Automated myocardial edge detection on MR images: accuracy in consecutive subjects

Mathematical model in left ventricle segmentation

In this paper a parametric model of the left ventricle is presented. Its task is to estimate the myocardium shape on those slices, on which the segmentation algorithm has outlined the structure incorrectly. The aim of using the model on improperly segmented slices is to improve the accuracy of computing cardiac hemodynamic parameters and the heart mass. The proposed model works with any segmentation algorithm. The usefulness of the model is the largest while determining the myocardium at end-systole and calculating the heart mass. In case of the segmentation algorithm applied in this study, the error decreased from clinically unacceptable to acceptable after using the presented model.

Unsupervised fully automated inline analysis of global left ventricular function in CINE MR imaging

OBJECTIVES

To implement and evaluate the accuracy of unsupervised fully automated inline analysis of global ventricular function and myocardial mass (MM). To compare automated with manual segmentation in patients with cardiac disorders.

MATERIALS AND METHODS

In 50 patients, cine imaging of the left ventricle was performed with an accelerated retrogated steady state free precession sequence (GRAPPA; R = 2) on a 1.5 Tesla whole body scanner (MAGNETOM Avanto, Siemens Healthcare, Germany). A spatial resolution of 1.4 x 1.9 mm was achieved with a slice thickness of 8 mm and a temporal resolution of 42 milliseconds. Ventricular coverage was based on 9 to 12 short axis slices extending from the annulus of the mitral valve to the apex with 2 mm gaps. Fully automated segmentation and contouring was performed instantaneously after image acquisition. In addition to automated processing, cine data sets were also manually segmented using a semi-automated postprocessing software. Results of both methods were compared with regard to end-diastolic volume (EDV), end-systolic volume (ESV), ejection fraction (EF), and MM. A subgroup analysis was performed in patients with normal (> or =55%) and reduced EF (<55%) based on the results of the manual analysis.

RESULTS

Thirty-two percent of patients had a reduced left ventricular EF of <55%. Volumetric results of the automated inline analysis for EDV (r = 0.96), ESV (r = 0.95), EF (r = 0.89), and MM (r = 0.96) showed high correlation with the results of manual segmentation (all P < 0.001). Head-to-head comparison did not show significant differences between automated and manual evaluation for EDV (153.6 +/- 52.7 mL vs. 149.1 +/- 48.3 mL; P = 0.05), ESV (61.6 +/- 31.0 mL vs. 64.1 +/- 31.7 mL; P = 0.08), and EF (58.0 +/- 11.6% vs. 58.6 +/- 11.6%; P = 0.5). However, differences were significant for MM (150.0 +/- 61.3 g vs. 142.4 +/- 59.0 g; P < 0.01). The standard error was 15.6 (EDV), 9.7 (ESV), 5.0 (EF), and 17.1 (mass). The mean time for manual analysis was 15 minutes.

CONCLUSIONS

Unsupervised fully automated segmentation and contouring during image reconstruction enables an accurate evaluation of global systolic cardiac function.

Quantification of global and regional ventricular function in cardiac magnetic resonance imaging

One of the strong assets of cardiac magnetic resonance (CMR) is its ability to assess myocardial anatomy, structure, function, flow, and perfusion within a single examination. Quantification of global and regional function from magnetic resonance imaging (MRI) studies was shown to be accurate and reproducible in experimental and clinical research studies. With the advent of high-performance MRI scanners and newly developed pulse sequences, image acquisition times have been reduced considerably in recent years. However, the clinical use of CMR remains limited for various reasons. Among these limitations is that the amount of images obtained in a typical cardiac examination is so large that visual and especially quantitative image analysis is tedious and time consuming. There is an urgent need for optimized dedicated software tools featuring highly automated contour detection and optimized display capabilities to present the quantitative results to the physician in an orderly fashion, thus facilitating clinical decision making. This article focuses on the state of the art in CMR postprocessing techniques for quantitative assessment of global and regional function.

A multicenter validation of an active contour-based left ventricular analysis technique

Quantitative analysis of functional cardiac magnetic resonance (MR) images has been limited by the lack of well-validated, semiautomatic, methods for rapid analysis. We describe the evaluation of a DICOM-compatible PC-based parallel-processing tool, for cardiac magnetic resonance analysis (CAMRA), which supports semiautomatic image mensuration using an active contour model-based algorithm. The CAMRA software was used to analyze data from 12 patients in a multicenter acquisition and analysis trial to compare semiautomatic contour detection with manual planimetry of the left ventricular endocardium from short-axis, breath-held, cine gradient-echo images. There was excellent agreement between the manual and semiautomatic measurements of global left ventricular function, with no significant (P = 0.32) difference in the determination of ejection fraction (-0.9 +/- 3.1% [mean difference +/- 1 standard deviation]). There was no significant interobserver difference in the semiautomatically measured ejection fraction. Additionally, a single observer completed the analysis on data from 30 patients and found no significant (P = 0.05) difference in the determination of ejection fraction (-1.3 +/- 3.5% [mean difference +/- 1 standard deviation]). The CAMRA software demonstrates the capability for the reproducible evaluation of global left ventricular function in cardiac patients, with adequate interobserver reproducibility for use in multicenter trials.

