Detection, Grading and Classification of Coronary Stenoses in Computed Tomography Angiography

Kelm, B. Michael; Mittal, Susheel K.; Zheng, Yefeng; Tsymbal, Alexey; Bernhardt, Dominik; Vega-Higuera, Fernando; Zhou, S. Kevin; Meer, Peter; Comanicìu, Dorin

doi:10.1007/978-3-642-23626-6_4

Cited by 49 publications

(30 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dinesh et al 30 proposed a method that utilized manual centerlines and artery classification, and did not provide specific stenosis calculation and was evaluated with a small number of patients (eight patients). Recently, Kelm et al 32 and Goldenberg et al 33 also published automated detection of obstructive (≥50% stenosis) coronary artery lesions from CTA. A performance comparison between our proposed algorithm (both lesions with ≥50% stenosis and ≥25% stenosis) and these studies (lesions with ≥50% stenosis) is shown in Table 4.…”

Section: Discussionmentioning

confidence: 99%

“…[25][26][27][28] A few studies attempted automatic detection of coronary lesions. [29][30][31][32][33] Detection and quantification of coronary artery lesions are particularly challenging due to limited spatial resolution and coronary artery motion, relatively small plaque size, and complex and variable coronary artery anatomy. [29][30][31][32][33] Automated lesion detection requires accurate extraction of coronary artery centerlines and classification of normal and abnormal lumen cross-sections, quantification of luminal stenosis, and classification of lesions with different degree of stenosis.…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies by other investigators in coronary lesion detection [29][30][31][32][33] attempted to detect only obstructive lesions (with stenosis ≥50%). However, nonobstructive lesions (stenosis <50% have been shown to be a clinically significant predictor of future coronary events.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Structured learning algorithm for detection of nonobstructive and obstructive coronary plaque lesions from computed tomography angiography

et al. 2015

View full text Add to dashboard Cite

Abstract. Visual identification of coronary arterial lesion from three-dimensional coronary computed tomography angiography (CTA) remains challenging. We aimed to develop a robust automated algorithm for computer detection of coronary artery lesions by machine learning techniques. A structured learning technique is proposed to detect all coronary arterial lesions with stenosis ≥25%. Our algorithm consists of two stages: (1) two independent base decisions indicating the existence of lesions in each arterial segment and (b) the final decision made by combining the base decisions. One of the base decisions is the support vector machine (SVM) based learning algorithm, which divides each artery into small volume patches and integrates several quantitative geometric and shape features for arterial lesions in each small volume patch by SVM algorithm. The other base decision is the formula-based analytic method. The final decision in the first stage applies SVM-based decision fusion to combine the two base decisions in the second stage. The proposed algorithm was applied to 42 CTA patient datasets, acquired with dual-source CT, where 21 datasets had 45 lesions with stenosis ≥25%. Visual identification of lesions with stenosis ≥25% by three expert readers, using consensus reading, was considered as a reference standard. Our method performed with high sensitivity (93%), specificity (95%), and accuracy (94%), with receiver operator characteristic area under the curve of 0.94. The proposed algorithm shows promising results in the automated detection of obstructive and nonobstructive lesions from CTA.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Structured learning algorithm for detection of nonobstructive and obstructive coronary plaque lesions from computed tomography angiography

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Dey and others [5] also used intravascular ultrasound (IVUS) to verify their method. Kelm and others [6] introduced a stenosis detecting system focusing on coronary CTA, which employed a nonlinear regression method to estimate the vessel diameter of a 2D vessel cross section to obtain the stenosis point of the vessel. Xu and others [7] presented a method for detecting and quantifying coronary arterial stenosis in CTA using the Fuzzy Distance Transform (FDT) approach and developed a method to estimate the "expected diameter" along a given arterial branch using a coherence analysis.…”

Section: Introductionmentioning

confidence: 99%

Coronary Artery Stenosis Quantification for Computed Tomography Angiography Based on Modified Student'st-Mixture Model

Sun¹,

Yang²,

Hu³

et al. 2017

ETRI Journal

View full text Add to dashboard Cite

Coronary artery disease (CAD) is a major cause of death in the world. As a non-invasive imaging modality, computed tomography angiography (CTA) is now usually used in clinical practice for CAD diagnosis. Precise quantification of coronary stenosis is of great interest for diagnosis and treatment planning. In this paper, a novel cluster method based on a Modified Student's t-Mixture Model is applied to separate the region of vessel lumen from other tissues. Then, the area of the vessel lumen in each slice is computed and the estimated value of it is fitted with a curve. Finally, the location and the level of the most stenoses are captured by comparing the calculated and fitted areas of the vessel. The proposed method has been applied to 17 clinical CTA datasets and the results have been compared with reference standard degrees of stenosis defined by an expert. The results of the experiment indicate that the proposed method can accurately quantify the stenosis of the coronary artery in CTA.

show abstract

“…Even in cases of severe coronary calcification, sensitivity and specificity of CTA in comparison to invasive angiography for significant stenosis are high [1]. Furthermore, automatic systems have been developed that enable the detection and grading of coronary stenoses based on accurate lumen estimations [2]. Recent studies also show that the blood pressure analysis of coronary arteries is a better predictor for ischemia-causing lesions than anatomically visible lumen obstructions.…”

Section: Introductionmentioning

confidence: 99%

Improving accuracy in coronary lumen segmentation via explicit calcium exclusion, learning-based ray detection and surface optimization

et al. 2014

Self Cite

View full text Add to dashboard Cite

Invasive cardiac angiography (catheterization) is still the standard in clinical practice for diagnosing coronary artery disease (CAD) but it involves a high amount of risk and cost. New generations of CT scanners can acquire high-quality images of coronary arteries which allow for an accurate identification and delineation of stenoses. Recently, computational flow dynamics (CFD) simulation has been applied to coronary blood flow using geometric lumen models extracted from CT angiography (CTA). The computed pressure drop at stenoses proved to be indicative for ischemia-causing lesions, leading to non-invasive Fractional Flow Reserve derived from CTA (FFRCT). Since the diagnostic value of non-invasive procedures for diagnosing CAD relies on an accurate extraction of the lumen, a precise segmentation of the coronary arteries is crucial. As manual segmentation is tedious, time-consuming and subjective, automatic procedures are desirable. We present a novel fully-automatic method to accurately segment the lumen of coronary arteries in the presence of calcified and noncalcified plaque. Our segmentation framework is based on three main steps: boundary detection, calcium exclusion and surface optimization. A learning-based boundary detector enables a robust lumen contour detection via dense ray-casting. The exclusion of calcified plaque is assured through a novel calcium exclusion technique which allows us to accurately capture stenoses of diseased arteries. The boundary detection results are incorporated into a closed set formulation whose minimization yields an optimized lumen surface. On standardized tests with clinical data, a segmentation accuracy is achieved which is comparable to clinical experts and superior to current automatic methods.

show abstract

Detection, Grading and Classification of Coronary Stenoses in Computed Tomography Angiography

Cited by 49 publications

References 13 publications

Structured learning algorithm for detection of nonobstructive and obstructive coronary plaque lesions from computed tomography angiography

Structured learning algorithm for detection of nonobstructive and obstructive coronary plaque lesions from computed tomography angiography

Coronary Artery Stenosis Quantification for Computed Tomography Angiography Based on Modified Student'st-Mixture Model

Improving accuracy in coronary lumen segmentation via explicit calcium exclusion, learning-based ray detection and surface optimization

Contact Info

Product

Resources

About