Segmentation and analysis of the glomerular basement membrane using the split and merge method

Certain renal diseases are characterized by alterations in the thickness of the glomerular basement membrane (GBM), as visualized by images of biopsy samples obtained by using a transmission electron microscope (TEM). Abnormal thinning, thickening, or variation in thickness can occur in familial hematuria, diabetes mellitus, and Alport syndrome, respectively. We propose image processing methods for the segmentation and measurement of the GBM. The methods include the split and merge algorithm, morphological image processing, skeletonization, and statistical analysis of the width of the GBM. The proposed methods were applied to 34 TEM images of six patients. The mean and standard deviation of normal GBM were estimated to be 368 ± 177 nm; those of thin GBMs associated with familial hematuria were 216 ± 95 nm; and those of thick GBM due to diabetic nephropathy were 1094 ± 361 nm. Comparative analysis of the results of image processing with manual measurements by an experienced renal pathologist indicated low error in the range of 12 ± 9 nm.