Validation and Development of a New Automatic Algorithm for Time-Resolved Segmentation of the Left Ventricle in Magnetic Resonance Imaging.
Bottom Line:
Ninety subjects imaged with a cine balanced steady state free precession sequence were included in the study (training set n = 40, test set n = 50).Manual delineation was reference standard and second observer analysis was performed in a subset (n = 25).The mean differences between automatic segmentation and manual delineation were EDV -11 mL, ESV 1 mL, EF -3%, and LVM 4 g in the test set.
View Article:
PubMed Central - PubMed
Affiliation: Department of Clinical Physiology, Lund University Hospital, Lund University, 221 85 Lund, Sweden ; Department of Numerical Analysis, Centre for Mathematical Sciences, Faculty of Engineering, Lund University, 221 00 Lund, Sweden.
ABSTRACT
Introduction: Manual delineation of the left ventricle is clinical standard for quantification of cardiovascular magnetic resonance images despite being time consuming and observer dependent. Previous automatic methods generally do not account for one major contributor to stroke volume, the long-axis motion. Therefore, the aim of this study was to develop and validate an automatic algorithm for time-resolved segmentation covering the whole left ventricle, including basal slices affected by long-axis motion. Methods: Ninety subjects imaged with a cine balanced steady state free precession sequence were included in the study (training set n = 40, test set n = 50). Manual delineation was reference standard and second observer analysis was performed in a subset (n = 25). The automatic algorithm uses deformable model with expectation-maximization, followed by automatic removal of papillary muscles and detection of the outflow tract. Results: The mean differences between automatic segmentation and manual delineation were EDV -11 mL, ESV 1 mL, EF -3%, and LVM 4 g in the test set. Conclusions: The automatic LV segmentation algorithm reached accuracy comparable to interobserver for manual delineation, thereby bringing automatic segmentation one step closer to clinical routine. The algorithm and all images with manual delineations are available for benchmarking. No MeSH data available. Related in: MedlinePlus |
Related In:
Results -
Collection
License getmorefigures.php?uid=PMC4491381&req=5
Mentions: Calculation of Balloon Image (Step 2). The balloon force, which is the most important part of the deformable model, is defined using an expectation maximization (EM) algorithm. The balloon force drives the expansion and contraction of the curve and thereby should be a distinction between what to include and exclude in the endocardial and epicardial segmentations. The balloon image is mapped from the image intensities by estimating the distribution of intensities in the images. For endocardial segmentation the intensity distributions for blood and myocardium are estimated. In addition for epicardial segmentation, the intensity distribution of tissues surrounding the left ventricle is estimated. An EM-algorithm was utilized to estimate assumed Gaussian distribution of intensities for blood, myocardium, and surrounding tissues. As an initialization to the EM-algorithm, the mean and standard deviation for the intensity of blood were estimated in a cylinder with radius of 10 mm placed at the left ventricular center point. The endocardial balloon image was calculated as the Gaussian distribution for blood divided by the sum of the Gaussian distributions for blood and myocardium. The epicardial balloon image was calculated as the Gaussian distribution for myocardium divided by the sum of the Gaussian distributions for blood, myocardium, and surrounding tissues. The balloon force is positive for intensity values to include and negative for intensities to exclude and the balloon force was rescaled to the interval −1 to 1. Figure 1 shows the results from calculation of the balloon image. |
View Article: PubMed Central - PubMed
Affiliation: Department of Clinical Physiology, Lund University Hospital, Lund University, 221 85 Lund, Sweden ; Department of Numerical Analysis, Centre for Mathematical Sciences, Faculty of Engineering, Lund University, 221 00 Lund, Sweden.
Introduction: Manual delineation of the left ventricle is clinical standard for quantification of cardiovascular magnetic resonance images despite being time consuming and observer dependent. Previous automatic methods generally do not account for one major contributor to stroke volume, the long-axis motion. Therefore, the aim of this study was to develop and validate an automatic algorithm for time-resolved segmentation covering the whole left ventricle, including basal slices affected by long-axis motion.
Methods: Ninety subjects imaged with a cine balanced steady state free precession sequence were included in the study (training set n = 40, test set n = 50). Manual delineation was reference standard and second observer analysis was performed in a subset (n = 25). The automatic algorithm uses deformable model with expectation-maximization, followed by automatic removal of papillary muscles and detection of the outflow tract.
Results: The mean differences between automatic segmentation and manual delineation were EDV -11 mL, ESV 1 mL, EF -3%, and LVM 4 g in the test set.
Conclusions: The automatic LV segmentation algorithm reached accuracy comparable to interobserver for manual delineation, thereby bringing automatic segmentation one step closer to clinical routine. The algorithm and all images with manual delineations are available for benchmarking.
No MeSH data available.