Feasibility of late gadolinium enhancement (LGE) in ischemic cardiomyopathy using 2D-multisegment LGE combined with artificial intelligence reconstruction deep learning noise reduction algorithm

2021 ◽  
Vol 343 ◽  
pp. 164-170
Author(s):  
Giuseppe Muscogiuri ◽  
Chiara Martini ◽  
Marco Gatti ◽  
Serena Dell'Aversana ◽  
Francesca Ricci ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Late Gadolinium Enhancement ◽  
Noise Reduction ◽  
Ischemic Cardiomyopathy ◽  
Reduction Algorithm ◽  
Gadolinium Enhancement ◽  
Noise Reduction Algorithm

scholarly journals Improvement of late gadolinium enhancement image quality using a deep learning–based reconstruction algorithm and its influence on myocardial scar quantification

2020 ◽  
Author(s):  
Nikki van der Velde ◽  
H. Carlijne Hassing ◽  
Brendan J. Bakker ◽  
Piotr A. Wielopolski ◽  
R. Marc Lebel ◽  
...  
Keyword(s):  
Deep Learning ◽  
Late Gadolinium Enhancement ◽  
Image Quality ◽  
Noise Reduction ◽  
Reconstruction Algorithm ◽  
Remote Myocardium ◽  
Full Width ◽  
Half Maximum ◽  
Gadolinium Enhancement ◽  
Scar Size

Abstract Objectives The aim of this study was to assess the effect of a deep learning (DL)–based reconstruction algorithm on late gadolinium enhancement (LGE) image quality and to evaluate its influence on scar quantification. Methods Sixty patients (46 ± 17 years, 50% male) with suspected or known cardiomyopathy underwent CMR. Short-axis LGE images were reconstructed using the conventional reconstruction and a DL network (DLRecon) with tunable noise reduction (NR) levels from 0 to 100%. Image quality of standard LGE images and DLRecon images with 75% NR was scored using a 5-point scale (poor to excellent). In 30 patients with LGE, scar size was quantified using thresholding techniques with different standard deviations (SD) above remote myocardium, and using full width at half maximum (FWHM) technique in images with varying NR levels. Results DLRecon images were of higher quality than standard LGE images (subjective quality score 3.3 ± 0.5 vs. 3.6 ± 0.7, p < 0.001). Scar size increased with increasing NR levels using the SD methods. With 100% NR level, scar size increased 36%, 87%, and 138% using 2SD, 4SD, and 6SD quantification method, respectively, compared to standard LGE images (all p values < 0.001). However, with the FWHM method, no differences in scar size were found (p = 0.06). Conclusions LGE image quality improved significantly using a DL-based reconstruction algorithm. However, this algorithm has an important impact on scar quantification depending on which quantification technique is used. The FWHM method is preferred because of its independency of NR. Clinicians should be aware of this impact on scar quantification, as DL-based reconstruction algorithms are being used. Key Points • The image quality based on (subjective) visual assessment and image sharpness of late gadolinium enhancement images improved significantly using a deep learning–based reconstruction algorithm that aims to reconstruct high signal-to-noise images using a denoising technique. • Special care should be taken when scar size is quantified using thresholding techniques with different standard deviations above remote myocardium because of the large impact of these advanced image enhancement algorithms. • The full width at half maximum method is recommended to quantify scar size when deep learning algorithms based on noise reduction are used, as this method is the least sensitive to the level of noise and showed the best agreement with visual late gadolinium enhancement assessment.

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 Implications of multiple late gadolinium enhancement lesions on the frequency of left ventricular reverse remodeling and prognosis in patients with non‐ischemic cardiomyopathy

2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Shingo Ota ◽  
Makoto Orii ◽  
Tsuyoshi Nishiguchi ◽  
Mao Yokoyama ◽  
Ryoko Matsushita ◽  
...  
Keyword(s):  
Heart Failure ◽  
Late Gadolinium Enhancement ◽  
Ischemic Cardiomyopathy ◽  
Left Ventricular ◽  
Reverse Remodeling ◽  
Cardiac Events ◽  
Gadolinium Enhancement ◽  
Systolic Volume ◽  
Linear Pattern ◽  
Multiple Lesions

