Mathematically Derived Criteria for Detecting Functionally Significant Stenoses Using Coronary Computed Tomographic Angiography–Based Myocardial Segmentation and Intravascular Ultrasound–Measured Minimal Lumen Area

Kang, Soo–Jin; Kweon, Jihoon; Yang, Dong Hyun; Lee, June-Goo; Jung, Joonho; Kim, Namkug; Mintz, Gary S.; Kang, Joon‐Won; Lim, Tae‐Hwan; Park, Seong-Wook; Kim, Young‐Hak

doi:10.1016/j.amjcard.2016.04.049

Cited by 16 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous study, the use of CAMS- V sub improved the diagnostic performance of angiographic MLD and/or IVUS-MLA for the prediction of FFR < 0.80 [ 12 , 13 ]. Although a mathematical model using V sub /MLD 4 > 6.26 increased the accuracy to 82%, it could be applied only when the patient underwent noninvasive CCTA prior to catheterization.…”

Section: Discussionmentioning

confidence: 99%

“…One of the reasons for the visual–functional mismatch is that myocardial ischemia is primarily determined by the variable size of the supplied myocardium at risk, as well as by the degree of stenosis [ 11 ]. Our previous data suggested that the application of coronary computed tomography angiography (CCTA)-based myocardial segmentation (CAMS)-derived percent myocardial volume subtended to a stenotic segment (CAMS-% V sub ) improves the diagnostic accuracy of angiographic indices used to identify ischemia-producing lesions [ 12 , 13 ]. Nonetheless, the necessity of concurrently performing noninvasive CCTA and invasive angiography limited the clinical utility of the mathematical model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation

et al. 2018

Self Cite

View full text Add to dashboard Cite

BackgroundInvasive fractional flow reserve (FFR) is a standard tool for identifying ischemia-producing coronary stenosis. However, in clinical practice, over 70% of treatment decisions still rely on visual estimation of angiographic stenosis, which has limited accuracy (about 60%–65%) for the prediction of FFR < 0.80. One of the reasons for the visual–functional mismatch is that myocardial ischemia can be affected by the supplied myocardial size, which is not always evident by coronary angiography. The aims of this study were to develop an angiography-based machine learning (ML) algorithm for predicting the supplied myocardial volume for a stenosis, as measured using coronary computed tomography angiography (CCTA), and then to build an angiography-based classifier for the lesions with an FFR < 0.80 versus ≥ 0.80.Methods and findingsA retrospective study was conducted using data from 1,132 stable and unstable angina patients with 1,132 intermediate lesions who underwent invasive coronary angiography, FFR, and CCTA at the Asan Medical Center, Seoul, Korea, between 1 May 2012 and 30 November 2015. The mean age was 63 ± 10 years, 76% were men, and 72% of the patients presented with stable angina. Of these, 932 patients (assessed before 31 January 2015) constituted the training set for the algorithm, and 200 patients (assessed after 1 February 2015) served as a test cohort to validate its diagnostic performance. Additionally, external validation with 79 patients from two centers (CHA University, Seongnam, Korea, and Ajou University, Suwon, Korea) was conducted. After automatic contour calibration using the caliber of guiding catheter, quantitative coronary angiography was performed using the edge-detection algorithms (CAAS-5, Pie-Medical). Clinical information was provided by the Asan BiomedicaL Research Environment (ABLE) system. The CCTA-based myocardial segmentation (CAMS)-derived myocardial volume supplied by each vessel (right coronary artery [RCA], left anterior descending [LAD], left circumflex [LCX]) and the myocardial volume subtended to a stenotic segment (CAMS-%Vsub) were measured for labeling. The ML for (1) predicting vessel territories (CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA) and CAMS-%Vsub and (2) identifying the lesions with an FFR < 0.80 was constructed. Angiography-based ML, employing a light gradient boosting machine (GBM), showed mean absolute errors (MAEs) of 5.42%, 8.57%, and 4.54% for predicting CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA, respectively. The percent myocardial volumes predicted by ML were used to predict the CAMS-%Vsub. With 5-fold cross validation, the MAEs between ML-predicted percent myocardial volume subtended to a stenotic segment (ML-%Vsub) and CAMS-%Vsub were minimized by the elastic net (6.26% ± 0.55% for LAD, 5.79% ± 0.68% for LCX, and 2.95% ± 0.14% for RCA lesions). Using all attributes (age, sex, involved vessel segment, and angiographic features affecting the myocardial territory and stenosis degree), the ML classifiers (L2 penalized logistic regression, support vector machine, ...

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…A potential reason for this fining may by the difference in subtended myocardial mass between the LAD and non‐LAD. In the previous studies using cardiac computed tomography, the LAD had a greater supplied myocardial mass than the non‐LAD, and the amount of subtended myocardial mass was an important factor to predict FFR ≤0.80 . In the territory of the LAD, the degree of vascular resistance decrease might be greater than the increase in the blood flow volume, owing to the smaller diameter of the artery.…”

Section: Discussionmentioning

confidence: 94%

Differential influence of lesion length on fractional flow reserve in intermediate coronary lesions between each coronary artery

