In prostate brachytherapy, intraoperative dosimetry requires clear information describing the three-dimensional position of the seeds deposited within the prostate. We propose a robust and fully-automatic seed segmentation of brachytherapy implants by utilizing a region-based implicit active contour approach. Overlapping seed clusters are then resolved using a simple yet effective de-clustering technique. A total of 248 clinical C-arm images from 16 patients were used to validate the proposed algorithm resulting in a 98.4% automatic detection rate with a corresponding 2.5% false-positive rate. The overall mean centroid error between the manual and automatic segmentations was measured to be 0.42 pixels.     «

In prostate brachytherapy, intraoperative dosimetry requires clear information describing the three-dimensional position of the seeds deposited within the prostate. We propose a robust and fully-automatic seed segmentation of brachytherapy implants by utilizing a region-based implicit active contour approach. Overlapping seed clusters are then resolved using a simple yet effective de-clustering technique. A total of 248 clinical C-arm images from 16 patients were used to validate the proposed al...     »