Value of artificial intelligence-based pericoronary fat attenuation index combined with stenosis rate and plaque characteristics in predicting myocardial ischemia

Fang Hui; Yin Run; Jin Li; Fang Lei

doi:10.13406/j.cnki.cyxb.003927

您当前的位置：

首页 >

文章列表页 >

Value of artificial intelligence-based pericoronary fat attenuation index combined with stenosis rate and plaque characteristics in predicting myocardial ischemia

Clinical research | 更新时间：2026-05-13

- Value of artificial intelligence-based pericoronary fat attenuation index combined with stenosis rate and plaque characteristics in predicting myocardial ischemia
- Journal of Chongqing Medical University Vol. 51, Issue 5, Pages: 709-714(2026)
- 作者机构：
  
  复旦大学附属浦东医院放射科，上海 201399
- 作者简介：
- 基金信息：
- DOI：10.13406/j.cnki.cyxb.003927
  CLC： R445.3
- Received：09 March 2025，
  
  Revised：2025-04-21，
  
  Accepted：10 May 2025，
  
  Published：28 May 2026
- 稿件说明：
移动端阅览
方慧,殷润,金利等.基于人工智能的冠状动脉周围脂肪衰减指数联合狭窄率及斑块特征预测心肌缺血的价值[J].重庆医科大学学报,2026,51(05):709-714.

Fang Hui,Yin Run,Jin Li,et al.Value of artificial intelligence-based pericoronary fat attenuation index combined with stenosis rate and plaque characteristics in predicting myocardial ischemia[J].Journal of Chongqing Medical University,2026,51(05):709-714.
方慧,殷润,金利等.基于人工智能的冠状动脉周围脂肪衰减指数联合狭窄率及斑块特征预测心肌缺血的价值[J].重庆医科大学学报,2026,51(05):709-714. DOI： 10.13406/j.cnki.cyxb.003927.

Fang Hui,Yin Run,Jin Li,et al.Value of artificial intelligence-based pericoronary fat attenuation index combined with stenosis rate and plaque characteristics in predicting myocardial ischemia[J].Journal of Chongqing Medical University,2026,51(05):709-714. DOI： 10.13406/j.cnki.cyxb.003927.

摘要

目的

探讨基于人工智能的冠状动脉周围脂肪衰减指数（fat attenuation index，FAI）联合冠状动脉CT血管成像（coronary CT angiography，CCTA）诊断的狭窄率与斑块特征预测心肌缺血的价值。

方法

回顾性分析2024年5月至2024年12月在复旦大学附属浦东医院行CCTA检查的资料，共纳入231例患者及其310个斑块。基于斑块分析CT血流储备分数（CT derived fractional flow reserve，CT-FFR）、FAI、狭窄率及斑块特征，根据CT-FFR≤0.80和CT-FFR>0.80，分为心肌缺血组和非心肌缺血组。比较FAI、狭窄率及斑块特征在2组间的差异；使用logistic回归分析筛选出心肌缺血的独立危险因素，构建并比较不同模型对心肌缺血的预测价值。

结果

FAI、狭窄率、斑块总体积、斑块长度、脂质斑块体积、纤维斑块体积、钙化斑块占比在2组间差异有统计学意义（

0.05）；脂质斑块占比、纤维斑块占比、钙化斑块体积、高危斑块占比在2组间差异无统计学意义（

0.05）。与单一预测模型相比，FAI、狭窄率、斑块长度＋脂质斑块体积的联合模型具有最高的预测效能（AUC=0.843，

0.05）。

结论

FAI、狭窄率、斑块长度、脂质斑块体积是心肌缺血的独立危险因素；FAI、狭窄率、斑块长度＋脂质斑块体积的预测模型均对心肌缺血有较好的预测价值；联合应用可提高对心肌缺血的预测效能。

Abstract

Objective

To investigate the value of artificial intelligence-based pericoronary fat attenuation index（FAI） combined with stenosis rate and plaque characteristics diagnosed by coronary CT angiography（CCTA） in predicting myocardial ischemia.

Methods

A retrospective analysis was performed for the data of 231 patients（310 plaques） who underwent CCTA in Pudong Hospital Affiliated to Fudan University from May to December 2024. CT-derived fractional flow reserve（CT-FFR），FAI，stenosis rate，and plaque characteristics were analyzed，and according to CT-FFR≤0.80 and CT-FFR>0.80，the patients were divided into myocardial ischemia group and non-myocardial ischemia group. FAI，stenosis rate，and plaque characteristics were compared between the two groups，and a logistic regression analysis was used to identify independent risk factors for myocardial ischemia，construct different models，and compare the value of these models in predicting myocardial ischemia.

Results

There were significant differences between the two groups in FAI，stenosis rate，total plaque volume，plaque length，lipid plaque volume，fibrous plaque volume，and the proportion of calcified plaques（

0.05），while there were no significant differences between the two groups in the proportions of lipid plaque and fibrous plaques，calcified plaque volume，and the proportion of high-risk plaques （

0.05）. Compared with the predictive model based on a single factor，the model based on the combination of FAI，stenosis rate，plaque length，and lipid plaque volume had the highest predictive efficacy （AUC=0.843，

0.05）.

