| bibtype |
J -
Journal Article
|
| ARLID |
0313710 |
| utime |
20240103190549.9 |
| mtime |
20090326235959.9 |
| WOS |
000258739700009 |
| DOI |
10.1016/j.compmedimag.2008.05.005 |
| title
(primary) (eng) |
Medical image analysis of 3D CT images based on extensions of Haralick texture features |
| specification |
|
| serial |
| ARLID |
cav_un_epca*0252561 |
| ISSN |
0895-6111 |
| title
|
Computerized Medical Imaging and Graphics |
| volume_id |
32 |
| volume |
6 (2008) |
| page_num |
513-520 |
| publisher |
|
|
| title
(cze) |
Analýza trojrozměrných CT medicínských obrázků pomocí rozšíření Haralickových texturních příznaků |
| keyword |
image segmentation |
| keyword |
Gaussian mixture model |
| keyword |
3D image analysis |
| author
(primary) |
| ARLID |
cav_un_auth*0101211 |
| name1 |
Tesař |
| name2 |
Ludvík |
| institution |
UTIA-B |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0230998 |
| name1 |
Shimizu |
| name2 |
A. |
| country |
JP |
|
| author
|
| ARLID |
cav_un_auth*0015541 |
| name1 |
Smutek |
| name2 |
D. |
| country |
CZ |
|
| author
|
| ARLID |
cav_un_auth*0230999 |
| name1 |
Kobatake |
| name2 |
H. |
| country |
JP |
|
| author
|
| ARLID |
cav_un_auth*0243177 |
| name1 |
Nawano |
| name2 |
S. |
| country |
JP |
|
| source |
|
| cas_special |
| project |
| project_id |
1ET101050403 |
| agency |
GA AV ČR |
| ARLID |
cav_un_auth*0001930 |
|
| project |
| project_id |
1M0572 |
| agency |
GA MŠk |
| ARLID |
cav_un_auth*0001814 |
|
| research |
CEZ:AV0Z10750506 |
| abstract
(eng) |
Texture-based segmentation of 3D CT images is adressed. The extension of Haralick 2D texture features to the 3D domain was studied. The co-occurrence matrix was calculated separately for each voxel in the image, using the co-occurrences of all voxels in a small cubic region around the voxel. The segmentation method used was model-based with a Gaussian Mixture Model. Evaluation of the proposed approach was performed using a set of 3D abdominal CT images. Statistical improvement of segmentation with 3D texture features was observed as opposed to the case without those features. |
| abstract
(cze) |
Tato práce se zabývá segmentací 3D CT medicínských obrázků. Byla použita extenze Haralickových dvourozměrných texturních příznaků na třetí dimenzi. Ko-okurenční matice se počítá pro každí voxel zvlášt, na základě ko-okurencí v jeho okolí. Segmentace se provádí pomocí Gaussovského směsového modelu. Vyhodnocení metody bylo provedeno s použitím abdominálních 3D CT obrázků. Bylo pozorováno zlepšení segmentace pomocí 3D texturních příznaků oproti segmenaci bez nich. |
| reportyear |
2009 |
| RIV |
IN |
| permalink |
http://hdl.handle.net/11104/0164445 |
| mrcbT16-f |
1.363 |
| mrcbT16-g |
0.095 |
| mrcbT16-h |
6.8 |
| mrcbT16-i |
0.00194 |
| mrcbT16-j |
0.303 |
| mrcbT16-k |
929 |
| mrcbT16-l |
74 |
| mrcbT16-q |
40 |
| mrcbT16-s |
0.508 |
| mrcbT16-y |
28.39 |
| mrcbT16-x |
1.67 |
| arlyear |
2008 |
| mrcbU34 |
000258739700009 WOS |
| mrcbU63 |
cav_un_epca*0252561 Computerized Medical Imaging and Graphics 0895-6111 1879-0771 Roč. 32 č. 6 2008 513 520 Elsevier |
|