angiography data to evaluate the hemodynamic significance of coronary artery disease. More and more evidence has found good correlation between the results of noninvasive CT-FFR and invasive FFR. CT-FFR has proven its potential in optimizing patient management, improving risk stratification and prognosis, and reducing total health care costs. However, there is still a lack of standardized interpretation of CT-FFR technology in real-world clinical settings. This expert consensus introduces the principle, workflow, and interpretation of CT-FFR; summarizes the stateof-the-art application of CT-FFR; and provides suggestions and recommendations for the application of CT-FFR with the aim of promoting the standardized application of CT-FFR in clinical practice.

show abstract

“…Tang et al [ 36 ] assessed the value of ML-FFRct in identifying hemodynamically in-stent restenosis using invasive FFR as reference in 33 patients who underwent stent implantations. Results showed that FFRct had a great correlation with invasive FFR (ICC = 0.84).…”

Section: Ai In Coronary Computed Tomography Angiographymentioning

confidence: 99%

Artificial Intelligence in Cardiovascular CT and MR Imaging

Lanzafame

Bucolo

Muscogiuri

et al. 2023

Life

View full text Add to dashboard Cite

The technological development of Artificial Intelligence (AI) has grown rapidly in recent years. The applications of AI to cardiovascular imaging are various and could improve the radiologists’ workflow, speeding up acquisition and post-processing time, increasing image quality and diagnostic accuracy. Several studies have already proved AI applications in Coronary Computed Tomography Angiography and Cardiac Magnetic Resonance, including automatic evaluation of calcium score, quantification of coronary stenosis and plaque analysis, or the automatic quantification of heart volumes and myocardial tissue characterization. The aim of this review is to summarize the latest advances in the field of AI applied to cardiovascular CT and MR imaging.

show abstract

Feasibility and prognostic role of machine learning-based FFRCT in patients with stent implantation

Cited by 17 publications

References 29 publications

The Predictive Value of the Perivascular Adipose Tissue CT Fat Attenuation Index for Coronary In-stent Restenosis

The Predictive Value of the Perivascular Adipose Tissue CT Fat Attenuation Index for Coronary In-stent Restenosis

Coronary Computed Tomography Angiography–derived Fractional Flow Reserve

Artificial Intelligence in Cardiovascular CT and MR Imaging

Contact Info

Product

Resources

About