Reproducibility study of left ventricular measurements with breath-hold cine MRI using a semiautomated volumetric image analysis program

The reproducibility of a semiautomated method of volumetric analysis allowing estimates of left ventricular (LV) parameters in approximately 5 minutes of analysis time is reported. Twenty normal volunteers underwent cine breath-hold cardiac MRI on two occasions with two observers using this new semiautomated method to estimate LV parameters. Reproducibility of this technique was comparable to published data with a variability of less than approximately 10% for all LV parameters calculated. Using this technique, the 95% confidence limits for change for left ventricular end diastolic volume (LVEDV) = +/-15 ml, left ventricular end systolic volume (LVESV) = +/-8 ml, LV mass = +/-24 g, and left ventricular ejection fraction (LVEF) = +/-6%. This new method also compared favorably to established manual methods. This new method permits estimation of LV parameters with acceptable reproducibility in a time that may permit routine quantitation of cardiac MR studies.

Comparison between manual and semiautomated analysis of left ventricular volume parameters from short-axis MR images

PURPOSE

The goal of this study was to evaluate a newly developed semiautomated contour detection algorithm for the quantitative analysis of cardiovascular MRI.

METHOD

Left ventricular function parameters derived from automatically detected endocardial and epicardial contours were compared with results derived from manually traced contours in short-axis multislice GRE MRI studies of 10 normal volunteers and 10 infarct patients.

RESULTS

Compared with manual image analysis, the semiautomated method resulted in the following systematic and random differences (auto-manual; mean +/- SD): end-diastolic volume: -5.5 +/- 9.7 ml; end-systolic volume: -3.6 +/- 6.5 ml; ejection fraction: 1.7 +/- 4.1%; left ventricular mass: 7.3 +/- 20.6 g. Total analysis time for a complete study was reduced from 3-4 h for the manual analysis to < 20 min using semiautomated contour detection.

CONCLUSION

Global left ventricular function parameters can be obtained with a high degree of accuracy and precision using the present semiautomated contour detection algorithm.

Automatic cardiac MR image segmentation using edge detection by tissue classification in pixel neighborhoods

A highly sensitive edge detector has been developed that uses tissue classification of pixels based on analysis of data in their local neighborhoods. In conjunction with recursive region growing, it has been used successfully to define regions of interest (ROI) when applied specifically to gradient echo MR images of the heart. The detector adapts to nonuniformity by carrying out an independent analysis at each location. If two tissues are present in a neighborhood and the pixel at that location cannot be classified with the seed pixel, a region edge has been crossed and recursion is stopped. No geometric assumptions relating to object shape such as definition of a region center and radial search are required. The detector was applied to multi-slice, multi-phase images of the heart from 26 subjects. A segmentation strategy specified slice processing order, graded ROIs, and used successfully detected ROIs to guide subsequent detection. Segmentation of all images resulted in a 90.3% median edge pixel detection efficiency.

Low-dosage dobutamine magnetic resonance imaging as an alternative to echocardiography in the detection of viable myocardium after acute infarction

The objective of this study was the evaluation of the feasibility of magnetic resonance (MR) imaging of the heart with low-dosage dobutamine stimulation for the detection of viability after acute myocardial infarction. Gradient echo MR images were obtained in 37 patients with recent myocardial infarction. Images of wall motion abnormalities and their reaction to low-dosage dobutamine stimulation were analyzed and compared with two-dimensional echocardiograms. Follow-up echocardiography at 3 to 6 months was available in 24 patients. Concordant diagnosis of viability between the two techniques was obtained in 30 (81%) of 37 patients. MR correctly predicted evolution of wall motion in 19 (79%) of 24 patients, a result not significantly different from echocardiography: 20 (83%) of 24. It was concluded that low-dosage dobutamine MR imaging is a safe alternative to echocardiography to predict recovery of wall motion abnormalities after myocardial infarction.

Segmentation of small structures in MR images: semiautomated tissue hydration measurement

Segmentation of small anatomic structures in noisy magnetic resonance (MR) images is inherently challenging because the edge information is contained in the same high-frequency image component as the noise. The authors overcame this obstacle in the analysis of the sural nerve in the ankle by processing images to reduce noise and extracting edges with an edge detection algorithm less sensitive to noise. Anatomic accuracy of the segmentation was confirmed by a neuroradiologist. A nerve hydration coefficient was determined from the signal intensity of the nerve in these segmented images. These semiautomated measurements of hydration agreed closely with those obtained with a previously described manual method (n = 44, P = .76). Each image in the study was analyzed identically, with no modification of the computer algorithm parameters. The data suggest that this robust method may be useful in a multicenter evaluation of diabetes treatment protocols.