Iterative Tensor Voting for Perceptual Grouping of Ill-Defined Curvilinear Structures

• Published in: IEEE transactions on medical imaging 2011-08, Vol.30 (8), p.1503-1513
• Main Authors: Loss, L. A., Bebis, G., Parvin, B.
• Format: Article
• Language: English
• Subjects: Adherens junctions; Adherens Junctions - ultrastructure; Cell Wall - chemistry; curvilinear structures; Humans; Image Processing, Computer-Assisted - methods; Image segmentation; Iterative methods; iterative tensor voting (ITV); Junctions; Kernel; Microscopy, Fluorescence - methods; Pattern Recognition, Automated - methods; perceptual grouping; Pixel; Proteins; Reproducibility of Results; Surfaces; Tensile stress
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2011.2129526

In this paper, a novel approach is proposed for perceptual grouping and localization of ill-defined curvilinear structures. Our approach builds upon the tensor voting and the iterative voting frameworks. Its efficacy lies on iterative refinements of curvilinear structures by gradually shifting from an exploratory to an exploitative mode. Such a mode shifting is achieved by reducing the aperture of the tensor voting fields, which is shown to improve curve grouping and inference by enhancing the concentration of the votes over promising, salient structures. The proposed technique is validated on delineating adherens junctions that are imaged through fluorescence microscopy. However, the method is also applicable for screening other organisms based on characteristics of their cell wall structures. Adherens junctions maintain tissue structural integrity and cell-cell interactions. Visually, they exhibit fibrous patterns that may be diffused, heterogeneous in fluorescence intensity, or punctate and frequently perceptual. Besides the application to real data, the proposed method is compared to prior methods on synthetic and annotated real data, showing high precision rates.