Shibutani

Fujii

Matsumura

et al. 2019

Cathet Cardio Intervent

View full text Add to dashboard Cite

Objectives: This study evaluated whether the influence of lesion length on functional significance is similar between each target artery.Background: In the presence of a similar moderate degree of stenosis, the fractional flow reserve (FFR) in the left anterior descending coronary artery (LAD) is more often <0.80 than in the other arteries. Methods: A total of 221 lesions with intermediate stenosis on coronary angiography that underwent FFR measurement for the evaluation of myocardial ischemia were enrolled. Quantitative coronary angiographic analysis including percent diameter stenosis and lesion length was performed. The area under the receiver operating characteristics (ROC) curve was estimated for the best cutoff value as a predictor of FFR value of ≤0.80 for each coronary artery.Results: Although lesion length was similar among the lesions with an FFR >0.80 at different locations, the mean lesion length was significantly longer for lesions in the right coronary artery (RCA) with an FFR ≤0.80 than for those in the LAD and left circumflex artery (13.4 ± 3.4 vs. 8.6 ± 3.1 vs. 12.0 ± 3.7 mm, p < .001). ROC analysis demonstrated that the optimal cutoff value of lesion length for predicting an FFR ≤0.80 was 10.0 mm in the LAD (0.56 area under the curve [AUC], 48% sensitivity, and 76% specificity), whereas 13.1 mm in the RCA (0.84 AUC, 67% sensitivity, and 93% specificity). Conclusions:The impact of lesion length on myocardial ischemia is different for each coronary artery. A longer lesion length is required in the RCA than in the LAD to achieve an FFR ≤0.80. K E Y W O R D S catheterization, coronary angiography, fractional flow reserve

show abstract

“…Kang et al evaluated the myocardial volume subtended by a stenotic coronary segment (which we refer to as MMAR), with the Voronoi algorithm and quantitative intravascular ultrasound data to assess functional coronary stenosis. e ratio of MMAR to minimal lumen area 2 >4.04 predicted an FFR < 0.80 with sensitivity, specificity, positive predictive value, negative predictive value, and AUC of 88%, 90%, 86%, 92%, and 0.944, respectively [10]. In their subsequent study, they investigated MMAR and QCA, as in our study, and a ratio of MMAR to MLD 4 >6.3 predicted an FFR < 0.80 with a sensitivity, specificity, and AUC of 73%, 72%, and 0.78, respectively [23].…”

Section: Discussionmentioning

confidence: 99%

“…us, the myocardial mass at risk (MMAR), representing the volume of myocardium distal to the culprit lesion, might be an important factor in determining the functional severity of a culprit lesion and for explaining this discordance. Actually, several reports have demonstrated a correlation between the myocardial supply area distal to the site of stenosis and the FFR [6][7][8], and a few recent studies have shown that the MMAR improved the accuracy of using anatomical information to predict functional stenosis with a novel system based on the Voronoi tessellation or allometric scaling law [9,10]. We have been able to measure the MMAR easily with only a few clicks using commercially available software programs.…”

Section: Introductionmentioning

confidence: 99%

The Functional Severity Assessment of Coronary Stenosis Using Coronary Computed Tomography Angiography-Based Myocardial Mass at Risk and Minimal Lumen Diameter

Sadamatsu

Nagaoka

Koga

et al. 2020

Cardiovascular Therapeutics

View full text Add to dashboard Cite

Background. We investigated whether or not the addition of myocardial mass at risk (MMAR) to quantitative coronary angiography was useful for diagnosing functionally significant coronary stenosis in the daily practice. Methods. We retrospectively enrolled 111 consecutive patients with 149 lesions who underwent clinically indicated coronary computed tomography angiography and subsequent elective coronary angiography with fractional flow reserve (FFR) measurement. MMAR was calculated using a workstation-based software program with ordinary thin slice images acquired for the computed tomography, and the minimal lumen diameter (MLD) and the diameter stenosis were measured with quantitative coronary angiography. Results. The MLD and MMAR were significantly correlated with the FFR, and the MMAR-to-MLD ratio (MMAR/MLD) showed a good correlation. The area under the receiver operating characteristic curve (AUC) of MMAR/MLD for FFR ≤ 0.8 was 0.746, and the sensitivity, specificity, positive predictive value, and negative predictive value were 60%, 83%, 68%, and 77%, respectively, at a cut-off value of 29.5 ml/mm. The addition of MMAR/MLD to diameter stenosis thus made it possible to further discriminate lesions with FFR ≤ 0.8 (AUC = 0.750). For the proximal left coronary artery lesions, in particular, MMAR/MLD showed a better correlation with the FFR, and the AUC of MMAR/MLD for FFR ≤ 0.8 was 0.919 at a cut-off value of 31.7 ml/mm. Conclusions. The index of MMAR/MLD correlated well with the physiological severity of coronary stenosis and showed good accuracy for detecting functional significance. The MMAR/MLD might be a useful parameter to consider when deciding the indication for revascularization.

show abstract

Mathematically Derived Criteria for Detecting Functionally Significant Stenoses Using Coronary Computed Tomographic Angiography–Based Myocardial Segmentation and Intravascular Ultrasound–Measured Minimal Lumen Area

Cited by 16 publications

References 22 publications

Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation

Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation

Differential influence of lesion length on fractional flow reserve in intermediate coronary lesions between each coronary artery

The Functional Severity Assessment of Coronary Stenosis Using Coronary Computed Tomography Angiography-Based Myocardial Mass at Risk and Minimal Lumen Diameter

Contact Info

Product

Resources

About