| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Gustavsson, Tomas, 1954, et al.
(författare)
-
Implementation and Comparison of Four Different Boundary Detection Algorithms for Quantitative Ultrasonic Measurements of the Human Carotid Artery
- 1997
-
Ingår i: IEEE Conf. on Computers in Cardiology, Lund, Sweden, 7-10 Sep. ; 24, s. 69-72
-
Konferensbidrag (refereegranskat)abstract
- In this paper we examine four algorithms for automated ultrasonic boundary detection, and describe the application of these algorithms to the quantification of the intima-media thickness (IMT) in the human carotid artery. The first algorithm uses a dynamic programming approach to identify the boundary that minimizes a certain cost function. The second algorithm is based on finding points of maximum gradient The third algorithm employs a mathematical model describing the intensity profile perpendicular to the two boundaries defining the IMT. The last algorithm is based on defining a template representing the intensity profile across a boundary and applying a matched filter procedure to find the image region that best marches it. We also present a quantitative and qualitative comparison between the four algorithms examined. It is shown that the dynamic programming algorithm provides superior performance in terms of accuracy and robustness. The correlation coefficients between automated measurements and manually obtained reference values were 0.96, 0.94, 0.63, and 0.85 for the dynamic programming, the maximum gradient, the model-based, and the matched filter algorithm, respectively (n=30).
|
|
| 5. |
|
|
| 6. |
- Althoff, Karin, 1974, et al.
(författare)
-
Tracking Contrast in Echocardiography by a Combined Snake and Optical Flow Technique
- 2000
-
Ingår i: IEEE Conf. on Computers in Cardiology. ; 27
-
Konferensbidrag (refereegranskat)abstract
- Contrast-echocardiography in conjunction with real-time video-densiometry can be an effective means of studying right ventricular (RV) structural changes, e.g. in patients diagnosed with Arrhythmogenic Right Ventricular Dysplasia (ARVD). In order to characterize RV flow pattern it may be necessary to track the front of the contrast agent as it enters the RV. Active contour models (ACM) is a standard image analysis method,which can be applied to time-dynamic tracking problem.To improve tracking speed we extended the formulationof ACM by including an additional force, derived fromthe optical flow field, another standard image analysisalgorithm. This reduced the number of iterations needed to find the front of the contrast agent significantly. Also the changes in intensity of the contrast agent over time were studied. Two groups were compared, one with30 patients diagnosed with ARVD and one with 18healthy volunteers. Our study shows that that using our suggested method (calculating wash-in and wash-out time indices) it is possible to discriminate between thetwo groups.
|
|
| 7. |
- Hamarneh, Ghassan, 1972, et al.
(författare)
-
A Method for Modeling and Segmentation of Spatio-Temporal Shapes
- 1999
-
Ingår i: Proceedings of the Swedish Symposium on Image Analysis (SSAB). Göteborg, Sweden.
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a method for modeling and segmenting spatio-temporal shapes. The modeling part is based on obtaining a description of the statistical variations of spatio-temporal shape parameters by studying a representative training set of examples. A deformable modelof spatio-temporal shapes is used for segmenting similarshapes in new image sequences. The deformations of the model are driven by image features and are forced toproduce results that are similar to what was found in thetraining set. The proposed deformations of the spatio-temporal shape are chosen to minimize a cost function usinga dynamic programming approach. The preliminary resultspresented show that the method succeeds in segmentingcomplex spatio-temporal shapes in synthetic noisy data.
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
