TY - JOUR
T1 - Accurate coronary centerline extraction, caliber estimation, and catheter detection in angiographies
AU - Hernandez-Vela, Antonio
AU - Gatta, Carlo
AU - Escalera, Sergio
AU - Igual, Laura
AU - Martin-Yuste, Victoria
AU - Sabate, Manel
AU - Radeva, Petia
N1 - Funding Information:
Manuscript received January 12, 2012; revised May 26, 2012, August 2, 2012, and September 14, 2012; accepted September 16, 2012. Date of current version November 16, 2012. This work was supported in part by the Project La Marató de TV3 082131, Project TIN2009-14404-C02, and Project CONSOLIDER-INGENIO CSD 2007-00018. The work of C. Gatta was supported by a “Beatriude Pinos” grant and by a “Ramon y Cajal” contract. The work of A. Hernandez-Vela was supported by an Formación de Personal Uni-versitario fellowship from the Spanish government.
PY - 2012
Y1 - 2012
N2 - Segmentation of coronary arteries in X-ray angiography is a fundamental tool to evaluate arterial diseases and choose proper coronary treatment. The accurate segmentation of coronary arteries has become an important topic for the registration of different modalities, which allows physicians rapid access to different medical imaging information from computed tomography (CT) scans or magnetic resonance imaging (MRI). In this paper, we propose an accurate fully automatic algorithm based on Graph-cuts for vessel centerline extraction, caliber estimation, and catheter detection. Vesselness, geodesic paths, and a new multiscale edgeness map are combined to customize the Graph-cuts approach to the segmentation of tubular structures, by means of a global optimization of the Graph-cuts energy function. Moreover, a novel supervised learning methodology that integrates local and contextual information is proposed for automatic catheter detection. We evaluate the method performance on three datasets coming from different imaging systems. The method performs as good as the expert observer with respect to centerline detection and caliber estimation. Moreover, the method discriminates between arteries and catheter with an accuracy of 96.5, sensitivity of 72, and precision of 97.4.
AB - Segmentation of coronary arteries in X-ray angiography is a fundamental tool to evaluate arterial diseases and choose proper coronary treatment. The accurate segmentation of coronary arteries has become an important topic for the registration of different modalities, which allows physicians rapid access to different medical imaging information from computed tomography (CT) scans or magnetic resonance imaging (MRI). In this paper, we propose an accurate fully automatic algorithm based on Graph-cuts for vessel centerline extraction, caliber estimation, and catheter detection. Vesselness, geodesic paths, and a new multiscale edgeness map are combined to customize the Graph-cuts approach to the segmentation of tubular structures, by means of a global optimization of the Graph-cuts energy function. Moreover, a novel supervised learning methodology that integrates local and contextual information is proposed for automatic catheter detection. We evaluate the method performance on three datasets coming from different imaging systems. The method performs as good as the expert observer with respect to centerline detection and caliber estimation. Moreover, the method discriminates between arteries and catheter with an accuracy of 96.5, sensitivity of 72, and precision of 97.4.
KW - Angiography
KW - caliber
KW - catheter
KW - centerline (CL)
KW - Graph-cuts (GC)
KW - quantitative coronary angiography (QCA)
KW - segmentation
KW - X-Ray
UR - http://www.scopus.com/inward/record.url?scp=84871032438&partnerID=8YFLogxK
U2 - 10.1109/TITB.2012.2220781
DO - 10.1109/TITB.2012.2220781
M3 - Journal article
C2 - 23033436
AN - SCOPUS:84871032438
SN - 1089-7771
VL - 16
SP - 1332
EP - 1340
JO - IEEE Transactions on Information Technology in Biomedicine
JF - IEEE Transactions on Information Technology in Biomedicine
IS - 6
M1 - 6316192
ER -