×

Automatic segmentation of pathological glomerular basement membrane in transmission electron microscopy images with random forest stacks. (English) Zbl 1423.92140

Summary: Pathological classification through transmission electron microscopy (TEM) is essential for the diagnosis of certain nephropathy, and the changes of thickness in glomerular basement membrane (GBM) and presence of immune complex deposits in GBM are often used as diagnostic criteria. The automatic segmentation of the GBM on TEM images by computerized technology can provide clinicians with clear information about glomerular ultrastructural lesions. The GBM region on the TEM image is not only complicated and changeable in shape but also has a low contrast and wide distribution of grayscale. Consequently, extracting image features and obtaining excellent segmentation results are difficult. To address this problem, we introduce a random forest- (RF-) based machine learning method, namely, RF stacks (RFS), to realize automatic segmentation. Specifically, this work proposes a two-level integrated RFS that is more complicated than a one-level integrated RF to improve accuracy and generalization performance. The integrated strategies include training integration and testing integration. Training integration can derive a full-view RFS\(_1\) by simultaneously sampling several images of different grayscale ranges in the train phase. Testing integration can derive a zoom-view RFS\(_2\) by separately sampling the images of different grayscale ranges and integrating the results in the test phase. Experimental results illustrate that the proposed RFS can be used to automatically segment different morphologies and gray-level basement membranes. Future study on GBM thickness measurement and deposit identification will be based on this work.

MSC:

92C55 Biomedical imaging and signal processing
92-08 Computational methods for problems pertaining to biology
68T05 Learning and adaptive systems in artificial intelligence

Software:

