Abstract | ||
---|---|---|
We have been developing, a computer-aided diagnosis (CAD) scheme for automatically recognizing human tissue and organ regions from high-resolution torso CT images. We show some initial results for extracting skin, soft-tissue and skeleton regions. 139 patient cases of torso CT images (male: 92, female: 47, age: 12-88) were used in this study. Each case was imaged with a common protocol (120kV/320mA) and covered the whole torso with 0.63 (mm) isotopic spatial resolution and 12 (bits) density resolution. A gray-level thresholding based procedure was applied to separate the human body from background. The density and distance features to body surface were used to determine skin, and separate soft-tissue from the other regions. A 3-D region growing based method was used to extract skeleton. We applied this system to 139 cases and found that the skin, soft-tissue and skeleton regions were recognized correctly for 93% patient cases. The accuracy of segmentation results was acceptable by evaluating the results slice by slice. This scheme will be included in a CAD system for detecting and diagnosing the abnormal lesions in multi-slice torso CT images. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1117/12.534843 | Proceedings of SPIE |
Keywords | Field | DocType |
mult-slice torso CT images,3-D image processing,organ region segmentations,CAD | Torso,Computer vision,Segmentation,Computer science,Computer-aided diagnosis,Image processing,Region growing,Artificial intelligence,Thresholding,Skeleton (computer programming),Image resolution | Conference |
Volume | ISSN | Citations |
5370 | 0277-786X | 3 |
PageRank | References | Authors |
1.89 | 3 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiangrong Zhou | 1 | 325 | 45.53 |
Takeshi Hara | 2 | 639 | 79.10 |
Hiroshi Fujita | 3 | 118 | 24.65 |
Ryujiro Yokoyama | 4 | 123 | 18.40 |
Takuji Kiryu | 5 | 41 | 4.55 |
Hiroaki Hoshi | 6 | 106 | 18.21 |