scholarly journals Evaluation of Late Gadolinium Enhancement and Cardiac Cine-MRI Based on Artificial Intelligence in a Patient with Selenium Deficiency Cardiomyopathy (Keshan Disease): A Case Report

2020 ◽  
Vol 17 (2) ◽  
Author(s):  
Wei-Feng Yuan ◽  
Xin-Xiang Zhao
Keyword(s):  
Artificial Intelligence ◽  
Case Report ◽  
Late Gadolinium Enhancement ◽  
Selenium Deficiency ◽  
Keshan Disease ◽  
Cine Mri ◽  
Gadolinium Enhancement ◽  
Cardiac Cine

scholarly journals Towards Replacing Late Gadolinium Enhancement with Artificial Intelligence Virtual Native Enhancement for Gadolinium-Free Cardiovascular Magnetic Resonance Tissue Characterization in Hypertrophic Cardiomyopathy

Circulation ◽  
2021 ◽  
Author(s):  
Qiang Zhang ◽  
Matthew K. Burrage ◽  
Elena Lukaschuk ◽  
Mayooran Shanmuganathan ◽  
Iulia A. Popescu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cardiovascular Magnetic Resonance ◽  
Deep Learning ◽  
Late Gadolinium Enhancement ◽  
Hypertrophic Cardiomyopathy ◽  
Magnetic Resonance ◽  
Image Quality ◽  
Tissue Characterization ◽  
Wilcoxon Test ◽  
Gadolinium Enhancement

Background: Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterization, but requires intravenous contrast agent administration. It is highly desired to develop a contrast-agent-free technology to replace LGE for faster and cheaper CMR scans. Methods: A CMR Virtual Native Enhancement (VNE) imaging technology was developed using artificial intelligence. The deep learning model for generating VNE uses multiple streams of convolutional neural networks to exploit and enhance the existing signals in native T1-maps (pixel-wise maps of tissue T1 relaxation times) and cine imaging of cardiac structure and function, presenting them as LGE-equivalent images. The VNE generator was trained using generative adversarial networks. This technology was first developed on CMR datasets from the multi-center Hypertrophic Cardiomyopathy Registry (HCMR), using HCM as an exemplar. The datasets were randomized into two independent groups for deep learning training and testing. The test data of VNE and LGE were scored and contoured by experienced human operators to assess image quality, visuospatial agreement and myocardial lesion burden quantification. Image quality was compared using nonparametric Wilcoxon test. Intra- and inter-observer agreement was analyzed using intraclass correlation coefficients (ICC). Lesion quantification by VNE and LGE were compared using linear regression and ICC. Results: 1348 HCM patients provided 4093 triplets of matched T1-maps, cines, and LGE datasets. After randomization and data quality control, 2695 datasets were used for VNE method development, and 345 for independent testing. VNE had significantly better image quality than LGE, as assessed by 4 operators (n=345 datasets, p<0.001, Wilcoxon test). VNE revealed characteristic HCM lesions in high visuospatial agreement with LGE. In 121 patients (n=326 datasets), VNE correlated with LGE in detecting and quantifying both hyper-intensity myocardial lesions (r=0.77-0.79, ICC=0.77-0.87; p<0.001) and intermediate-intensity lesions (r=0.70-0.76, ICC=0.82-0.85; p<0.001). The native CMR images (cine plus T1-map) required for VNE can be acquired within 15 minutes. Producing a VNE image takes less than one second. Conclusions: VNE is a new CMR technology that resembles conventional LGE, without the need for contrast administration. VNE achieved high agreement with LGE in the distribution and quantification of lesions, with significantly better image quality.

scholarly journals Cytarabine-induced pericarditis confirmed using cardiac MRI after inconclusive echocardiography: A case report

2021 ◽  
Author(s):  
Tony Dong ◽  
Tarek Chami ◽  
Besher Chami ◽  
Sadeer Al-Kindi ◽  
Brian Hoit
Keyword(s):  
Acute Myeloid Leukemia ◽  
Case Report ◽  
Late Gadolinium Enhancement ◽  
Induction Chemotherapy ◽  
Cardiac Mri ◽  
Myeloid Leukemia ◽  
Gadolinium Enhancement ◽  
Acute Pericarditis ◽  
Pericardial Edema ◽  
Acute Myeloid

Pericarditis is a rare but debilitating complication of cytarabine therapy. While echocardiography can aid with the diagnosis, cardiac MRI has superior accuracy in establishing the diagnosis. In this case, we describe a 65-year-old patient receiving cytarabine as part of induction chemotherapy for acute myeloid leukemia who developed acute pericarditis. Her cardiac MRI revealed pericardial edema on T2-weighted STIR imaging and pericardial late gadolinium enhancement which confirmed the diagnosis.

