| 1. |
- Gonzales, Ricardo A., et al.
(författare)
-
MVnet : automated time-resolved tracking of the mitral valve plane in CMR long-axis cine images with residual neural networks: a multi-center, multi-vendor study
- 2021
-
Ingår i: Journal of Cardiovascular Magnetic Resonance. - : Springer Science and Business Media LLC. - 1097-6647 .- 1532-429X. ; 23, s. 1-15
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Mitral annular plane systolic excursion (MAPSE) and left ventricular (LV) early diastolic velocity (e’) are key metrics of systolic and diastolic function, but not often measured by cardiovascular magnetic resonance (CMR). Its derivation is possible with manual, precise annotation of the mitral valve (MV) insertion points along the cardiac cycle in both two and four-chamber long-axis cines, but this process is highly time-consuming, laborious, and prone to errors. A fully automated, consistent, fast, and accurate method for MV plane tracking is lacking. In this study, we propose MVnet, a deep learning approach for MV point localization and tracking capable of deriving such clinical metrics comparable to human expert-level performance, and validated it in a multi-vendor, multi-center clinical population. Methods: The proposed pipeline first performs a coarse MV point annotation in a given cine accurately enough to apply an automated linear transformation task, which standardizes the size, cropping, resolution, and heart orientation, and second, tracks the MV points with high accuracy. The model was trained and evaluated on 38,854 cine images from 703 patients with diverse cardiovascular conditions, scanned on equipment from 3 main vendors, 16 centers, and 7 countries, and manually annotated by 10 observers. Agreement was assessed by the intra-class correlation coefficient (ICC) for both clinical metrics and by the distance error in the MV plane displacement. For inter-observer variability analysis, an additional pair of observers performed manual annotations in a randomly chosen set of 50 patients. Results: MVnet achieved a fast segmentation (<1 s/cine) with excellent ICCs of 0.94 (MAPSE) and 0.93 (LV e’) and a MV plane tracking error of −0.10 ± 0.97 mm. In a similar manner, the inter-observer variability analysis yielded ICCs of 0.95 and 0.89 and a tracking error of −0.15 ± 1.18 mm, respectively. Conclusion: A dual-stage deep learning approach for automated annotation of MV points for systolic and diastolic evaluation in CMR long-axis cine images was developed. The method is able to carefully track these points with high accuracy and in a timely manner. This will improve the feasibility of CMR methods which rely on valve tracking and increase their utility in a clinical setting.
|
|
| 2. |
|
|
| 3. |
- Lundin, Magnus, et al.
(författare)
-
Left ventricular global wall thickness is easily calculated, detects and characterizes hypertrophy, and has prognostic utility
- 2019
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- BACKGROUND: Cardiovascular magnetic resonance (CMR) can be used to measure left ventricular end-diastolic volume (LVEDV) and left ventricular mass (LVM). However, there is currently no good way to measure the normality of LVM in relation to a given LVEDV. We hypothesized that a simple measure of left ventricular global wall thickness (GWT) would be accurate, beneficial for detecting and characterizing hypertrophy, and have prognostic significance.METHODS: Subjects underwent CMR at 1.5T, including healthy volunteers (n=99) and patients assessed for heart disease (n=2828).RESULTS: GWT calculated from LVEDV and LVM had excellent agreement with measured mean end-diastolic wall thickness of the entire left ventricle (bias 0.01±0.23mm). GWT was most predictive of death or hospitalization for heart failure in patients with normal findings by CMR (n=326, log-rank 26.8, p<0.001, median [interquartile range] follow-up 5.8 [5.0–6.7] years). GWT indexed to body surface area (GWTi) was most predictive of outcomes in patients with normal LVEDV index (n=1352, log-rank 36.4, p<0.001, follow-up 5.5 [4.1–6.5] years). Patients with concentric remodeling had worse prognosis than the normal patients (p=0.02), and the patients with hypertrophy had worse prognosis than both normal patients (p<0.001) and patients with concentric remodeling (p=0.045), see Figure 1. Of patients with suspected heart disease but normal CMR findings regarding left ventricular volumes, function, mass, and scar, 22% were found to have increased mean GWTi corresponding to concentric remodeling, see Figure 2.CONCLUSIONS: Left ventricular GWT is an intuitive measure that can be easily calculated from mass and volume with high accuracy, and has prognostic utility in patients with normal CMR findings. Also, GWTi classifies hypertrophy as concentric or eccentric, and detects concentric remodeling in a substantial portion of patients with otherwise normal findings.
|
|
| 4. |
|
|
| 5. |
- Lundin, Magnus, et al.
