Non-invasive evaluation of hepatic steatosis by ultrasound image analysis with simple brightness features and support vector machines

Abstract

The gold standard for the quantitative evaluation of steatosis is liver biopsy, but this is an invasive method. The recent trend is to investigate and develop novel non-invasive hepatic tissue evaluation methods, able to give performances close to biopsy, one of the possible solutions being ultrasound image analysis. Finding the most suitable descriptors of the histological tissue changes (invariant to the ultrasound device and patient) in this imaging modality is an important issue. Several such descriptors are reported in the literature, starting from simple intensity parameters to more sophisticated ones. Here we investigate the discrimination ability of the hepatic steatosis as opposed to healthy tissue by a set of computationally simple features, extracted from the gray level histogram of a small sized region of interest (ROI) positioned at three depths in the ultrasound hepatic image. The advantage of finding computationally simple features, as intensity histogram extracted features, can be the possibility to include their computation directly in ultrasound devices, provided they offer good tissue discrimination. The in-depth variations of some of the features investigated in this paper show a good discrimination in steatosis evaluation and quantification, close to the state of the art in the field.

Computer aided diagnosis method for steatosis rating in ultrasound images using random forests

“…Although our overall accuracy compared favorably with Nagy et al [7] and Lupşor et al [16] results and are similar to the Ribeiro et al [17] work, comparison is still problematic, given the different datasets and reference method used in our study. However, it is possible to assess the usefulness of the features used in literature in the present work.…”

“…Direct comparison of the classification accuracy of the proposed method with the results of the most relevant work on computer aided diagnosis of steatosis in the literature [7,16,17] is not possible, since these papers report only results of two class (steatosis versus normal) classification, in contrast with our study, targeting automatic quantification of the steatosis severity. Although our overall accuracy compared favorably with Nagy et al [7] and Lupşor et al [16] results and are similar to the Ribeiro et al [17] work, comparison is still problematic, given the different datasets and reference method used in our study.…”

“…The intraobserver agreement rate for severity of the disease is 55%-68%. To improve these results, several computer vision based solutions have been proposed [7][8][9][10].…”

Computerized ultrasound image analysis for noninvasive evaluation of hepatic steatosis

“…The hepatic and splenic ultrasound sections were stored in a database used further by USICA. We mention that preliminary results were published before [23] and this study presents the final work.…”

Automatic evaluation of steatosis by ultrasound image analysis

“…Computer-aided ultrasound studies for steatosis detection and for the assessment of the degree of disease have been reported in [4]- [6]. A major problem that needs to be addressed in such a system is the selection of relevant features to solve the task.…”