Artificial Neural Networks and Principal Components Analysis for Detection of Idiopathic Pulmonary Fibrosis in Microscopy Images

In this study we present a computer assisted image identification and recognition tool that aims to help the diagnosis of idiopathic pulmonary fibrosis in microscopy images. To this end, we use principal components analysis to reduce the dimensionality of the data and subsequently we perform classification using Artificial Neural Networks. The proposed approach succeeded in locating the pathological regions and achieved high quality results in terms of classification accuracy.

[1]  V. Paradis,et al.  Sampling variability of liver fibrosis in chronic hepatitis C , 2003, Hepatology.

[2]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[3]  Donald A. Jackson.  STOPPING RULES IN PRINCIPAL COMPONENTS ANALYSIS: A COMPARISON OF HEURISTICAL AND STATISTICAL APPROACHES' , 1993 .

[4]  Koji Shiraishi,et al.  Influence of interstitial fibrosis on spermatogenesis after vasectomy and vasovasostomy. , 2002, Contraception.

[5]  Bogdan M. Wilamowski.  Neural network architectures and learning , 2003, IEEE International Conference on Industrial Technology, 2003.

[6]  G. Izbicki,et al.  Time course of bleomycin‐induced lung fibrosis , 2002, International journal of experimental pathology.

[7]  Changsong Deng,et al.  Statistics and Probability Letters , 2011 .

[8]  W. Black,et al.  The epidemiology of interstitial lung diseases. , 1994, American journal of respiratory and critical care medicine.

[9]  Paul L. Rosin.  Training Cellular Automata for Image Processing , 2006, IEEE Trans. Image Process..

[10]  M. Chalfie,et al.  Green fluorescent protein as a marker for gene expression. , 1994, Science.

[11]  Qeethara Al-Shayea.  Artificial Neural Networks in Medical Diagnosis , 2024, International Journal of Research Publication and Reviews.

[12]  Vassilis P. Plagianakos,et al.  Unsupervised Detection of Fibrosis in Microscopy Images Using Fractals and Fuzzy c-Means Clustering , 2012, AIAI.

[13]  John von Neumann,et al.  Theory Of Self Reproducing Automata , 1967 .

[14]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[15]  N. Siafakas,et al.  Pathogenetic pathways and novel pharmacotherapeutic targets in idiopathic pulmonary fibrosis. , 2007, Pulmonary pharmacology & therapeutics.

[16]  M Masseroli,et al.  Automatic quantification of liver fibrosis: design and validation of a new image analysis method: comparison with semi-quantitative indexes of fibrosis. , 2000, Journal of hepatology.

[17]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[18]  M. Hussain,et al.  A decrease in effective diameter of rat mesenteric venules due to leukocyte margination after a bolus injection of pentoxifylline--digital image analysis of an intravital microscopic observation. , 2004, Microvascular research.

[19]  Chris T. Kiranoudis,et al.  Radial Basis Function Neural Networks Classification for the Recognition of Idiopathic Pulmonary Fibrosis in Microscopic Images , 2008, IEEE Transactions on Information Technology in Biomedicine.

[20]  Rakesh K. Kumar.  Idiopathic pulmonary fibrosis: an epithelial/fibroblastic cross-talk disorder , 2002, Respiratory Research.

[21]  Jonathan Goldstein,et al.  When Is ''Nearest Neighbor'' Meaningful? , 1999, ICDT.

[22]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[23]  Yi Lin.  A note on margin-based loss functions in classification , 2004 .

[24]  M Masseroli,et al.  Liver fibrosis assessment with semiquantitative indexes and image analysis quantification in sustained-responder and non-responder interferon-treated patients with chronic hepatitis C. , 2001, Journal of hepatology.

[25]  K. Shiraishi,et al.  Quantitative analysis of testicular interstitial fibrosis after vasectomy in humans. , 2003, Aktuelle Urologie.

[26]  M. Selman,et al.  Idiopathic pulmonary fibrosis: an epithelial/fibroblastic cross-talk disorder , 2001, Respiratory research.

[27]  Conrad Sanderson,et al.  Armadillo: An Open Source C++ Linear Algebra Library for Fast Prototyping and Computationally Intensive Experiments , 2010 .

[28]  I. Jolliffe.  Principal Component Analysis , 2002 .