Segmentation of cell nuclei in images of renal biopsy samples

Diagnosis and monitoring of kidney diseases and transplants is supported by microscopic analysis of needle-core biopsy samples. The current methods of analysis are affected by inconsistencies, bias, and inaccuracies. We propose and evaluate image processing methods for automatic segmentation of cell nuclei in digital images of renal biopsy samples. The methods evaluated include automatic thresholding, adaptive thresholding, and morphological granulometry. The results are compared to annotations made by an expert pathologist of more than 1500 cells in 18 images from different patients. The three methods provided true-positive ratios in the range 0.80 to 0.93.

[1]  H. E. Hansen,et al.  The Banff 97 working classification of renal allograft pathology. , 1999, Kidney international.

[2]  A. Michael,et al.  Interstitial nephritis associated with cytomegalovirus infection. , 1985, Kidney international.

[3]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[4]  G. Matheron.  Random Sets and Integral Geometry , 1976 .

[5]  Peter Meer,et al.  Unsupervised segmentation based on robust estimation and color active contour models , 2005, IEEE Transactions on Information Technology in Biomedicine.

[6]  Rangaraj M. Rangayyan,et al.  Segmentation of the effective area of images of renal biopsy samples , 2009, 2009 Canadian Conference on Electrical and Computer Engineering.

[7]  A. Schwarz,et al.  Infiltrates in Protocol Biopsies from Renal Allografts , 2007, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[8]  N. Marcussen,et al.  Kidney allograft with a lymphocytic infiltrate: acute rejection, posttransplantation lymphoproliferative disorder, neither, or both entities? , 1997, American journal of kidney diseases : the official journal of the National Kidney Foundation.