Parallel Double Snakes. Application to the segmentation of retinal layers in 2D-OCT for pathological subjects

被引:28
作者
Rossant, Florence [1 ]
Bloch, Isabelle [2 ]
Ghorbel, Itebeddine [1 ,2 ,3 ]
Paques, Michel [4 ]
机构
[1] ISEP, Paris, France
[2] Telecom ParisTech, CNRS LTCI, Inst Mines Telecom, Paris, France
[3] FOVEA Pharmaceut, Paris, France
[4] Ctr Hosp Natl Quinze Vingts, Clin Invest Ctr 1423, Paris, France
关键词
Parametric active contours; Double snakes; Approximate parallelism; Optical coherence tomography; Retinal layers; ACTIVE CONTOURS;
D O I
10.1016/j.patcog.2015.06.009
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In order to segment elongated structures, we propose a new approach for integrating an approximate parallelism constraint in deformable models. The proposed Parallel Double Snakes evolve simultaneously two contours, in order to minimize an energy functional which attracts these contours towards high image gradients and enforces the approximate parallelism between them by controlling their distance to a centerline under regularity constraints of this line. The proposed approach is applied on retina images, for segmenting retinal layers in optical coherence tomography images of pathological subjects (and it applies to healthy subjects as well). Results are evaluated by comparing with manual segmentations for three retinal layers, and provide a similarity index above 0.87, sensitivity between 0.85 and 0.93, and specificity between 0.84 and 0.94. These results are within the range of intra and inter-expert variability. Moreover, quantitative studies demonstrate that, in our application, our Parallel Double Snake (PDS) model outperforms other parametric active contour algorithms integrating parallelism information. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:3857 / 3870
页数:14
相关论文
共 30 条
  • [1] An Active Contour Model for Segmenting and Measuring Retinal Vessels
    Al-Diri, Bashir
    Hunter, Andrew
    Steel, David
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2009, 28 (09) : 1488 - 1497
  • [2] Active contours without edges
    Chan, TF
    Vese, LA
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2001, 10 (02) : 266 - 277
  • [3] Three-Dimensional Segmentation of Fluid-Associated Abnormalities in Retinal OCT: Probability Constrained Graph-Search-Graph-Cut
    Chen, Xinjian
    Niemeijer, Meindert
    Zhang, Li
    Lee, Kyungmoo
    Abramoff, Michael D.
    Sonka, Milan
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2012, 31 (08) : 1521 - 1531
  • [4] Intraretinal layer segmentation of macular optical coherence tomography images using optimal 3-D graph search
    Garvin, Mona K.
    Abramoff, Michael D.
    Kardon, Randy
    Russell, Stephen R.
    Wu, Xiaodong
    Sonka, Milan
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2008, 27 (10) : 1495 - 1505
  • [5] STOCHASTIC RELAXATION, GIBBS DISTRIBUTIONS, AND THE BAYESIAN RESTORATION OF IMAGES
    GEMAN, S
    GEMAN, D
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1984, 6 (06) : 721 - 741
  • [6] Ghorbel I., 2014, INT M GERM SOC CELL
  • [7] Ghorbel I, 2011, IEEE IMAGE PROC, P445, DOI 10.1109/ICIP.2011.6116546
  • [8] Automated segmentation of macular layers in OCT images and quantitative evaluation of performances
    Ghorbel, Itebeddine
    Rossant, Florence
    Bloch, Isabelle
    Tick, Sarah
    Paques, Michel
    [J]. PATTERN RECOGNITION, 2011, 44 (08) : 1590 - 1603
  • [9] Hacker M, 2007, LECT NOTES COMPUT SC, V4584, P607
  • [10] Retinitis pigmentosa
    Hartong, Dyonne T.
    Berson, Eliot L.
    Dryja, Thaddeus P.
    [J]. LANCET, 2006, 368 (9549) : 1795 - 1809