Conclusion

FAI，stenosis rate，plaque length，and lipid plaque volume are independent risk factors for myocardial ischemia. The predictive models based on FAI，stenosis rate，plaque length，and lipid plaque volume have a good predictive value for myocardial ischemia，and the model based on the combination of these four factors can enhance the predictive efficacy for myocardial ischemia.

关键词

Keywords

references

李俊清，刘丽君，鲍海龙，等 . 颈动脉粥样硬化与冠心病关系的研究进展 [J ] . 中国医药， 2022 ， 17 （ 9 ）： 1418 - 1422 .

Li JQ ， Liu LJ ， Bao HL ， et al . Research progress on the relationship between carotid atherosclerosis and coronary atherosclerotic heart disease [J ] . Chinese Medicine ， 2022 ， 17 （ 9 ）， 1418 - 1422 .

刘明波，何新叶，杨晓红，等 . 《中国心血管健康与疾病报告2023》要点解读 [J ] . 中国全科医学， 2025 ， 28 （ 1 ）： 20 - 38 .

Liu MB ， He XY ， Yang XH ， et al . Interpretation of Report on Cardiovascular Health and Diseases in China 2023 [J ] . Chinese General Practice ， 2025 ， 28 （ 1 ）： 20 - 38 .

Guo B ， Xing W ， Hu C ， et al . Clinical effectiveness of automated coronary CT-derived fractional flow reserve：a Chinese randomized controlled trial [J ] . Radiology ， 2024 ， 313 （ 1 ）： e233354 ．

Simantiris S ， Pappa A ， Papastamos C ， et al . Perivascular fat：a novel risk factor for coronary artery disease [J ] . Diagnostics（Basel）， 2024 ， 14 （ 16 ）： 1830 ．

Antonopoulos AS ， Sanna F ， et al . Detecting human coronary inflammation by imaging perivascular fat [J ] . Sci Transl Med ， 2017 ， 9 （ 398 ）： eaal2658 ．

赵娜，高扬，徐波，等 . 基于冠状动脉CT血管成像的狭窄率与斑块特征联合分析对提高CT诊断心肌缺血效能的价值 [J ] . 中华放射学杂志， 2021 ， 55 （ 1 ）： 40 - 47 .

Zhao N ， Gao Y ， Xu B ， et al . The value of combined analysis of plaque characteristics and stenosis based on coronary CT angiography in improving CT diagnostic performance for lesion-specific myocardial ischemia [J ] . Chin J Radiol ， 2021 , 55 （ 1 ）： 40 - 47 .

谢圆圆，李冬梅，毛鑫乐，等 . 人工智能在超声诊断冠心病中的应用现状 [J/OL ] . 中华医学超声杂志（电子版）， 2024 ， 21 （ 2 ）： 170 - 174 ．

Xie YY ， Li DM ， Mao XL ， et al . Application of artificial intelligence in ultrasonic diagnosis of coronary heart disease [J/OL ] . Chin J Med Ultrasound Electron Ed ， 2024 ， 21 （ 2 ）： 170 - 174 ．

王钰璇，任超，孙宵宇，等 . 冠状动脉周围脂肪衰减指数、冠状动脉狭窄程度及肝脏脂肪含量与心肌缺血的关系研究 [J ] . 中国医学计算机成像杂志， 2024 ， 30 （ 4 ）： 421 - 426 .

Wang YX ， Ren C ， Sun XY ， et al . Study on the Relationship of Myocardial Ischemia with Pericoronary Fat Attenuation Index，Degree of Coronary Artery Stenosis and Liver Fat Content [J ] . Chin Comput Med Imag ， 2024 ， 30 （ 4 ）： 421 - 426 .

陆意歌，何　玮，林泓言，等 . CT冠状动脉周围脂肪衰减结合机器学习算法诊断冠心病心肌缺血 [J ] . 中国动脉硬化杂志， 2024 ， 32 （ 6 ）： 514 - 520 ．

Lu YG ， He W ， Lin HY ， et al . CT coronary perivascular fat attenuation combined with machine learning algorithms for diagnosis of myocardial ischemia in coronary heart disease [J ] . Chin J Arterioscler ， 2024 ， 32 （ 6 ）： 514 - 520 ．

Long YF ， Guo R ， Jin KY ， et al . Analysis of the perivascular fat attenuation index and quantitative plaque parameters in relation to haemodynamically impaired myocardial ischaemia [J ] . Int J Cardiovasc Imag ， 2024 ， 40 （ 7 ）： 1455 - 1463 ．

Klüner LV ， Oikonomou EK ， Antoniades C . Assessing cardiovascular risk by using the fat attenuation index in coronary CT angiography [J ] . Radiol Cardiothorac Imaging ， 2021 ， 3 （ 1 ）： e200563 ．