(författare)
-
Prognostic utility and characterization of left ventricular hypertrophy using global thickness
- 2023
-
Ingår i: Scientific Reports. - 2045-2322. ; 13:1
-
Tidskriftsartikel (refereegranskat)abstract
- Cardiovascular magnetic resonance (CMR) can accurately measure left ventricular (LV) mass, and several measures related to LV wall thickness exist. We hypothesized that prognosis can be used to select an optimal measure of wall thickness for characterizing LV hypertrophy. Subjects having undergone CMR were studied (cardiac patients, n = 2543; healthy volunteers, n = 100). A new measure, global wall thickness (GT, GTI if indexed to body surface area) was accurately calculated from LV mass and end-diastolic volume. Among patients with follow-up (n = 1575, median follow-up 5.4 years), the most predictive measure of death or hospitalization for heart failure was LV mass index (LVMI) (hazard ratio (HR)[95% confidence interval] 1.16[1.12-1.20], p < 0.001), followed by GTI (HR 1.14[1.09-1.19], p < 0.001). Among patients with normal findings (n = 326, median follow-up 5.8 years), the most predictive measure was GT (HR 1.62[1.35-1.94], p < 0.001). GT and LVMI could characterize patients as having a normal LV mass and wall thickness, concentric remodeling, concentric hypertrophy, or eccentric hypertrophy, and the three abnormal groups had worse prognosis than the normal group (p < 0.05 for all). LV mass is highly prognostic when mass is elevated, but GT is easily and accurately calculated, and adds value and discrimination amongst those with normal LV mass (early disease).
|
|
| 6. |
- Seemann, Felicia, et al.
(författare)
-
Time-resolved tracking of the atrioventricular plane displacement in Cardiovascular Magnetic Resonance (CMR) images
- 2017
-
Ingår i: BMC Medical Imaging. - : Springer Science and Business Media LLC. - 1471-2342. ; 17:19
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND:Atrioventricular plane displacement (AVPD) is an indicator for systolic and diastolic function and accounts for 60% of the left ventricular, and 80% of the right ventricular stroke volume. AVPD is commonly measured clinically in echocardiography as mitral and tricuspid annular plane systolic excursion (MAPSE and TAPSE), but has not been applied widely in cardiovascular magnetic resonance (CMR). To date, there is no robust automatic algorithm available that allows the AVPD to be measured clinically in CMR with input in a single timeframe. This study aimed to develop, validate and provide a method that automatically tracks the left and right ventricular AVPD in CMR images, which can be used in the clinical setting or in applied cardiovascular research in multi-center studies.METHODS:The proposed algorithm is based on template tracking by normalized cross-correlation combined with a priori information by principal component analysis. The AVPD in each timeframe is calculated for the left and right ventricle separately using CMR long-axis cine images of the 2, 3, and 4-chamber views. The algorithm was developed using a training set (n = 40), and validated in a test set (n = 113) of healthy subjects, athletes, and patients after ST-elevation myocardial infarction from 10 centers. Validation was done using manual measurements in end diastole and end systole as reference standard. Additionally, AVPD, peak emptying velocity, peak filling velocity, and atrial contraction was validated in 20 subjects, where time-resolved manual measurements were used as reference standard. Inter-observer variability was analyzed in 20 subjects.RESULTS:In end systole, the difference between the algorithm and the reference standard in the left ventricle was (mean ± SD) -0.6 ± 1.9 mm (R = 0.79), and -0.8 ± 2.1 mm (R = 0.88) in the right ventricle. Inter-observer variability in end systole was -0.6 ± 0.7 mm (R = 0.95), and -0.5 ± 1.4 mm (R = 0.95) for the left and right ventricle, respectively. Validation of peak emptying velocity, peak filling velocity, and atrial contraction yielded lower accuracy than the displacement measures.CONCLUSIONS:The proposed algorithm show good agreement and low bias with the reference standard, and with an agreement in parity with inter-observer variability. Thus, it can be used as an automatic method of tracking and measuring AVPD in CMR.
|
|
