Abstract
An algorithm for the detection and measurement of the glomerular basement membrane in kidney electron micrographs by image analysis techniques is described. Starting from a user-specified point, local features within a small window are computed to give a feature score. Feature scores for adjacent neighbourhoods are also determined, and windows that satisfy similarity criteria are linked to produce the centerline of the membrane. A region-growing process completes the segmentation procedure. The adaptive and local nature of the algorithm ensures successful segmentation despite the complex and variable characteristics of the micrograph image.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abmayr W, Mannweiler E, Oesterle D, Deml E (1987) Segmentation of scenes in tissue sections. Anal Quant Cytol Histol 9:190–196
Autio-Harmainen H, Rapola J (1983) The thickness of the glomerular basement membrane in congenital nephrotic syndrome of the Finnish type. Nephron 34:48–50
Basta-Jovanovic G, Venkataseshan VS, Gil J, Kim DU, Dikman SH, Churg J (1990) Morphometric analysis of glomerular basement membranes (GBM) in thin basement GBM disease (TBMD). Clin Nephrol 33:110–114
Carlson EC, Surerus KK, Hinds D (1986) Ultrastructural analysis of major basement membrane types in rhesus monkeyMacaca mulatta acellular renal cortex. Acta Anat 125:14–22
Colchester ACF, Ritchings RT, Kodikara ND (1990) Image segmentation using maximum gradient profiles orthogonal to edges. Image Vision Comput 8:211–217
Coleman M, David W, Haynes G, Dimopoulos P, Barratt LJ, Jarvis LR (1986) Glomerular basement membrane abnormalities associated with apparently idiopathic hematuria. Hum Pathol 17:1022–1030
Cuyck PJH van, Gerbrands JJ, Reiber JHC (1988) Automated centerline tracing in coronary angiograms. In: Gelsema ES, Kanal LN (eds) Pattern Recogn Artificial Intelligence. Elsevier, New York, 169–183
Eichel PH, Delp EJ, Koral K, Buda AJ (1988) A method for a fully automatic definition of coronary arterial edges from cineangiograms. IEEE Trans Med Imag MI-7:313–320
Liedtke CE, Gahm T, Kappei F, Aeikens B (1987) Segmentation of microscopic cell scenes. Anal Quant Cytol Histol 9:197–211
Marion M, Carlson EC (1989) Ultrastructural analyses of acellular glomerular basement membranes and mesangial matrix in a spontaneously diabetic rhesus monkey. Acta Anat 135:119–128
O'Gorman L, Sanderson AC, Preston K Jr (1985) System for automated liver tissue image analysis: methods and results. IEEE Trans Biomed Eng BME-32:696–706
Ong SH, Nickolls PM (1986) Techniques in automated cell classification. Australas Phys Eng Sci Med 9:82–92
Saxena S, Davies DJ, Kirsner RLG (1990) Thin basement membranes in minimally abnormal glomeruli. J Clin Pathol 43:32–38
Sun Y (1989) Automated identification of vessel contours in coronary arteriograms by an adaptive tracking algorithm. IEEE Trans Med Imag 8:78–87
Tiebosch ATMG, Frederik PM, Breda-Vriesman PJC van, Mooy JMV, Rie H van, Wiel TWM van de, Wolters J, Zeppenfeldt E (1989) Thin-basement-membrane nephropathy in adults with persistent hematuria. N Eng J Med 320:14–18
Yamada H, Merritt C, Kasvand T (1988) Recognition of kidney glomerulus by dynamic programming matching method. IEEE Trans Pattern Anal Machine Intelligence PAMI-10:731–737
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ong, S.H., Giam, S.T., Jayasooriah et al. Adaptive window-based tracking for the detection of membrane structures in kidney electron micrographs. Machine Vis. Apps. 6, 215–223 (1993). https://doi.org/10.1007/BF01212300
Issue Date:
DOI: https://doi.org/10.1007/BF01212300