• Je něco špatně v tomto záznamu ?

Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration

J. Jan, J. Odstrcilik, J. Gazarek, R. Kolar,

. 2012 ; 36 (6) : 431-41.

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc13000776

An automatic method of segmenting the retinal vessel tree and estimating status of retinal neural fibre layer (NFL) from high resolution fundus camera images is presented. First, reliable blood vessel segmentation, using 2D directional matched filtering, enables to remove areas occluded by blood vessels thus leaving remaining retinal area available to the following NFL detection. The local existence of rather faint and hardly visible NFL is detected by combining several newly designed local textural features, sensitive to subtle NFL characteristics, into feature vectors submitted to a trained neural-network classifier. Obtained binary retinal maps of NFL distribution show a good agreement with both medical expert evaluations and quantitative results obtained by optical coherence tomography.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc13000776
003      
CZ-PrNML
005      
20130109112443.0
007      
ta
008      
130108s2012 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.compmedimag.2012.04.006 $2 doi
035    __
$a (PubMed)22640597
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Jan, J $u Department of Biomedical Engineering FEEC, Brno University of Technology, Kolejní 4, 61200 Brno, Czech Republic. jan@feec.vutbr.cz
245    10
$a Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration / $c J. Jan, J. Odstrcilik, J. Gazarek, R. Kolar,
520    9_
$a An automatic method of segmenting the retinal vessel tree and estimating status of retinal neural fibre layer (NFL) from high resolution fundus camera images is presented. First, reliable blood vessel segmentation, using 2D directional matched filtering, enables to remove areas occluded by blood vessels thus leaving remaining retinal area available to the following NFL detection. The local existence of rather faint and hardly visible NFL is detected by combining several newly designed local textural features, sensitive to subtle NFL characteristics, into feature vectors submitted to a trained neural-network classifier. Obtained binary retinal maps of NFL distribution show a good agreement with both medical expert evaluations and quantitative results obtained by optical coherence tomography.
650    _2
$a fluoresceinová angiografie $x metody $7 D005451
650    _2
$a lidé $7 D006801
650    _2
$a interpretace obrazu počítačem $x metody $7 D007090
650    _2
$a nervová síť $x patologie $7 D009415
650    _2
$a nemoci zrakového nervu $x patologie $7 D009901
650    _2
$a rozpoznávání automatizované $x metody $7 D010363
650    _2
$a reprodukovatelnost výsledků $7 D015203
650    _2
$a retinální cévy $x patologie $7 D012171
650    _2
$a retinoskopie $x metody $7 D042262
650    _2
$a senzitivita a specificita $7 D012680
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Odstrcilik, J
700    1_
$a Gazarek, J
700    1_
$a Kolar, R
773    0_
$w MED00001216 $t Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society $x 1879-0771 $g Roč. 36, č. 6 (2012), s. 431-41
856    41
$u https://pubmed.ncbi.nlm.nih.gov/22640597 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20130108 $b ABA008
991    __
$a 20130109112548 $b ABA008
999    __
$a ok $b bmc $g 963558 $s 798940
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2012 $b 36 $c 6 $d 431-41 $i 1879-0771 $m Computerized medical imaging and graphics $n Comput Med Imaging Graph $x MED00001216
LZP    __
$a Pubmed-20130108

Najít záznam

Citační ukazatele

    Možnosti archivace