Abstract | ||
---|---|---|
Tissue core de-arraying is one of the most important steps in tissue microarray (TMA) image analysis. However, few solutions and mathematical frameworks are available. This paper presents a robust TMA de-arraying method adapted for digital images from classical optical and new fluorescent devices. The proposed algorithm is composed of three modules: (a) detection, (b) segmentation, and (c) array indexing. The detection of TMA cores is performed by local adaptive thresholding of isotropic wavelet transform coefficients. The segmentation component uses parametric ellipse to delineate the boundaries of potential tissue cores. Array indices of each core are computed by using thin-plate splines to estimate the deformation of the deposited core grid. Our method is appropriate for non-linear deformation and is able to quantify the deformation of TMA grids when compared to existing algorithms. |
Year | Venue | Keywords |
---|---|---|
2015 | 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI) | Tissue microarray, TMA de-arraying, thin-plate splines, isotropic wavelet transform, parametric ellipse-based segmentation |
Field | DocType | ISSN |
Computer vision,Thin plate spline,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Image segmentation,Digital image,Parametric statistics,Artificial intelligence,Thresholding,Wavelet transform | Conference | 1945-7928 |
Citations | PageRank | References |
1 | 0.36 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hoai-Nam Nguyen | 1 | 1 | 0.36 |
Charles Kervrann | 2 | 934 | 67.36 |
Cyril Cauchois | 3 | 1 | 1.03 |
Vincent Paveau | 4 | 1 | 1.03 |