Abstract 5931: The Presence and Pattern of Late Gadolinium Enhancement on cardiac MRI in Amyloidosis is Associated with Other Markers of Prognosis

Circulation ◽  
2008 ◽  
Vol 118 (suppl_18) ◽  
Author(s):  
Imran Syed ◽  
James Glockner ◽  
Philip A Araoz ◽  
DaLi Feng ◽  
Matthew Martinez ◽  
...  
Keyword(s):  
Late Gadolinium Enhancement ◽  
Cardiac Mri ◽  
Biochemical Parameters ◽  
Nyha Class ◽  
Cardiac Biomarkers ◽  
Cine Mri ◽  
List Type ◽  
Gadolinium Enhancement ◽  
Cardiac Biomarker ◽  
Prognostic Implications

Objective: Recent MRI studies have demonstrated the common occurrence of late gadolinium enhancement (LGE) in cardiac amyloidosis (CA). However, the association of LGE presence and pattern with other clinical, morphological, functional, and biochemical parameters has not yet been demonstrated. It is important to define this association, since many of these parameters (NYHA class, ventricular thickness, cardiac biomarkers) have prognostic implications. Methods: Of 151 patients with confirmed systemic amyloidosis who underwent LGE cardiac MRI between January 2006 and December 2007 to evaluate for possible CA, 120 (AL 100, senile 9, and familial 11) were included after meeting of inclusion and exclusion criteria. Cine MRI images were analyzed for morphologic and functional data. LGE images were analyzed for presence and pattern of LGE. Clinical data including ECG’s and cardiac biomarkers was obtained. Results: LGE evidence of CA was present in 95 patients and absent in 25 patients. Three main patterns of LGE were observed. These were global diffuse transmural (homogenous or heterogenous) or subendocardial, suboptimally nulled myocardium without clear hyperenhancement, and focal patchy LGE. Symptoms, morphologic/functional variables, ECG voltages, and cardiac biomarker levels were worst in patients with global diffuse LGE, followed by suboptimally nulled myocardium, focal patchy LGE, and absent LGE groups (Table 1 ). Conclusions: The presence of LGE in amyloidosis patients is associated with worse clinical, morphologic, functional, and biochemical parameters. Amongst patients with abnormal LGE, global diffuse (transmural or subendocardial) LGE is associated with the worst profile. This provides initial evidence that the presence and pattern of LGE in CA is associated with other markers of prognosis.

Tissue tracking MR to evaluate left ventricular global myocardial deformation in patients with cardiac amyloidosis of transmural late gadolinium enhancement

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
Z Li ◽  
H Jin ◽  
H Yun ◽  
Z Wei ◽  
M.S Zeng
Keyword(s):  
Late Gadolinium Enhancement ◽  
Cardiac Amyloidosis ◽  
Contractile Function ◽  
Global Longitudinal Strain ◽  
Left Ventricular ◽  
Myocardial Deformation ◽  
Cine Mri ◽  
Gadolinium Enhancement ◽  
Deformation Parameters ◽  
Tissue Tracking

Abstract Purpose Cardiac amyloidosis (CA) is a major cause of mortality in patients with amyloidosis because it leads to heart failure and lethal arrhythmia. The present study was aimed to evaluate left ventricular (LV) global myocardial deformation in patients with CA of transmural late gadolinium enhancement (LGE) using tissue tracking MRI. Materials and methods Thirty-nine patients with CA, confirmed by cardiac MRI, and a biopsy of at least one involved organ were enrolled. According to LV ejection fraction (LVEF), they were divided into reduced LVEF (CArEF) and preserved EF (CApEF) groups. Thirty-nine normal controls were recruited (NC). Tissue tracking analysis was done based on cine MRI sequences. LV global longitudinal strain (GLS), global circumferential strain (GCS), and global radial strain (GRS) were computed. Results GLS [CArEF vs. CApEF vs. NC: (−5.82±2.42) % vs. (−8.44±4.15) % vs. (−14.74±2.93)%], GCS [CArEF vs. CApEF vs. NC: (−9.47±2.96) % vs. (−15.01±1.81) % vs. (−19.86±2.30) %], and GRS [CArEF vs. CApEF vs. NC: (11.37±4.68) % vs. (20.61±6.27) % vs. (39.02±8.98) %] were all reduced in the CArEF and CApEF groups compared with healthy control subjects (all P&lt;0.01). GCS and GRS in the CArEF group were reduced compared with the CApEF group (P&lt;0.01). GLS, GCS, and GRS were also strongly correlated with LVEF (r=−0.77, −0.88, and 0.83, respectively; P&lt;0.01). Furthermore, the optimal cutoff values to predict LVEF reduction were −9.31% (sensitivity 88%, specificity 97%) for GLS, −14.13% (sensitivity 96%, specificity 97%) for GCS, and 20.11% (sensitivity 90%, specificity 97%) for GRS. Conclusion MRI-based LV global deformation parameters could be a useful method to assess LV myocardial systolic function and predict LVEF reduction in patients with CA of transmural enhancement on LGE. The differences of GCS and GRS between the CArEF and CApEF groups may also reflect preserved contractile function of the mid- or/and subepicardial myocardium. Figure 1. LV deformation parameters Funding Acknowledgement Type of funding source: None

Sign in / Sign up

Export Citation Format

Share Document