PURPOSE: Dynamic dosimetry is becoming the standard to evaluate the quality of radioactive implants during brachytherapy. For this, it is essential to obtain a 3D visualization of the implanted seeds and their relative position to the prostate. A method was developed to obtain a robust and precise segmentation of seeds in C-arm images, and this approach was tested using clinical datasets. METHOD: A region-based implicit active contour approach was used to delineate implanted seeds. Then, a template-based matching was employed to segment iodine implants whereas a K-means algorithm is implemented to resolve palladium seed clusters. To validate the method, 55 C-arm images from 10 patients were used for the segmentation of iodine sources, whereas 225 C-arm images from 16 patients were used for the palladium case. RESULTS: Compared to manual ground truth segmentation of 6,002 iodine seeds and 15,354 palladium seeds, 98.7 % of iodine sources were automatically detected and declustered showing a false-positive rate of only 1.7 %. A total of 98.7 % of palladium sources were automatically detected and declustered with a false-positive rate of only 2.0 %. CONCLUSION: An automated segmentation method was developed that is able to perform the identification and annotation processes of seeds on par with a human expert. This method was shown to be robust and suitable for integration in the dynamic dosimetry workflow of prostate brachytherapy interventions.
PURPOSE: Dynamic dosimetry is becoming the standard to evaluate the quality of radioactive implants during brachytherapy. For this, it is essential to obtain a 3D visualization of the implanted seeds and their relative position to the prostate. A method was developed to obtain a robust and precise segmentation of seeds in C-arm images, and this approach was tested using clinical datasets. METHOD: A region-based implicit active contour approach was used to delineate implanted seeds. Then, a template-based matching was employed to segment iodine implants whereas a K-means algorithm is implemented to resolve palladium seed clusters. To validate the method, 55 C-arm images from 10 patients were used for the segmentation of iodine sources, whereas 225 C-arm images from 16 patients were used for the palladium case. RESULTS: Compared to manual ground truth segmentation of 6,002 iodine seeds and 15,354 palladium seeds, 98.7 % of iodine sources were automatically detected and declustered showing a false-positive rate of only 1.7 %. A total of 98.7 % of palladium sources were automatically detected and declustered with a false-positive rate of only 2.0 %. CONCLUSION: An automated segmentation method was developed that is able to perform the identification and annotation processes of seeds on par with a human expert. This method was shown to be robust and suitable for integration in the dynamic dosimetry workflow of prostate brachytherapy interventions.
Authors: S Nag; J P Ciezki; R Cormack; S Doggett; K DeWyngaert; G K Edmundson; R G Stock; N N Stone; Y Yu; M J Zelefsky Journal: Int J Radiat Oncol Biol Phys Date: 2001-12-01 Impact factor: 7.038
Authors: Junghoon Lee; Christian Labat; Ameet K Jain; Danny Y Song; Everette Clif Burdette; Gabor Fichtinger; Jerry L Prince Journal: IEEE Trans Med Imaging Date: 2010-07-19 Impact factor: 10.048
Authors: Nathanael Kuo; Anton Deguet; Danny Y Song; Everette C Burdette; Jerry L Prince; Junghoon Lee Journal: Med Eng Phys Date: 2011-07-29 Impact factor: 2.242
Authors: Ehsan Dehghan; Junghoon Lee; Pascal Fallavollita; Nathanael Kuo; Anton Deguet; Yi Le; E Clif Burdette; Danny Y Song; Jerry L Prince; Gabor Fichtinger Journal: Med Image Anal Date: 2012-06-16 Impact factor: 8.545