P1669 Automated quantification of left-ventricular volumes and function: a novel clinical tool?

Abstract To investigate the performance of a deep learning-based algorithm for fully automated quantification of left ventricular (LV) volumes and function in cardiac MRI. We retrospectively analysed MR examinations of 50 patients (74% men, median age 57 years). The most common indications were known or suspected ischemic heart disease, cardiomyopathies or myocarditis. Fully automated analysis of LV volumes and function was performed using a deep learning-based algorithm. The analysis was subsequently corrected by a senior cardiovascular radiologist. Manual volumetric analysis was performed by two radiology trainees. Volumetric results were compared using Bland–Altman statistics and intra-class correlation coefficient. The frequency of clinically relevant differences was analysed using re-classification rates. The fully automated volumetric analysis was completed in a median of 8 s. With expert review and corrections, the analysis required a median of 110 s. Median time required for manual analysis was 3.5 min for a cardiovascular imaging fellow and 9 min for a radiology resident (p < 0.0001 for all comparisons). The correlation between fully automated results and expert-corrected results was very strong with intra-class correlation coefficients of 0.998 for end-diastolic volume, 0.997 for end-systolic volume, 0.899 for stroke volume, 0.972 for ejection fraction and 0.991 for myocardial mass (all p < 0.001). Clinically meaningful differences between fully automated and expert corrected results occurred in 18% of cases, comparable to the rate between the two manual readers (20%). Deep learning-based fully automated analysis of LV volumes and function is feasible, time-efficient and highly accurate. Clinically relevant corrections are required in a minority of cases.

Download Full-text

The apical long-axis rather than the two-chamber view should be used in combination with the four-chamber view for accurate assessment of left ventricular volumes and function

European Heart Journal ◽

10.1093/oxfordjournals.eurheartj.a015414 ◽

1997 ◽

Vol 18 (7) ◽

pp. 1175-1185 ◽

Cited By ~ 34

Author(s):

Y. F. M. Nosir ◽

W. B. Vletter ◽

E. Boersma ◽

R. Frowijn ◽

F. J. Ten Cate ◽

...

Keyword(s):

Left Ventricular ◽

Left Ventricular Volumes ◽

Accurate Assessment ◽

Ventricular Volumes ◽

Chamber View ◽

And Function

Download Full-text

Left ventricular non-compaction in patients with single ventricle heart disease

Cardiology in the Young ◽

10.1017/s1047951119001872 ◽

2020 ◽

Vol 30 (1) ◽

pp. 12-18 ◽

Cited By ~ 1

Author(s):

Preeti Choudhary ◽

Wendy Strugnell ◽

Rajesh Puranik ◽

Christian Hamilton-Craig ◽

Shelby Kutty ◽

...

Keyword(s):

Heart Disease ◽

Ventricular Function ◽

Single Ventricle ◽

Systolic Function ◽

Left Ventricular ◽

Left Ventricular Ejection ◽

Left Ventricular Volumes ◽

Ventricular Ejection Fraction ◽

Ventricular Volumes ◽

And Function

AbstractObjective:Left ventricular non-compaction is an architectural abnormality of the myocardium, associated with heart failure, systemic thromboembolism, and arrhythmia. We sought to assess the prevalence of left ventricular non-compaction in patients with single ventricle heart disease and its effects on ventricular function.Methods:Cardiac MRI of 93 patients with single ventricle heart disease (mean age 24 ± 8 years; 55% male) from three tertiary congenital centres was retrospectively reviewed; 65 of these had left ventricular morphology and are the subject of this report. The presence of left ventricular non-compaction was defined as having a non-compacted:compacted (NC:C) myocardial thickness ratio >2.3:1. The distribution of left ventricular non-compaction, ventricular volumes, and function was correlated with clinical data.Results:The prevalence of left ventricular non-compaction was 37% (24 of 65 patients) with a mean of 4 ± 2 affected segments. The distribution was apical in 100%, mid-ventricular in 29%, and basal in 17% of patients. Patients with left ventricular non-compaction had significantly higher end-diastolic (128 ± 44 versus 104 ± 46 mL/m2, p = 0.047) and end-systolic left ventricular volumes (74 ± 35 versus 56 ± 35 mL/m2, p = 0.039) with lower left ventricular ejection fraction (44 ± 11 versus 50 ± 9%, p = 0.039) compared to those with normal compaction. The number of segments involved did not correlate with ventricular function (p = 0.71).Conclusions:Left ventricular non-compaction is frequently observed in patients with left ventricle-type univentricular hearts, with predominantly apical and mid-ventricular involvement. The presence of non-compaction is associated with increased indexed end-diastolic volumes and impaired systolic function.

Download Full-text