Automatic Bifurcation Detection in Coronary IVUS Sequences

被引:23
作者
Alberti, Marina [1 ,2 ]
Balocco, Simone [1 ,2 ]
Gatta, Carlo [1 ,2 ]
Ciompi, Francesco [1 ,2 ]
Pujol, Oriol [1 ,2 ]
Silva, Joana [3 ]
Carrillo, Xavier [4 ]
Radeva, Petia [1 ,2 ]
机构
[1] Univ Barcelona, Dept Matemat Aplicada & Anal, Barcelona 08007, Spain
[2] Comp Vis Ctr, Barcelona 08193, Spain
[3] Coimbras Hosp Ctr, P-3041801 Coimbra, Portugal
[4] Univ Hosp Germans Trias & Pujol, Badalona 08916, Spain
关键词
Contextual classification; coronary bifurcations; intravascular ultrasound (IVUS); texture analysis; INTRAVASCULAR ULTRASOUND; IN-VIVO; SEGMENTATION; WALL;
D O I
10.1109/TBME.2011.2181372
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In this paper, we present a fully automatic method which identifies every bifurcation in an intravascular ultrasound (IVUS) sequence, the corresponding frames, the angular orientation with respect to the IVUS acquisition, and the extension. This goal is reached using a two-level classification scheme: first, a classifier is applied to a set of textural features extracted from each image of a sequence. A comparison among three state-of-the-art discriminative classifiers (AdaBoost, random forest, and support vector machine) is performed to identify the most suitable method for the branching detection task. Second, the results are improved by exploiting contextual information using a multiscale stacked sequential learning scheme. The results are then successively refined using a-priori information about branching dimensions and geometry. The proposed approach provides a robust tool for the quick review of pullback sequences, facilitating the evaluation of the lesion at bifurcation sites. The proposed method reaches an F-Measure score of 86.35%, while the F-Measure scores for inter- and intraobserver variability are 71.63% and 76.18%, respectively. The obtained results are positive. Especially, considering the branching detection task is very challenging, due to high variability in bifurcation dimensions and appearance.
引用
收藏
页码:1022 / 1031
页数:10
相关论文
共 35 条
[1]  
Alberti M, 2011, LECT NOTES COMPUT SC, V6669, P126
[2]   FLOW PATTERNS AND SPATIAL-DISTRIBUTION OF ATHEROSCLEROTIC LESIONS IN HUMAN CORONARY-ARTERIES [J].
ASAKURA, T ;
KARINO, T .
CIRCULATION RESEARCH, 1990, 66 (04) :1045-1066
[3]   Multi-agent segmentation of IVUS images [J].
Bovenkamp, EGP ;
Dijkstra, J ;
Bosch, JG ;
Reiber, JHC .
PATTERN RECOGNITION, 2004, 37 (04) :647-663
[4]   MULTICHANNEL TEXTURE ANALYSIS USING LOCALIZED SPATIAL FILTERS [J].
BOVIK, AC ;
CLARK, M ;
GEISLER, WS .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (01) :55-73
[5]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[6]  
Bruining N., 1996, P INT C IEEE ENG MED, P664
[7]   Using reconstructed IVUS images for coronary plaque classification [J].
Caballero, Karla L. ;
Barajas, Joel ;
Pujol, Oriol ;
Rodriguez, Oriol ;
Radeva, Petia .
2007 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-16, 2007, :2167-2170
[8]  
Ciompi F., 2010, RECONSTRUCTION ANAL, P223
[9]   Fusing in-vitro and in-vivo intravascular ultrasound data for plaque characterization [J].
Ciompi, Francesco ;
Pujol, Oriol ;
Gatta, Carlo ;
Rodriguez-Leor, Oriol ;
Mauri-Ferre, Josepa ;
Radeva, Petia .
INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING, 2010, 26 (07) :763-779
[10]  
Cortes C., 1995, Machine Learning, V297, P273, DOI [DOI 10.1007/BF00994018, DOI 10.1023/A:1022627411411]