Abstract Background Non-ischemic cardiomyopathy (NICM) is a heterogeneous disease, and its prognosis varies. Although late gadolinium enhancement (LGE)-cardiovascular magnetic resonance (CMR) demonstrates a linear pattern in the mid-wall of the septum or multiple LGE lesions in patients with NICM, the therapeutic response and prognosis of multiple LGE lesions have not been elucidated. This study aimed to investigate the frequency of left ventricular (LV) reverse remodeling (LVRR) and prognosis in patients with NICM who have multiple LGE lesions. Methods This single-center retrospective study included 101 consecutive patients with NICM who were divided into 3 groups according to LGE-CMR results: patients without LGE (no LGE group = 48 patients), patients with a typical mid-wall LGE pattern (n = 29 patients), and patients with multiple LGE lesions (n = 24 patients). LVRR was defined as an increase in LV ejection fraction (LVEF) ≥ 10 % and a final value of LVEF > 35 %, which was accompanied by a decrease in LV end-systolic volume ≥ 15 % at 12-month follow-up using echocardiography. The frequency of composite cardiac events, defined as sudden cardiac death (SCD), aborted SCD (non-fatal ventricular fibrillation, sustained ventricular tachycardia, or adequate implantable cardioverter-defibrillator therapies), and heart failure death or hospitalization for worsening heart failure, were summarized and compared between the groups. Results Among the 3 groups, the frequency of LVRR was significantly lower in the multiple lesions group than in the no LGE and mid-wall groups (no LGE vs. mid-wall vs. multiple lesions: 49 % vs. 52 % vs. 19 %, p = 0.03). There were 24 composite cardiac events among the patients: 2 in patients without LGE (hospitalization for worsening heart failure; 2), 7 in patients of the mid-wall group (SCD; 1, aborted SCD; 1 and hospitalization for worsening heart failure; 5), and 15 in patients of the multiple lesions group (SCD; 1, aborted SCD; 8 and hospitalization for worsening heart failure; 6). The multiple LGE lesions was an independent predictor of composite cardiac events (hazard ratio: 11.40 [95 % confidence intervals: 1.49−92.01], p = 0.020). Conclusions Patients with multiple LGE lesions have a higher risk of cardiac events and poorer LVRR. The LGE pattern may be useful for an improved risk stratification in patients with NICM.

scholarly journals Feasibility of Total Variation Noise Reduction Algorithm According to Various MR-Based PET Images in a Simultaneous PET/MR System: A Phantom Study

Diagnostics ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 319
Author(s):  
Chan-Rok Park ◽  
Seong-Hyeon Kang ◽  
Young-Jin Lee
Keyword(s):  
Image Quality ◽  
Noise Reduction ◽  
Total Variation ◽  
Parallel Imaging ◽  
Pulse Sequence ◽  
Reduction Algorithm ◽  
Median Filters ◽  
Reduction Techniques ◽  
Imaging Results ◽  
Noise Reduction Algorithm

Recently, the total variation (TV) algorithm has been used for noise reduction distribution in degraded nuclear medicine images. To acquire positron emission tomography (PET) to correct the attenuation region in the PET/magnetic resonance (MR) system, the MR Dixon pulse sequence, which is based on controlled aliasing in parallel imaging, results from higher acceleration (CAIPI; MR-ACDixon-CAIPI) and generalized autocalibrating partially parallel acquisition (GRAPPA; MR-ACDixon-GRAPPA) algorithms are used. Therefore, this study aimed to evaluate the image performance of the TV noise reduction algorithm for PET/MR images using the Jaszczak phantom by injecting 18F radioisotopes with PET/MR, which is called mMR (Siemens, Germany), compared with conventional noise-reduction techniques such as Wiener and median filters. The contrast-to-noise (CNR) and coefficient of variation (COV) were used for quantitative analysis. Based on the results, PET images with the TV algorithm were improved by approximately 7.6% for CNR and decreased by approximately 20.0% for COV compared with conventional noise-reduction techniques. In particular, the image quality for the MR-ACDixon-CAIPI PET image was better than that of the MR-ACDixon-GRAPPA PET image. In conclusion, the TV noise-reduction algorithm is efficient for improving the PET image quality in PET/MR systems.

scholarly journals Image Noise Reduction Algorithm for Digital Subtraction Angiography: Clinical Results

Radiology ◽  
2013 ◽  
Vol 269 (2) ◽  
pp. 553-560 ◽  
Author(s):  
Michael Söderman ◽  
Staffan Holmin ◽  
Tommy Andersson ◽  
Charlotta Palmgren ◽  
Draženko Babić ◽  
...  
Keyword(s):  
Noise Reduction ◽  
Digital Subtraction Angiography ◽  
Clinical Results ◽  
Image Noise ◽  
Reduction Algorithm ◽  
Digital Subtraction ◽  
Image Noise Reduction ◽  
Noise Reduction Algorithm
Sign in / Sign up

Export Citation Format

Share Document