Differentiation of Focal Liver Lesions: Usefulness of Parametric Imaging with Contrast-enhanced US

Anaye, Anass; Perrenoud, G.; Rognin, N.; Arditi, Marcel; Mercier, Laurent; Frinking, Peter; Ruffieux, Christiane; Peetrons, P; Meuli, Reto; Meuwly, Jean Yves

doi:10.1148/radiol.11101866

Cited by 43 publications

(47 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We retrospectively compared the hemodynamic changes of HCC with or without PVTT by quantitative perfusion analysis using SonoLiver, which is designed to process DICOM files of real-time CEUS data and allows the user to objectively visualize the differences in perfusion kinetics of different regions of interest (Anaye et al 2011;Rognin et al 2010). Our results indicated that the time-dependent parameters (such as RT and TTP) of HCCs were significantly faster than those of liver parenchyma in both groups, which is consistent with the hypervascular nature of HCC.…”

Section: Discussionmentioning

confidence: 99%

Role of Portal Vein Tumor Thrombosis in Quantitative Perfusion Analysis of Contrast-Enhanced Ultrasound of Hepatocellular Carcinoma

Wang

Liu

Lü

et al. 2015

Ultrasound in Medicine & Biology

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Role of Portal Vein Tumor Thrombosis in Quantitative Perfusion Analysis of Contrast-Enhanced Ultrasound of Hepatocellular Carcinoma

Wang

Liu

Lü

et al. 2015

Ultrasound in Medicine & Biology

View full text Add to dashboard Cite

“…Cascades of Artificial Neural Networks [13] have also been employed to classify FLLs based on manually segmented lesion regions. Anaye et al [14] analyzes the Dynamic Vascular Patterns (DVPs) of FLLs with respect to surrounding healthy parenchyma to differentiate between benign and malignant FLLs. Rognin et al [19] developed the parametric imaging technique for mapping the DVP signatures into a single image.…”

Section: Related Workmentioning

confidence: 99%

“…We compute the hidden variables for all training data, which corresponds to approximating the concave function by a linear upper bound, (14) The optimal hidden variables are computed by maximizing with two following steps: find the best locations of ROIs for each possible classifier selection , and then given all of all possible , we select the best local classifiers and the corresponding best ROIs , i.e. we determine the latent structures.…”

Section: A Optimizationmentioning

confidence: 99%

“…In the experiments, we adopt the standard setup of randomized 5-fold cross-validation. The sensitivity for each class and mean accuracy are used as the evaluation criteria, which are commonly used by others [14]. The experiments are carried out on a PC with Core I7 3.4 GHz CPU, 12 GB RAM and conventional hard drive, and the typical processing time for testing a 4-min CEUS video is about 200 seconds.…”

Section: B Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Recognizing Focal Liver Lesions in CEUS With Dynamically Trained Latent Structured Models

Liang

Cao

Huang

et al. 2016

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

This work investigates how to automatically classify Focal Liver Lesions (FLLs) into three specific benign or malignant types in Contrast-Enhanced Ultrasound (CEUS) videos, and aims at providing a computational framework to assist clinicians in FLL diagnosis. The main challenge for this task is that FLLs in CEUS videos often show diverse enhancement patterns at different temporal phases. To handle these diverse patterns, we propose a novel structured model, which detects a number of discriminative Regions of Interest (ROIs) for the FLL and recognize the FLL based on these ROIs. Our model incorporates an ensemble of local classifiers in the attempt to identify different enhancement patterns of ROIs, and in particular, we make the model reconfigurable by introducing switch variables to adaptively select appropriate classifiers during inference. We formulate the model learning as a non-convex optimization problem, and present a principled optimization method to solve it in a dynamic manner: the latent structures (e.g. the selections of local classifiers, and the sizes and locations of ROIs) are iteratively determined along with the parameter learning. Given the updated model parameters in each step, the data-driven inference is also proposed to efficiently determine the latent structures by using the sequential pruning and dynamic programming method. In the experiments, we demonstrate superior performances over the state-of-the-art approaches. We also release hundreds of CEUS FLLs videos used to quantitatively evaluate this work, which to the best of our knowledge forms the largest dataset in the literature. Please find more information at "http://vision.sysu.edu.cn/projects/fllrecog/".

show abstract

“…Typical CT appearance is that of native hypo-or isodense FLL, with homogenous enhancement during the arterial phase, becoming hyperdense, except for the central scar which remains unenhanced. The lesion is isodense during the portal phase and in the late phase the enhanced, hyperdense central scar can be seen [5,15].…”

Section: Figmentioning

confidence: 99%

An atypical case of focal nodular hyperplasia. Problems of imagistic diagnosis

et al. 2014

View full text Add to dashboard Cite

Focal nodular hyperplasia (FNH) is a hepatic disease first described in 1958. The existence of an accessible and minimally invasive imagistic investigation to establish the diagnosis in a large number of cases would be desirable, especially because once diagnosed, the disease needs no treatment. We present the case of a young woman with long term use of oral contraceptives in which the diagnosis of FNH was established at a routine ultrasound. Evolution of disease during the pregnancy and the atypical imagistic aspect of liver lesions raised many problems of differential diagnosis.

show abstract

Differentiation of Focal Liver Lesions: Usefulness of Parametric Imaging with Contrast-enhanced US

Abstract: Parametric imaging of DVP improves diagnostic performance of contrast-enhanced US in the differentiation between malignant and benign FLLs; it also provides excellent interobserver agreement.

Cited by 43 publications

References 28 publications

Role of Portal Vein Tumor Thrombosis in Quantitative Perfusion Analysis of Contrast-Enhanced Ultrasound of Hepatocellular Carcinoma

Role of Portal Vein Tumor Thrombosis in Quantitative Perfusion Analysis of Contrast-Enhanced Ultrasound of Hepatocellular Carcinoma

Recognizing Focal Liver Lesions in CEUS With Dynamically Trained Latent Structured Models

An atypical case of focal nodular hyperplasia. Problems of imagistic diagnosis

Contact Info

Product

Resources

About