Interactive binary active contours for prostate contour delineation
| Autor: | Foued Derraz, Laurent Peyrodie, Abdelmalik Taleb-Ahmed, Gerard Forzy |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
business.industry
Segmentation-based object categorization Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Scale-space segmentation Pattern recognition Image segmentation Geometric shape Image (mathematics) Bhattacharyya distance Computer vision Segmentation Artificial intelligence business |
| Zdroj: | BIBE |
| DOI: | 10.1109/bibe.2012.6399727 |
| Popis: | We present a new interactive segmentation framework to delineate the prostate from MR images. We first explicitly address the segmentation problem based on fast globally Finsler Active Contours (FAC) by incorporating both statistical and geometric shape prior knowledge. In doing so, we are able to exploit the more global aspects of segmentation by incorporating user feedback in segmentation process. In addition, once the prostate shape has been segmented, a cost functional is designed to incorporate both the local image statistics as user feedback and the learned shape prior. We provide experimental results, which include several challenging clinical data sets, to highlight the algorithm's capability of robustly handling supine/prone prostate segmentation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|