new approach to the segmentation of 3D CT images is proposed in an attempt to provide texture-based segmentation of organs or disease diagnosis. 3D extension of Haralick texture features was studied calculating co-occurrences of all voxels in a small cubic region around the voxel. RESULTS: For verification, the proposed method was tested on a set of abdominal 3D volumes of patients. Statistically, the improvement in segmentation was significant for most of the organs considered herein. CONCLUSIONS: The proposed method has potential application in medical image segmentation, including diagnosis of diseases.

Institute of Information Theory and Automation Czech Academy of Sciences Department of Adaptive Systems Pod Vodarenskou Vezi 4 18208 Praha 8 Czech Republic

000      

01955naa 2200385 a 4500

001      

bmc11006407

003      

CZ-PrNML

005      

20130617110340.0

008      

110401s2008 xxu e eng||

009      

AR

040    __

$a ABA008 $b cze $c ABA008 $d ABA008 $e AACR2

041    0_

$a eng

044    __

$a xxu

100    1_

$a Tesař, Ludvík $7 xx0129530

245    10

$a Medical image analysis of 3D CT images based on extension of Haralick texture features / $c L Tesar, A Shimizu, D Smutek, H Kobatake, S Nawano

314    __

$a Institute of Information Theory and Automation, Czech Academy of Sciences, Department of Adaptive Systems, Pod Vodarenskou Vezi 4, 18208 Praha 8, Czech Republic. tesar@utia.cas.cz

520    9_

$a new approach to the segmentation of 3D CT images is proposed in an attempt to provide texture-based segmentation of organs or disease diagnosis. 3D extension of Haralick texture features was studied calculating co-occurrences of all voxels in a small cubic region around the voxel. RESULTS: For verification, the proposed method was tested on a set of abdominal 3D volumes of patients. Statistically, the improvement in segmentation was significant for most of the organs considered herein. CONCLUSIONS: The proposed method has potential application in medical image segmentation, including diagnosis of diseases.

590    __

$a bohemika - dle Pubmed

650    _2

$a algoritmy $7 D000465

650    _2

$a umělá inteligence $7 D001185

650    _2

$a lidé $7 D006801

650    _2

$a zobrazování trojrozměrné $x metody $7 D021621

650    _2

$a rozpoznávání automatizované $x metody $7 D010363

650    _2

$a vylepšení rentgenového snímku $x metody $7 D011856

650    _2

$a rentgenový obraz - interpretace počítačová $x metody $7 D011857

650    _2

$a rentgendiagnostika břicha $x metody $7 D011860

650    _2

$a reprodukovatelnost výsledků $7 D015203

650    _2

$a senzitivita a specificita $7 D012680

650    _2

$a počítačová rentgenová tomografie $x metody $7 D014057

655    _2

$a práce podpořená grantem $7 D013485

700    1_

$a Shimizu, Akinobu

700    1_

$a Smutek, Daniel, $d 1974- $7 xx0018677

700    1_

$a Kobatake, Hidefumi

700    1_

$a Nawano, Shigeru

773    0_

$t Computerized Medical Imaging & Graphics $g Roč. 32, č. 6 (2008), s. 513-520 $x 0895-6111 $w MED00001216

910    __

$a ABA008 $b x $y 2

990    __

$a 20110414104250 $b ABA008

991    __

$a 20130617110728 $b ABA008

999    __

$a ok $b bmc $g 833999 $s 698508

BAS    __

$a 3

BMC    __

$a 2008 $b 32 $c 6 $d 513-520 $i 0895-6111 $m Computerized medical imaging and graphics $n Comput Med Imaging Graph $x MED00001216

LZP    __

$a 2011-1B09/jjme