2017
DOI: 10.1109/tmi.2017.2659734
|View full text |Cite
|
Sign up to set email alerts
|

Computer-Aided Diagnosis of Focal Liver Lesions Using Contrast-Enhanced Ultrasonography With Perflubutane Microbubbles

Abstract: This paper proposes an automatic classification method based on machine learning in contrast-enhanced ultrasonography (CEUS) of focal liver lesions using the contrast agent Sonazoid. This method yields spatial and temporal features in the arterial phase, portal phase, and post-vascular phase, as well as max-hold images. The lesions are classified as benign or malignant and again as benign, hepatocellular carcinoma (HCC), or metastatic liver tumor using support vector machines (SVM) with a combination of select… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
34
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 68 publications
(34 citation statements)
references
References 40 publications
0
34
0
Order By: Relevance
“…This possibility has been explored most thoroughly in hepatic imaging, for which recent work has demonstrated utility of perflubutane-enhanced US not only in identifying location of focal liver lesions but in characterization as benign or malignant. 19 Another study showed that use of perflubutane-enhanced US improves the accuracy of diagnostic liver biopsy by differentiating viable from necrotic tissue. 20 Finally, there is evidence from a mouse cholangitis model that perflubutane-enhanced US can detect impaired phagocytic activity associated with hepatic inflammation and hypoxia.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…This possibility has been explored most thoroughly in hepatic imaging, for which recent work has demonstrated utility of perflubutane-enhanced US not only in identifying location of focal liver lesions but in characterization as benign or malignant. 19 Another study showed that use of perflubutane-enhanced US improves the accuracy of diagnostic liver biopsy by differentiating viable from necrotic tissue. 20 Finally, there is evidence from a mouse cholangitis model that perflubutane-enhanced US can detect impaired phagocytic activity associated with hepatic inflammation and hypoxia.…”
Section: Discussionmentioning
confidence: 99%
“…However, perflubutane's predilection for uptake by the reticuloendothelial system provides a mechanism by which perflubutane‐enhanced US can provide further insight into tissue characteristics. This possibility has been explored most thoroughly in hepatic imaging, for which recent work has demonstrated utility of perflubutane‐enhanced US not only in identifying location of focal liver lesions but in characterization as benign or malignant . Another study showed that use of perflubutane‐enhanced US improves the accuracy of diagnostic liver biopsy by differentiating viable from necrotic tissue .…”
Section: Discussionmentioning
confidence: 99%
“…The lesions are classified as benign or malignant and again as benign, HCC, or metastatic liver tumor using support vector machines (SVM) with a combination of selected optimal features. Experimental results from 98 subjects indicated that benign and malignant classification showed 94.0% sensitivity, 87.1% specificity, and 91.8% accuracy, and that the accuracies of the benign, HCC, and metastatic liver tumor classifications were 84.4%, 87.7%, and 85.7%, respectively [98].…”
Section: Computer-aided Diagnostic (Cad) Systemsmentioning
confidence: 99%
“…Encouraging results have been reported on multiparametric combination of quantitative ultrasound features for disease classification in various organs. Several authors have studied the combination of DCE-US-derived (semi)quantitative features for liver lesions classification, using either SVMs (C aleanu et al 2014;Kondo et al 2017) or ANNs (Shiraishi et al 2008;Sugimoto et al 2009), usually reaching an appreciable accuracy in distinguishing hepatocellular carcinoma, hemangioma and benign lesions. In the prostate, Wildeboer et al (2017) found that the combination of (in particular) perfusionand dispersion-related DCE-US parameters by means of a Gaussian mixture model (GMM) improved the accuracy of prostate cancer classification.…”
Section: Multiparametric Analysis By Machine Learningmentioning
confidence: 99%