Integrating Atlas and Graph Cut Methods for Left Ventricle Segmentation from Cardiac Cine MRI

2017 ◽  
pp. 76-86 ◽  
Author(s):  
Shusil Dangi ◽  
Nathan Cahill ◽  
Cristian A. Linte
Keyword(s):  
Left Ventricle ◽  
Graph Cut ◽  
Cine Mri ◽  
Cardiac Cine ◽  
Ventricle Segmentation

scholarly journals Automatic Image-Driven Segmentation of Left Ventricle in Cardiac Cine MRI

2009 ◽  
Author(s):  
Yingli Lu ◽  
Perry Radau ◽  
Kim Connelly ◽  
Alexander Dick ◽  
Graham Wright
Keyword(s):  
Left Ventricle ◽  
Automatic Segmentation ◽  
Polar Coordinates ◽  
Cine Mri ◽  
Mr Images ◽  
Contour Segmentation ◽  
Cardiac Cine ◽  
Two Phases ◽  
Ventricle Segmentation ◽  
Cine Short Axis

This study investigates a fully automatic left ventricle segmentation method from cine short axis MR images. Advantages of this method include that it: 1) is image-driven and does not require manually drawn initial contours. 2) provides not only endocardial and epicardial contours, but also papillary muscles and trabeculations’ contours; 3) introduces a roundness measure that is fast and automatically locates the left ventricle; 4) simplifies the epicardial contour segmentation by mapping the pixels from Cartesian to approximately polar coordinates; and 5) applies a fast Fourier transform to smooth the endocardial and epicardial contours. Quantitative evaluation was performed on the 15 subjects of the MICCAI 2009 Cardiac MR Left Ventricle Segmentation hallenge. The average perpendicular distance between manually drawn and automatically selected contours over all slices, all studies, and two phases (end-diastole and end-systole) was 2.07 0.61 mm for endocardial and 1.91 0.63 mm for epicardial contours. These results indicate a promising method for automatic segmentation of left ventricle for clinical use.

scholarly journals Fully Automatic Left Ventricle Segmentation in Cardiac Cine MR Images Using Registration and Minimum Surfaces

2009 ◽  
Author(s):  
Marie-pierre Jolly
Keyword(s):  
Left Ventricle ◽  
Shortest Paths ◽  
Blood Pool ◽  
Grand Challenge ◽  
Mr Images ◽  
Cine Mr ◽  
Cardiac Cine ◽  
Cine Study ◽  
Fully Automatic ◽  
Ventricle Segmentation

This paper describes a fully automatic system to segment the left ventricle in all slices and all phases of a magnetic resonance cardiac cine study. After localizing the left ventricle blood pool using motion, thresholding and clustering, slices are segmented sequentially. For each slice, deformable registration is used to align all the phases, candidate contours are recovered in the average image using shortest paths, and a minimal surface is built to generate the final contours. The advantage of our method is that the resulting contours follow the edges in each phase and are consistent over time. As part of the MICCAI grand challenge on left ventricle segmentation, we demonstrate using 15 training datasets and 15 validation datasets that the results are very good with average errors around 2 mm and the method is ready for clinical routine.

Sign in / Sign up

Export Citation Format

Share Document