Title | ||
---|---|---|
Automated LGE Myocardial Scar Segmentation Using MaskSLIC Supervoxels - Replicating the Clinical Method. |
Abstract | ||
---|---|---|
Cardiovascular diseases (CVD) are one of the major killers in modern society. In the UK alone 70,000 people have died from CVD last year according to the 2016 British Heart Foundation Annual Report [2]. Furthermore, the number of patients suffering from chronic CVDs is likely to rise due to an ageing population, as well as, better survival rates after cardiac events. In the case of a heart attack, accurate quantification of the formed scar is essential for improving and deciding the treatment plan, and therefore improving the patient outcomes. In this work we present an automated method for segmenting the scar from late gadolinium enhancement magnetic resonance images using maskSLIC clustering method and Otsu thresholding to divide the myocardium into regions based on differences in intensity. Our method is fast and simple to use, and is consistent across cases and eliminates the spatial inconsistencies previously reported in the literature. The validation is performed using visual assessment from \(cmr^{42}\) clinical software. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-60964-5_20 | MIUA |
Field | DocType | Citations |
Segmentation,Visual assessment,Radiology,Thresholding,Cluster analysis,Medicine,Magnetic resonance imaging | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Iulia A. Popescu | 1 | 1 | 1.72 |
Alessandra Borlotti | 2 | 0 | 1.35 |
erica dallarmellina | 3 | 0 | 0.68 |
Vicente Grau | 4 | 38 | 12.23 |