Whole heart coronary magnetic resonance angiography for the detection of coronary artery stenosis and atherosclerotic coronary artery plaque in a patient with unstable angina

End-to-end deep learning nonrigid motion-corrected reconstruction for highly accelerated free-breathing coronary MRA

PURPOSE

To develop an end-to-end deep learning technique for nonrigid motion-corrected (MoCo) reconstruction of ninefold undersampled free-breathing whole-heart coronary MRA (CMRA).

METHODS

A novel deep learning framework was developed consisting of a diffeomorphic registration network and a motion-informed model-based deep learning (MoDL) reconstruction network. The registration network receives as input highly undersampled (~22×) respiratory-resolved images and outputs 3D nonrigid respiratory motion fields between the images. The motion-informed MoDL performs MoCo reconstruction from undersampled data using the predicted motion fields. The whole deep learning framework, termed as MoCo-MoDL, was trained end-to-end in a supervised manner for simultaneous 3D nonrigid motion estimation and MoCo reconstruction. MoCo-MoDL was compared with a state-of-the-art nonrigid MoCo CMRA reconstruction technique in 15 retrospectively undersampled datasets and 9 prospectively undersampled acquisitions.

RESULTS

The acquisition time for ninefold accelerated CMRA was ~2.5 min. The reconstruction time was ~22 s for the proposed MoCo-MoDL and ~35 min for the conventional approach. MoCo-MoDL achieved higher peak SNR (27.86 ± 3.00 vs. 26.71 ± 2.79; P < .05) and structural similarity (0.78 ± 0.06 vs. 0.75 ± 0.06; P < .05) than the conventional approach. Similar vessel length and visual image quality score were obtained with the 2 methods, whereas improved vessel sharpness was observed with MoCo-MoDL.

CONCLUSION

An end-to-end deep learning approach was introduced for simultaneous nonrigid motion estimation and MoCo reconstruction of highly undersampled free-breathing whole-heart CMRA. The rapid free-breathing CMRA acquisition together with the fast reconstruction of the proposed approach promises easy integration into clinical workflow.

Non-invasive assessment and clinical strategy of stable coronary artery disease by magnetic resonance imaging, multislice computed tomography and myocardial perfusion SPECT

Coronary multislice computed tomography (MSCT) angiography and magnetic resonance angiography (MRA) have emerged as new diagnostic techniques that allow direct visualization of the coronary artery. These new modalities have both advantages and disadvantages concerning radiation exposure, the use of contrast medium, ability of visualizing heavily calcified artery lumens, and spatial and temporal resolution. However, these modalities only provide anatomical information of the coronary artery. Functional assessment of the severity of coronary artery disease (CAD) is essential for the management of patients with known or suspected CAD in practical clinical settings. Myocardial perfusion single-photon emission computed tomography is thought to be the most suitable diagnostic procedure for the determination of therapeutic strategy when coronary MSCT and MRA show significant and also insignificant coronary artery lesions. (Circ J 2010; 74: 34 - 40).

Whole-heart coronary magnetic resonance angiography of double left anterior descending artery

Double left anterior descending artery arising from the left and right coronary arteries is an extremely rare congenital coronary anomaly. We describe, for the first time, three-dimensional, whole-heart coronary magnetic resonance angiographic findings of double left anterior descending artery.

Detection of non-ST-elevation myocardial infarction and unstable angina in the acute setting: meta-analysis of diagnostic performance of multi-detector computed tomographic angiography

Background

Multi-detector computed tomography angiography (MDCTA) has been increasingly used in the evaluation of the coronary arteries. The purpose of this study was to review the literature on the diagnostic performance of MDCTA in the acute setting, for the detection of non-ST-elevation myocardial infarction (NSTEMI) and unstable angina pectoris (UAP).

Methods

A Pubmed and manual search of the literature published between January 2000 and June 2007 was performed. Studies were included that compared MDCTA with clinical outcome and/or CA in patients with acute chest pain, presenting at the emergency department. More specifically, studies that only included patients with initially negative cardiac enzymes suspected of having NSTEMI or UAP were included. Summary estimates of diagnostic odds ratio (DOR), sensitivity and specificity, negative (NLR) and positive likelihood ratio (PLR) were calculated on a patient basis. Random-effects models and summary receiver operating curve (SROC) analysis were used to assess the diagnostic performance of MDCTA with 4 detectors or more. The proportion of non assessable scans (NAP) on MDCTA was also evaluated. In addition, the influence of study characteristics of each study on diagnostic performance and NAP was investigated with multivariable logistic regression.

Results

Nine studies totalling 566 patients, were included in the meta-analysis: one randomised trial and eight prospective cohort studies. Five studies on 64-detector MDCTA and 4 studies on MDCTA with less than 64 detectors were included (32 detectors n = 1, 16 detectors n = 2, 16 and 4 detectors n = 1). Pooled DOR was 131.81 (95%CI, 50.90–341.31). The pooled sensitivity and specificity were 0.95 (95%CI, 0.90–0.98) and 0.90 (95%CI, 0.87–0.93). The pooled NLR and PLR were 0.12 (95%CI, 0.06–0.21) and 8,60 (95%CI, 5.03–14,69).

The results of the logistic regressions showed that none of the investigated variables had influence on the diagnostic performance or NAP

Conclusion

MDCTA of the coronary arteries performs good to excellent in the diagnosis of coronary artery disease in the acute setting and it can be used for early exclusion of NSTEMI or UAP in patients in the emergency department.

Isolated Subvalvular Pulmonary Stenosis: Depiction at Whole Heart Magnetic Resonance Imaging

Isolated subvalvular pulmonary stenosis is a rare condition and its morphological evaluation is obscure. Whole heart magnetic resonance imaging (MRI) is a new, totally non-invasive technique which allows three-dimensional comprehension of the cardiac structure. We describe a patient with isolated subvalvular pulmonary stenosis, in whom whole heart MRI was useful to detect and evaluate the right ventricular outflow obstruction.