Lu ZF ， Yin WH ， Schoepf UJ ， et al . Prediction value of pericoronary fat attenuation index for coronary in-stent restenosis [J ] . Eur Radiol ， 2024 ， 34 （ 8 ）： 4950 - 4959 ．

Yu MM ， Dai X ， Deng JH ， et al . Diagnostic performance of perivascular fat attenuation index to predict hemodynamic significance of coronary stenosis：a preliminary coronary computed tomography angiography study [J ] . Eur Radiol ， 2020 ， 30 （ 2 ）： 673 - 681 ．

Wang J ， Wu QX ， Zeng SY ， et al . Nomogram for evaluating coronary revascularisation necessity based on multi-parameter coronary CT angiography [J ] . Clin Radiol ， 2023 ， 78 （ 7 ）： e526 - e534 ．

陈柳丹，涂圣贤，李泽杭，等 . 斑块对基于CTA虚拟计算冠状动脉血流储备分数的影响 [J ] . 中山大学学报（医学科学版）， 2023 ， 44 （ 5 ）： 823 - 829 ．

Chen LD ， Tu SX ， Li ZH ， et al . Impact of coronary plaque on the precision of computational fractional flow reserve derived from CTA [J ] . J Sun Yat Sen Univ Med Sci ， 2023 ， 44 （ 5 ）： 823 - 829 ．

Iguchi T ， Hasegawa T ， Nishimura S ， et al . Impact of lesion length on functional significance in intermediate coronary lesions [J ] . Clin Cardiol ， 2013 ， 36 （ 3 ）： 172 - 177 ．

Shibutani H ， Fujii K ， Matsumura K ， et al . Differential influence of lesion length on fractional flow reserve in intermediate coronary lesions between each coronary artery [J ] . Catheter Cardiovasc Interv ， 2020 ， 95 （ 6 ）： e168 - e174 ．

Ahmadi N ， Ruiz-Garcia J ， Hajsadeghi F ， et al . Impaired coronary artery distensibility is an endothelium-dependent process and is associated with vulnerable plaque composition [J ] . Clin Physiol Funct Imaging ， 2016 ， 36 （ 4 ）： 261 - 268 ．

Yu MM ， Lu ZG ， Shen CX ， et al . The best predictor of ischemic coronary stenosis：subtended myocardial volume，machine learning-based FFRCT，or high-risk plaque features [J ] . Eur Radiol ， 2019 ， 29 （ 7 ）： 3647 - 3657 ．

Waksman R ， Legutko J ， Singh J ， et al . FIRST：fractional flow reserve and intravascular ultrasound relationship study [J ] . J Am Coll Cardiol ， 2013 ， 61 （ 9 ）： 917 - 923 ．

高艳，顾慧，杨世锋，等 . 基于冠状动脉CT血管成像的斑块定量分析及其与心肌缺血损伤的相关性研究 [J ] . 中华放射学杂志， 2020 ， 54 （ 2 ）： 129 - 135 .

Gao Y ， Gu H ， Yang SF ， et al . Correlation study of coronary plaque quantitative analysis and myocardial ischemic injury based on coronary CT angiography [J ] . Chin J Radiol ， 2020 ， 54 （ 2 ）： 129 - 135 .

Ma S ， Chen X ， Ma Y ， et al . Lesion-specific peri-coronary fat attenuation index is associated with functional myocardial ischemia defined by abnormal fractional flow reserve [J ] . Front Cardiovasc Med ， 2021 ， 8 ： 755295 ．

Yan HK ， Zhao N ， Geng WL ， et al . Pericoronary fat attenuation index and coronary plaque quantified from coronary computed tomography angiography identify ischemia-causing lesions [J ] . Int J Cardiol ， 2022 ， 357 ： 8 - 13 ．

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of artificial intelligence in the diagnosis and treatment of sepsis: innovations，challenges，and clinical practice

Research advances in artificial intelligence for difficult airway prediction

Advances in the application of ultrasound combined with radiomics and artificial intelligence in the diagnosis and prognostic evaluation of gastrointestinal stromal tumors

Optimization strategy and practice analysis of airway management based on artificial intelligence

Jianpi Rougan decoction alleviates carbon tetrachloride-induced liver fibrosis in rats by regulating ferroptosis mediated by the Nrf2/HMOX1 signaling pathway

Related Author

Fang Hui

Fang Lei

Peng Jiachen

Xu Fang

Zhou Guilin

Shao Jianlin

Liu Yang

He Xuemei

Related Institution

Department of Critical Care Medicine，The First Affiliated Hospital of Chongqing Medical University

Department of Anesthesiology，The First Affiliated Hospital of Kunming Medical University

Department of Ultrasound，The First Affiliated Hospital of Chongqing Medical University

China Academy of Information and Communications Technology

Department of Anesthesiology，Peking University Third Hospital

⁰