摘要 |
A method for segmenting digitized images includes providing (11) a training set comprising a plurality of digitized whole-body images, providing labels (12) on anatomical landmarks in each image of said training set, aligning (13) each said training set image, generating (14) positive and negative training examples for each landmark by cropping the aligned training volumes into one or more cropping windows of different spatial scales, and using said positive and negative examples to train (15) a detector for each landmark at one or more spatial scales ranging from a coarse resolution to a fine resolution, wherein the spatial relationship between a cropping windows of a coarse resolution detector and a fine resolution detector is recorded. |
申请人 |
SIEMENS MEDICAL SOLUTIONS USA, INC.;HUANG, XIAOLEI;ZHOU, XIANG;JEREBKO, ANNA;KRISHNAN, ARUN;GUAN, HAIYING;KUBOTA, TOSHIRO;POTESIL, VACLAV |
发明人 |
HUANG, XIAOLEI;ZHOU, XIANG;JEREBKO, ANNA;KRISHNAN, ARUN;GUAN, HAIYING;KUBOTA, TOSHIRO;POTESIL, VACLAV |