WEKA
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Zhou, F.-D.; Zhao, M.-H.; Zou, W.-Z., The changing spectrum of primary glomerular diseases within 15 years: a survey of 3331 patients in a single Chinese centre, Nephrology Dialysis Transplantation, 24, 3, 870-876 (2009) · doi:10.1093/ndt/gfn554
[2] Haas, M., A reevaluation of routine electron microscopy in the examination of native renal biopsies, Journal of the American Society of Nephrology, 8, 1, 70-76 (1997)
[3] Santostefano, M.; Zanchelliet, F.; Zaccaria, A., The ultrastructural basis of renal pathology in monoclonal gammopathies, Journal of nephrology, 18, 6, 659 (2005)
[4] Wagrowska-Danilewicz, M.; Danilewicz, M., Current position of electron microscopy in the diagnosis of glomerular diseases, Polish Journal of Pathology, 58, 2, 87-92 (2007)
[5] Sementilli, A.; Moura, L. A.; Franco, M. F., The role of electron microscopy for the diagnosis of glomerulopathies, Sao Paulo Medical Journal, 122, 3, 104-109 (2004) · doi:10.1590/s1516-31802004000300006
[6] Osawa, G.; Kimmelstiel, P.; Sailing, V., Thickness of glomerular basement membranes, American Journal of Clinical Pathology, 45, 1, 7-20 (1966) · doi:10.1093/ajcp/45.1.7
[7] Saxela, S.; Davies, D. J.; Kirsner, R. L. G., Thin basement membranes in minimally abnormal glomeruli, American Journal of Clinical Pathology, 43, 32-38 (1990)
[8] Basta, J. G.; Venkataseshan, V. S.; Gil, J.; Kim, D. U.; Dikman, S. H.; Churg, J., Morphometric analysis of glomerular basement membranes (GBM) in thin basement membrane disease (TBMD), Clinical Nephrology, 33, 110-114 (1990)
[9] Marquez, B.; Zouvani, I.; Karagrigoriou, A., A simplified method for measuring the thickness of glomerular basement membranes, Ultrastructural Pathology, 27, 6, 409-416 (2003) · doi:10.1080/716100797
[10] Thomson, S. E.; McLennan, S. V.; Kirwan, P. D., Renal connective tissue growth factor correlates with glomerular basement membrane thickness and prospective albuminuria in a non-human primate model of diabetes: possible predictive marker for incipient diabetic nephropathy, Journal of Diabetes and Its Complications, 22, 4, 284-294 (2008) · doi:10.1016/j.jdiacomp.2007.07.001
[11] Kyriacou, K.; Nearchou, M.; Zouvani, I., The many faces of thin basement membrane nephropathy; a population based study, Topics in Renal Biopsy and Pathology, 93-114 (2012), London, UK: IntechOpen, London, UK
[12] Ong, S. H.; Giam, S. T.; Sinniah, R., Adaptive window-based tracking for the detection of membrane structures in kidney electron micrographs, Machine Vision and Applications, 6, 4, 215-223 (1993) · doi:10.1007/bf01212300
[13] Kamenetsky, I.; Rangayyan, R. M.; Benediktsson, H., Analysis of the glomerular basement membrane in images of renal biopsies using the split-and-merge method: a pilot study, Journal of Digital Imaging, 23, 4, 463-474 (2010) · doi:10.1007/s10278-009-9233-5
[14] Rangayyan, R. M.; Kamenetsky, I.; Benediktsson, H., Segmentation and analysis of the glomerular basement membrane in renal biopsy samples using active contours: a pilot study, Journal of Digital Imaging, 23, 3, 323-331 (2010) · doi:10.1007/s10278-009-9188-6
[15] Wu, H. S.; Dikman, S.; Gil, J., A semi-automatic algorithm for measurement of basement membrane thickness in kidneys in electron microscopy images, Computer Methods and Programs in Biomedicine, 97, 3, 223-231 (2010) · doi:10.1016/j.cmpb.2009.07.002
[16] Wu, H. S.; Dikman, S., Segmentation and thickness measurement of glomerular basement membranes from electron microscopy images, Journal of Electron Microscopy, 59, 5, 409-418 (2010) · doi:10.1093/jmicro/dfq060
[17] Liu, J., Implementation of a semi-automatic tool for analysis of TEM images of kidney samples, Master Thesis, Uppsala, Sweden: Uppsala University, Uppsala, Sweden
[18] Breiman, L., Random forests, Machine Learning, 45, 1, 5-32 (2001) · Zbl 1007.68152 · doi:10.1023/a:1010933404324
[19] Ho, T. K., The random subspace method for constructing decision forests, IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 8, 832-844 (1998) · doi:10.1109/34.709601
[20] Ho, T. K., Random decision forests, Proceedings of 3rd International Conference on Document Analysis and Recognition
[21] Lebedev, A. V.; Westman, E.; VanWesten, G. J. P., Random Forest ensembles for detection and prediction of Alzheimer’s disease with a good between-cohort robustness, NeuroImage: Clinical, 6, 115-125 (2014), C · doi:10.1016/j.nicl.2014.08.023
[22] Saiprasad, G.; Chang, C. I.; Safdar, N., Adrenal gland abnormality detection using random forest classification, Journal of digital imaging, 26, 5, 891-897 (2013) · doi:10.1007/s10278-012-9554-7
[23] Mahapatra, D., Automatic cardiac segmentation using semantic information from random forests, Journal of Digital Imaging, 27, 6, 794-804 (2014) · doi:10.1007/s10278-014-9705-0
[24] Arganda-Carreras, I.; Kaynig, V.; Rueden, C., Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification, Bioinformatics, 33, 15, 75-80 (2017) · doi:10.1093/bioinformatics/btx180
[25] Frank, E.; Hall, M.; Holmes, G., Weka-a machine learning workbench for data mining, Data Mining and Knowledge Discovery Handbook, 1269-1277 (2005)
[26] Nayak, J.; Naik, B.; Behera, H. S., Fuzzy C-means (FCM) clustering algorithm: a decade review from 2000 to 2014, Smart Innovation, Systems and Technologies, 32, 133-149 (2015), New Delhi, India: Springer, New Delhi, India · doi:10.1007/978-81-322-2208-8_14
[27] Padma, A.; Sukanesh, R., Segmentation and classification of brain CT images using combined wavelet statistical texture features, Arabian Journal for Science and Engineering, 39, 2, 767-776 (2014) · doi:10.1007/s13369-013-0649-3
[28] Tóth, B.; Lillo, F.; Farmer, J. D., Segmentation algorithm for non-stationary compound Poisson processes, The European Physical Journal B, 78, 2, 235-243 (2010) · doi:10.1140/epjb/e2010-10046-8
[29] Noor, N. M.; Than, J. C. M.; Rijal, O. M., Automatic lung segmentation using control feedback system: morphology and texture paradigm, Journal of Medical Systems, 39, 3, 214 (2015) · doi:10.1007/s10916-015-0214-6
[30] Dietterich, T. G., Ensemble Methods in Machine Learning, Multiple Classifier Systems, LNCS 1857, 1-15 (2000), Berlin, Germany: Springer, Berlin, Germany
[31] Oshiro, T. M.; Perez, P. S.; Baranauskas, J. A., How many trees in a random forest?, Machine Learning and Data Mining in Pattern Recognition. Lecture Notes in Computer Science, 7376, 4, 154-168 (2012), Berlin, Germany: Springer, Berlin, Germany · doi:10.1007/978-3-642-31537-4_13
[32] Lu, S.; Xia, Y.; Cai, W.; Fulham, M.; Feng, D. D., Early identification of mild cognitive impairment using incomplete random forest-robust support vector machine and FDG-PET imaging, Computerized Medical Imaging and Graphics, 60, 35-41 (2017) · doi:10.1016/j.compmedimag.2017.01.001
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.