Data mining framework for fatty liver disease classification in ultrasound: A hybrid feature extraction paradigm

• Published in: Medical physics (Lancaster) Vol. 39; no. 7; pp. 4255 - 4264
• Main Authors: Acharya, U. Rajendra, Sree, S. Vinitha, Ribeiro, Ricardo, Krishnamurthi, Ganapathy, Marinho, Rui Tato, Sanches, João, Suri, Jasjit S.
• Format: Journal Article
• Language: English
• Published: United States American Association of Physicists in Medicine 01.07.2012
• Subjects: Algorithms; Analysis of texture; Artificial Intelligence; biomedical ultrasonics; CAD; Computed tomography; Computer aided diagnosis; computer aided diagnostic technique; Computer software; Computer‐aided design; Data Mining - methods; decision trees; Diagnosis using ultrasonic, sonic or infrasonic waves; Digital computing or data processing equipment or methods, specially adapted for specific applications; discrete wavelet transform; Diseases; Entropy; Fatty Liver - diagnostic imaging; fatty liver disease; feature extraction; higher order spectra; Humans; Image analysis; image classification; Image data processing or generation, in general; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; image texture; Integral transforms; liver; medical image processing; Medical imaging; Pattern Recognition, Automated - methods; Radiology Information Systems; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; texture; ultrasonic imaging; Ultrasonographic imaging; Ultrasonography; Ultrasonography - methods; Wavelet transform; wavelet transforms; Wavelets; discrete wavelet transform; computer aided diagnostic technique; texture; higher order spectra; fatty liver disease
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1118/1.4725759

Purpose: Fatty liver disease (FLD) is an increasing prevalent disease that can be reversed if detected early. Ultrasound is the safest and ubiquitous method for identifying FLD. Since expert sonographers are required to accurately interpret the liver ultrasound images, lack of the same will result in interobserver variability. For more objective interpretation, high accuracy, and quick second opinions, computer aided diagnostic (CAD) techniques may be exploited. The purpose of this work is to develop one such CAD technique for accurate classification of normal livers and abnormal livers affected by FLD. Methods: In this paper, the authors present a CAD technique (called Symtosis) that uses a novel combination of significant features based on the texture, wavelet transform, and higher order spectra of the liver ultrasound images in various supervised learning-based classifiers in order to determine parameters that classify normal and FLD-affected abnormal livers. Results: On evaluating the proposed technique on a database of 58 abnormal and 42 normal liver ultrasound images, the authors were able to achieve a high classification accuracy of 93.3% using the decision tree classifier. Conclusions: This high accuracy added to the completely automated classification procedure makes the authors' proposed technique highly suitable for clinical deployment and usage.