Fat Quantitation in Liver Biopsies Using a Pretrained Classification Based System

A. Arjmand, N. Giannakeas

Abstract


Non-Alcoholic Fatty Liver Disease (NAFLD) is a common syndrome that mainly leads to fat accumulation in liver and steatohepatitis. It is targeted as a severe medical condition ranging from 20% to 40% in adult populations of the Western World. Its effect is identified through insulin resistance, which places patients at high mortality rates. An increased fat aggregation rate, can dramatically increase the development of liver steatosis, which in later stages may advance into fibrosis and cirrhosis. During recent years, new studies have focused on building new methodologies capable of detecting fat cells, based on the histology method with digital image processing techniques. The current study, expands previous work on the detection of fatty liver, by identifying once more a number of diverse histological findings. It is a combined study of both image analysis and supervised learning of fat droplet features, with a specific goal to exclude other findings from fat ratio calculation. The method is evaluated in a total set of 40 liver biopsy images with different magnification capabilities, performing satisfyingly (1.95% absolute error).


Keywords


liver biopsy; steatohepatitis; fatty liver; machine learning; image analysis

Full Text:

PDF

References


R. S. O’Shea, S. Dasarathy, A. J. McCullough, “Alcoholic liver disease”, The American Journal of Gastroenterology, Vol. 105, No.1, pp. 14-32, 2010

J. W. Ward, “Viral hepatitis and liver cancer”, U.S. Department of Health and Human Services, Services Centers for Disease Control and Prevention, 2016

A. M. Zaitoun, H. A. Mardini, S. Awad, S. Ukabam, S. Makadisi, C. Record, “Quantitative assessment of fibrosis and steatosis in liver biopsies from patients with chronic hepatitis C”, Journal of Clinical Pathology, Vol. 54, No. 6, pp. 461-465, 2001

H. Marsman, T. Matsushita, R. Dierkhising, W. Kremers, C. Rosen, L. Burgart, S. L. Nyberg, “Assessment of donor liver steatosis: pathologist or automated software”, Human Pathology, Vol. 35, No. 4, pp. 430-435, 2004

V. Roullier, C. Cavaro-Menard, C. Guillaume, C. Aube, “Fuzzy algorithms to extract vacuoles of steatosis on liver histological color images”, 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, France, August 22-26, 2007

B. Turlin, G. A. Ramn, D. M. Purdie, F. Laine, M. Perrin, Y. Deugnier, G. A. Macdonald, “Assessment of hepatic steatosis: comparison of quantitative and semiquantitative methods in 108 liver biopsies”, Liver International, Vol. 29, No. 4, pp. 530-535, 2009

G. E. Liquori, G. Calamita, D. Cascella, M. Mastrodonato, P. Portincasa, D. Ferri, “An innovative methodology for the automated morphometric and quantitative estimation of liver steatosis”, Histology and Histopathology, Vol. 24, No. 1, pp. 49-60, 2009

A. M. El-Badry, S. Breitenstein, W. Jochum, K. Washington, V. Paradis, L. Rubbia-Brandt, M. A. Puhan, K. Slankamenac, R. Graf, P. A. Clavien, “Assessment of hepatic steatosis by expert pathologists: the end of a gold standard”, Annals of Surgery, Vol. 250, No. 5, pp. 691-697, 2009

J. Kong, M. J. Lee, P. Bagci, P. Sharma, D. Martin, N. V. Adsay, J. H. Saltz, A. B. Farris, “Computer-based image analysis of liver steatosis with large scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis”, IEEE International Conference on Bioinformatics and Biomedicine, USA, November 12-15, 2011

N. I. Nativ, A. I. Chen, G. Yarmush, S. D. Henry, J. H. Lefkowitch, K. M. Klein, T. J. Maguire, R. Schloss, J. V. Guarrera, F. Berthiaume, M. L. Yarmush, “Automated image analysis method for detecting and quantifying macrovesicular steatosis in hematoxylin and eosin-stained histology images of human livers”, Liver Transplantation, Vol. 20, No. 2, pp. 228-236, 2014

S. Vanderbeck, J. Bockhorst, R. Komorowski, D. E. Kleiner, S. Gawrieh, “Automatic classification of white regions in liver biopsies by supervised machine learning”, Human Pathology, Vol. 45, No. 4, pp. 785-792, 2014

M. Sciarabba, M. Vertemati, C. Moscheni, M. Cossa, L. Vizzotto, “Automated lipid droplets recognition in human steatotic liver: some preliminary results”, In Proceedings of the Medical Image Understanding and Analysis Conference, London, UK, pp. 20-24, 2015

N. Batool, “Detection and spatial analysis of hepatic steatosis in histopathology images using sparse linear models”, Sixth International Conference on Image Processing Theory, Tools and Applications, Oulu, Finland, December 12-15, 2016

B. Jahne, Digital image processing, 5th revised and extended edition, Springer Science & Business Media, 2002

T. Dietterich, C. Bishop, D. Heckerman, M. Jordan, M. Kearns, Introduction to machine learning, second edition, Ethem Alpaydin, The MIT Press, 2010

K. P. Murphy, Machine learning: a probabilistic perspective, Adaptive Computation and Machine Learning, The MIT Press, 2012

P. Cunningham, S. J. Delany, “k-nearest neighbour classifiers”, Technical Report UCD-CSI-2007-4, 2007

M. Mohri, A. Rostamizadeh, A. Talwalkar, Foundations of machine learning, The MIT Press, 2012

N. Giannakeas, M. G. Tsipouras, A. T. Tzallas, M. G. Vavva, M. Tsiplakidou, E. C. Karvounis, R. Forlano, P. Manousou, “Measuring steatosis in liver biopsies using machine learning and morphological imaging”, 30th IEEE International Symposium on Computer-Based Medical Systems, Thessaloniki, Greece, June 22-24, 2017

A. Arjmand, AT. Tzallas, M. G. Tsipouras, R. Forlano, P. Manousou, N. Ketertsidis, N. Giannakeas, “Fat droplet identification in liver biopsies using supervised learning techniques”, Proceedings of Pervasive Technologies Related to Assistive Environments, Corfu, Greece, June 26-29, 2018




eISSN: 1792-8036     pISSN: 2241-4487