Classifier Approaches for Liver Steatosis using Ultrasound Images

Abstract This paper presents a semi-automatic classification approach to evaluate steatotic liver tissues using B-scan ultrasound images. Several features have been extracted and used in three different classifiers, such as Artificial Neural Networks (ANN), Support Vector Machines (SVM) and k-Nearest Neighbors (kNN). The classifiers were trained using the 10-cross validation method. A feature selection method based on stepwise regression was also exploited resulting in better accuracy predictions. The results showed that the SVM have a slightly higher performance than the kNN and the ANN, appearing as the most relevant one to be applied to the discrimination of pathologic tissues in clinical practice.

[1]  Abdulhakim Coskun,et al.  Quantitative Grading Using Grey Relational Analysis on Ultrasonographic Images of a Fatty Liver , 2012, Journal of Medical Systems.

[2]  José Silvestre Silva,et al.  Intra-patient Registration Methods for Thoracic CT Exams , 2009, BIOSIGNALS.

[3]  João M. Sanches,et al.  Chronic liver disease staging classification based on ultrasound, clinical and laboratorial data , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[4]  Luis Marques,et al.  Statistical textural features for classification of lung emphysema in CT images: A comparative study , 2010, 5th Iberian Conference on Information Systems and Technologies.

[5]  Beatriz Sousa Santos,et al.  Image Denoising Methods for Tumor Discrimination in High-Resolution Computed Tomography , 2010, Journal of Digital Imaging.

[6]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[7]  Benoit B. Mandelbrot,et al.  Fractal Geometry of Nature , 1984 .

[8]  Carlos Nicolau,et al.  Gray-scale ultrasound in hepatic cirrhosis and chronic hepatitis: diagnosis, screening, and intervention. , 2002, Seminars in ultrasound, CT, and MR.

[9]  Beatriz Sousa Santos,et al.  Comparison of a segmentation algorithm to six expert imagiologists in detecting pulmonary contours on x-ray CT images , 2003, SPIE Medical Imaging.

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

[11]  Wen-Chun Yeh,et al.  Liver fatty change classification using 25 MHz high frequency ultrasound , 2004, IEEE Ultrasonics Symposium, 2004.

[12]  Yamashita,et al.  Backpropagation algorithm which varies the number of hidden units , 1989 .

[13]  Joaquim Madeira,et al.  Detection and 3D representation of pulmonary air bubbles in HRCT volumes , 2003, SPIE Medical Imaging.

[14]  José Silvestre Silva,et al.  A Level Set Segmentation Method of the Four Heart Cavities in Pediatric Ultrasound Images , 2010, ICIAR.

[15]  Zamir Halpern,et al.  Diagnostic value of a computerized hepatorenal index for sonographic quantification of liver steatosis. , 2009, AJR. American journal of roentgenology.

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

[17]  Beatriz Sousa Santos,et al.  A volumetric pulmonary CT segmentation method with applications in emphysema assessment , 2006, SPIE Medical Imaging.

[18]  Ana Ferreira,et al.  Automatic Corneal Nerves Recognition for Earlier Diagnosis and Follow-Up of Diabetic Neuropathy , 2010, ICIAR.

[19]  Geoffrey E. Hinton,et al.  Learning representations of back-propagation errors , 1986 .

[20]  Richard F. Gunst,et al.  Applied Regression Analysis , 1999, Technometrics.

[21]  J. S. Silva,et al.  Fast volumetric registration method for tumor follow‐up in pulmonary CT exams , 2011, Journal of applied clinical medical physics.

[22]  Laurent Sandrin,et al.  Novel Controlled Attenuation Parameter for the evaluation of fatty liver disease , 2009, 2009 IEEE International Ultrasonics Symposium.

[23]  Vinod Kumar,et al.  Neural network based focal liver lesion diagnosis using ultrasound images , 2011, Comput. Medical Imaging Graph..

[24]  Ji-Wook Jeong,et al.  Computer-assisted Sonographic Analysis of the Hepatorenal and Textural Features for the Diagnosis of the Fatty Liver , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[25]  Jinchang Ren,et al.  ANN vs. SVM: Which one performs better in classification of MCCs in mammogram imaging , 2012, Knowl. Based Syst..

[26]  S.A. Azaid,et al.  Automatic Diagnosis of Liver Diseases from Ultrasound Images , 2006, 2006 International Conference on Computer Engineering and Systems.

[27]  Hemanta Kumar Kalita,et al.  A New Algorithm for Measuring Available Bandwidth in a Wide Area Network , 2007 .

[28]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[29]  K. Ghosh,et al.  Corroborating the Subjective Classification of Ultrasound Images of Normal and Fatty Human Livers by the Radiologist through Texture Analysis and SOM , 2007, 15th International Conference on Advanced Computing and Communications (ADCOM 2007).

[30]  George G. Lendaris,et al.  Diffraction-Pattern Sampling For Automatic Pattern Recognition , 1969, Other Conferences.

[31]  Paula Martins,et al.  Phase Symmetry Approach Applied to Children Heart Chambers Segmentation: A Comparative Study , 2011, IEEE Transactions on Biomedical Engineering.

[32]  Janardan K Reddy,et al.  Lipid metabolism and liver inflammation. II. Fatty liver disease and fatty acid oxidation. , 2006, American journal of physiology. Gastrointestinal and liver physiology.

[33]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[34]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[35]  Jaime B. Santos,et al.  A new level set based segmentation method for the four cardiac chambers , 2010, 5th Iberian Conference on Information Systems and Technologies.

[36]  Yu-Len Huang,et al.  Computer-aided Diagnosis Using Neural Networks and Support Vector Machines for Breast Ultrasonography , 2009 .

[37]  Ana Ferreira,et al.  A method for corneal nerves automatic segmentation and morphometric analysis , 2012, Comput. Methods Programs Biomed..

[38]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[39]  Tom Fawcett,et al.  ROC Graphs: Notes and Practical Considerations for Data Mining Researchers , 2003 .

[40]  Weizhong Yan,et al.  Classifier performance measures in multifault diagnosis for aircraft engines , 2002, SPIE Defense + Commercial Sensing.

[41]  S. Poonguzhali,et al.  Automatic Classification of Focal Lesions in Ultrasound Liver Images Using Combined Texture Features , 2008 .

[42]  S. Nedevschi,et al.  Ultrasonography Contribution to Hepatic Steatosis Quantification. Possibilities of Improving this Method through Computerized Analysis of Ultrasonic Image , 2006, 2006 IEEE International Conference on Automation, Quality and Testing, Robotics.

[43]  N. Draper,et al.  Applied Regression Analysis: Draper/Applied Regression Analysis , 1998 .

[44]  David A Clausi.  An analysis of co-occurrence texture statistics as a function of grey level quantization , 2002 .

[45]  Mineichi Kudo,et al.  Comparison of algorithms that select features for pattern classifiers , 2000, Pattern Recognit..

[46]  Blockin.  SVM : Which One Performs Better in Classification of MCCs in Mammogram Imaging , 2022 .

[47]  Enmin Song,et al.  Computer aided diagnosis of fatty liver ultrasonic images based on support vector machine , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[48]  John A. Belward,et al.  Fractal dimensions for rainfall time series , 1999 .

[49]  Tom Fawcett,et al.  ROC Graphs: Notes and Practical Considerations for Researchers , 2007 .