Rib suppression in radiographic images
AssigneeCarestream Health, Inc.
InventorsZhimin Huo, Fan Xu, Shoupu Chen, Qinran Chen
Life of this patent
Estimating the term…
Abstract
A method for rib suppression in a chest x-ray image detects and labels one or more ribs in a region of interest and detects rib edges of the one or more detected ribs. Cross rib profiles are generated along the detected ribs. The original x-ray image is conditioned according to at least one of the detected rib edge and cross rib profiles. The conditioned x-ray image can be stored, displayed, or transmitted.
Claims20
A method for rib suppression in a chest x-ray image, comprising:
- detecting one or more ribs in a region of interest in the chest x-ray image;
- applying a pixel classification to the one or more detected ribs in the region of interest;
- using the pixel classification, labeling the one or more detected ribs in the region of interest;
- detecting rib edges of the one or more detected ribs;
- generating cross rib profiles along the detected rib edges;
- conditioning the chest x-ray image according to at least one of the detected rib edges and cross rib profiles;
- and
- storing, displaying, or transmitting the conditioned chest x-ray image.
A method for rib suppression in a chest x-ray image, comprising:
- segmenting one or more lung regions in the chest image;
- determining one or more rib features for each pixel within the one or more segmented lung regions;
- extracting a medial axis from at least one of the one or more determined rib features and iteratively segmenting one or more rib edges from the at least one or more rib features according to the extracted medial axis and according to an anatomical model;
- forming a conditioned image by combining the one or more segmented rib edges with the original x-ray image;
- and
- storing, displaying, or transmitting the conditioned image.
A method for rib detection in a chest x-ray image, executed at least in part by a computer system, comprising:
- detecting pixels for one or more ribs in a region of interest;
- labeling one or more of the detected ribs as individual ribs by grouping the pixels to generate detected ribs and removing one or more false positive pixels from the detected pixels;
- detecting one or more rib edges of the detected ribs by adjusting one or more edge segments;
- and
- storing, displaying, or transmitting the detected results.
Dependencies are inferred from the claim text.