Tunable Tensor Voting for Regularizing Punctate Patterns of Membrane-Bound Protein Signals

Membrane-bound protein, expressed in the basal-lateral region, is heterogeneous and an important endpoint for understanding biological processes. At the optical resolution, membrane-bound protein can be visualized as being diffused (e.g., E-cadherin), punctate (e.g., connexin), or simultaneously diffused and punctate as a result of sample preparation or conditioning. Furthermore, there is a significant amount of heterogeneity as a result of technical and biological variations. This paper aims at enhancing membrane-bound proteins that are expressed between epithelial cells so that quantitative analysis can be enabled on a cell-by-cell basis. We propose a method to detect and enhance membrane-bound protein signal from noisy images. More precisely, we build upon the tensor voting framework in order to produce an efficient method to detect and refine perceptually interesting linear structures in images. The novelty of the proposed method is in its iterative tuning of the tensor voting ...

• Type: Conference
• Year: 2009
• Where: ISBI
• Authors: Leandro A. Loss, George Bebis, Bahram Parvin
• Keywords: ISBI 2009, Medical Imaging, Membrane-bound Protein, Membrane-bound Protein Signals, Tensor Voting