Symtosis: A liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm

Background and Objective Fatty Liver Disease (FLD) - a disease caused by deposition of fat in liver cells, is predecessor to terminal diseases such as liver cancer. The machine learning (ML) techniques applied for FLD detection and risk stratification using ultrasound (US) have limitations in computing tissue characterization features, thereby limiting the accuracy. Methods Under the class of Symtosis for FLD detection and risk stratification, this study presents a Deep Learning (DL)-based paradigm that computes nearly seven million weights per image when passed through a 22 layered neural network during the cross-validation (training and testing) paradigm. The DL architecture consists of cascaded layers of operations such as: convolution, pooling, rectified linear unit, dropout and a special block called inception model that provides speed and efficiency. All data analysis is performed in optimized tissue region, obtained by removing background information. We benchmark the DL system against the conventional ML protocols: support vector machine (SVM) and extreme learning machine (ELM). Results The liver US data consists of 63 patients (27 normal/36 abnormal). Using the K10 cross-validation protocol (90% training and 10% testing), the detection and risk stratification accuracies are: 82%, 92% and 100% for SVM, ELM and DL systems, respectively. The corresponding area under the curve is: 0.79, 0.92 and 1.0, respectively. We further validate our DL system using two class biometric facial data that yields an accuracy of 99%. Conclusion DL system shows a superior performance for liver detection and risk stratification compared to conventional machine learning systems: SVM and ELM.

[1]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[2]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[3]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Jasjit S. Suri,et al.  Extreme Learning Machine Framework for Risk Stratification of Fatty Liver Disease Using Ultrasound Tissue Characterization , 2017, Journal of Medical Systems.

[5]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[6]  Xiang Liu,et al.  Learning to Diagnose Cirrhosis with Liver Capsule Guided Ultrasound Image Classification , 2017, Sensors.

[7]  Ayman El-Baz,et al.  Prostate Tissue Characterization/Classification in 144 Patient Population Using Wavelet and Higher Order Spectra Features from Transrectal Ultrasound Images , 2013, Technology in cancer research & treatment.

[8]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[9]  Kedar N. Chintapalli,et al.  MRI evaluation of fatty liver in day to day practice: Quantitative and qualitative methods , 2014 .

[10]  Ayman El-Baz,et al.  In-vitro and in-vivo diagnostic techniques for prostate cancer: a review. , 2014, Journal of biomedical nanotechnology.

[11]  U. Rajendra Acharya,et al.  Automated classification of patients with coronary artery disease using grayscale features from left ventricle echocardiographic images , 2013, Comput. Methods Programs Biomed..

[12]  Li Zhang,et al.  A computer-aided diagnostic system to discriminate SPIO-enhanced magnetic resonance hepatocellular carcinoma by a neural network classifier , 2009, Comput. Medical Imaging Graph..

[13]  Jasjit S. Suri,et al.  Carotid artery intra-plaque attenuation variability using computed tomography , 2016 .

[14]  Jacek M. Zurada,et al.  Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images , 1996, IEEE Trans. Medical Imaging.

[15]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[16]  Jasjit S. Suri,et al.  Analysis of Tumor Vascularity Using Three-Dimensional Power Doppler Ultrasound Images , 2008, IEEE Transactions on Medical Imaging.

[17]  Alistair Munro,et al.  Evolving fuzzy rule based controllers using genetic algorithms , 1996, Fuzzy Sets Syst..

[18]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[19]  Ajay Gupta,et al.  Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm , 2017, Journal of Medical Systems.

[20]  Jasjit S. Suri,et al.  Reliable and accurate psoriasis disease classification in dermatology images using comprehensive feature space in machine learning paradigm , 2015, Expert Syst. Appl..

[21]  Paulo R. S. Mendonça,et al.  Stratification of Patients With Liver Fibrosis Using Dual-Energy CT , 2015, IEEE Transactions on Medical Imaging.

[22]  J. Ross Quinlan,et al.  Simplifying Decision Trees , 1987, Int. J. Man Mach. Stud..

[23]  S Vinitha Sree,et al.  Evolutionary algorithm-based classifier parameter tuning for automatic ovarian cancer tissue characterization and classification. , 2014, Ultraschall in der Medizin.

[24]  Huai Li,et al.  Artificial convolution neural network for medical image pattern recognition , 1995, Neural Networks.

[25]  Jasjit S. Suri,et al.  Risk stratification of 2D ultrasound-based breast lesions using hybrid feature selection in machine learning paradigm , 2017 .

[26]  Jonathan C. Cohen,et al.  Prevalence of hepatic steatosis in an urban population in the United States: Impact of ethnicity , 2004, Hepatology.

[27]  Jasjit S. Suri,et al.  Automatic Lung Segmentation Using Control Feedback System: Morphology and Texture Paradigm , 2015, Journal of Medical Systems.

[28]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[29]  Andrew Beng Jin Teoh,et al.  A Discriminant Pseudo Zernike Moments in Face Recognition , 2006, J. Res. Pract. Inf. Technol..

[30]  Nilanjan Dey,et al.  Automated stratification of liver disease in ultrasound: An online accurate feature classification paradigm , 2016, Comput. Methods Programs Biomed..

[31]  Agnieszka Witkowska,et al.  Computer‐Aided Diagnostic System for Detection of Hashimoto Thyroiditis on Ultrasound Images From a Polish Population , 2014, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[32]  U Rajendra Acharya,et al.  Data mining framework for fatty liver disease classification in ultrasound: A hybrid feature extraction paradigm. , 2012, Medical physics.

[33]  N. G. Chitaliya,et al.  An Efficient Method for Face Feature Extraction and Recognition based on Contourlet Transform and Principal Component Analysis using Neural Network , 2010 .

[34]  Eliseo Guallar,et al.  Prevalence of nonalcoholic fatty liver disease in the United States: the Third National Health and Nutrition Examination Survey, 1988-1994. , 2013, American journal of epidemiology.

[35]  Tadashi Araki,et al.  PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound: A link between carotid and coronary grayscale plaque morphology , 2016, Comput. Methods Programs Biomed..

[36]  Jasjit S. Suri,et al.  A novel and robust Bayesian approach for segmentation of psoriasis lesions and its risk stratification , 2017, Comput. Methods Programs Biomed..

[37]  Petia Radeva,et al.  Well-balanced system for coronary calcium detection and volume measurement in a low resolution intravascular ultrasound videos , 2017, Comput. Biol. Medicine.