Heart Visualization from MRI Marek Zimnyi Julius Parulek Faculty - PowerPoint PPT Presentation

Heart Visualization from MRI Marek Zimányi Julius Parulek Faculty of Mathematics, Physics and Informatics Comenius University, Bratislava and International Laser Center Bratislava

Goal of this work n Input MRI data set n Create Heart surface model from MRI data set # 2 Marek Zimányi, DAI CU

Three main problems: n MRI Image Enhancement n Heart segmentation n Surface modeling from contours # 3 Marek Zimányi, DAI CU

Load DICOM Data n Data n MRI – Dicom FILES (not parallel too) n Loading using DCMTK n Computing time period for every slice and group slices with the same period value # 4 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Image Enhancement n Enhance contrast and histogram equalization n Bias correction ( Estimation of inhomogeneities ) n Work in progress # 5 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Image Enh. - Bias correction n Bias correction ( Estimation of inhomogeneities ) # 6 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Image Enh. - Bias correction Measured Restored Bias field # 7 Marek Zimányi, DAI CU

POSSIBLE USE SENARIOS Image Preprocessing n original image -> IntensityCorrector -> preprocessed image n Bias Field Estimation n original image (or preprocessed image) -> BiasFieldEstimator -> n coefficients of the bias field estimate Bias Correction n original image + the coefficients of the bias field estimate (from n BiasFieldEstimator) -> BiasCorrector -> bias field corrected image Bias Image Generation n the coefficients of the bias field estimate + result image dimension n and size -> BiasImageGenerator -> bias image # 8 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Segmentation n Small changes – median filter, sharpen etc … n Then segmentation # 9 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Segmentation n Canny/Deriche n than Snake # 10 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Segmentation # 11 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Segmentation - next n Automatic segmentation n Create heart contour when ventricle(s) contour is known # 12 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Segmentation n Our added value: n Add value for extracted pixel of contour, “how sure we are that it is a contour point” n Segmetation of heart when ventricles is known # 13 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling n Input: contours n Ouput: Surface model # 14 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling by Implicit Surfaces n Set of points { c 1 , c 2 , … c k } - contour n Set of constraints { h 1 , h 2 , … h k } n f(c i )= h i , n Minimization of energy: # 15 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling by Implicit Surfaces n Equestion E can be solved using radial basis functions n c i is localization of points, d i are weights and P(x) if polynomial of deg 1 # 16 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling by Implicit Surfaces n f(c i )= h i , than n Solving by symmetric LU decomposition # 17 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling by Implicit Surfaces n Problems: n Correct setting of constrains n Contours don’t have to intersect - points with constrain value 0 can be in the object # 18 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling by Implicit Surfaces n Solution: n Add new contours of L/R ventricle as an interior of heart # 19 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Heart Modeling n Our added value: n Create mechanism for creating implicit surface when points with constrain value 0 can be in the object. # 20 DataLoad Enhancement Segmentation Modeling Marek Zimányi, DAI CU

Next work n Finnish correct setting of constrains fo implicit surface generation n (Semi)Automatic segmentation of heart n Add motion info to segmentation # 21 Marek Zimányi, DAI CU

Literature Jorgen Ahlberg, Active Contours in Three Dimension , research report, n 1996 Zhukov et al, Dynamic Deformable Models for 3D MRI Heart Segmentation n Sorgel W., Vaerman V., Automatic heart localization from a 4D MRI n dataset Majcenic Z., Loncaric S., Algorithm for spatio-temporal hear segmentation n Uschler M., Image-Based verification of parametric models in heart- n ventricle volumetry , Graz 2001, Cipolla R., Giblin P., Visual Motion of Curves and Surfaces , book n Rucker D., Segmentation and Tracking in Cardiovascular MR Images using n Geometrically Deformable Models and Templates , PhD work 1997 M-P Jolly, N.Duta, G F-Lea, Segmentation of Left Ventricle in Cardiac MR n Images, ICCV 01 Greg Turk, J F O’Brien, Shape Transformation Using Variatonal Implicit n Functions, Siggraph’99 # 22 Marek Zimányi, DAI CU