scholarly journals Diagnostic Accuracy of Delayed Phase Post Contrast Computed Tomographic Images in the Diagnosis of Focal Liver Lesions in Dogs: 69 Cases

2021 ◽  
Vol 8 ◽  
Author(s):  
Silvia Burti ◽  
Alessandro Zotti ◽  
Federico Bonsembiante ◽  
Barbara Contiero ◽  
Tommaso Banzato
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Normal Liver ◽  
Focal Liver Lesions ◽  
Liver Lesions ◽  
Quantitative Ct ◽  
Post Contrast ◽  
Surface Appearance ◽  
Computed Tomographic ◽  
Ct Features

To describe the computed tomographic (CT) features of focal liver lesions (FLLs) in dogs, that could enable predicting lesion histotype. Dogs diagnosed with FLLs through both CT and cytopathology and/or histopathology were retrospectively collected. Ten qualitative and 6 quantitative CT features have been described for each case. Lastly, a machine learning-based decision tree was developed to predict the lesion histotype. Four categories of FLLs - hepatocellular carcinoma (HCC, n = 13), nodular hyperplasia (NH, n = 19), other benign lesions (OBL, n = 18), and other malignant lesions (OML, n = 19) - were evaluated in 69 dogs. Five of the observed qualitative CT features resulted to be statistically significant in the distinction between the 4 categories: surface, appearance, lymph-node appearance, capsule formation, and homogeneity of contrast medium distribution. Three of the observed quantitative CT features were significantly different between the 4 categories: the Hounsfield Units (HU) of the radiologically normal liver parenchyma during the pre-contrast scan, the maximum dimension, and the ellipsoid volume of the lesion. Using the machine learning-based decision tree, it was possible to correctly classify NHs, OBLs, HCCs, and OMLs with an accuracy of 0.74, 0.88, 0.87, and 0.75, respectively. The developed decision tree could be an easy-to-use tool to predict the histotype of different FLLs in dogs. Cytology and histology are necessary to obtain the final diagnosis of the lesions.

Tu1040 Comparison of Different Machine Learning Systems in Classifying Focal Liver Lesions Based on Clinical and Dynamic Imaging Data

2013 ◽  
Vol 144 (5) ◽  
pp. S-1038-S-1039
Author(s):  
Costin T. Streba ◽  
Cristin C. Vere ◽  
Larisa D. Sandulescu ◽  
Adrian Saftoiu ◽  
Dan Ionut Gheonea ◽  
...  
Keyword(s):  
Machine Learning ◽  
Dynamic Imaging ◽  
Learning Systems ◽  
Focal Liver Lesions ◽  
Liver Lesions ◽  
Imaging Data

scholarly journals Effects of Gray-Scale Ultrasonography Immediate Post-Contrast on Characterization of Focal Liver Lesions

2015 ◽  
Vol 2015 ◽  
pp. 1-11
Author(s):  
Wei Yang ◽  
Min-Hua Chen ◽  
Wei Wu ◽  
Ying Dai ◽  
Zhi-Hui Fan
Keyword(s):  
Interventional Procedure ◽  
Hepatic Metastases ◽  
Focal Liver Lesions ◽  
Imaging Features ◽  
Liver Lesions ◽  
Gray Scale ◽  
Post Contrast ◽  
Contrast Enhanced ◽  
Before And After

This study compared the imaging features of conventional gray scale ultrasound (US) before and after contrast-enhanced ultrasound (CEUS) for focal liver lesions and 22 evaluated the role of US post-CEUS in characterizing liver lesions. 126 patients with 158 focal liver lesions underwent CEUS and US post-CEUS examination and entered this study. There were 74 hepatocellular carcinomas (HCC), 43 hepatic metastases, and 41 hemangiomas. Imaging features of US pre-CEUS and US post-CEUS were analyzed offsite by two blinded experienced radiologists to evaluate size, boundary, echogenicity, internal texture, posterior acoustic enhancement, spatial resolution, and contrast resolution. In the end with pathological and clinical evidence, the diagnostic accuracy rate of US pre-CEUS was 53.8% (85/158 lesions), lower than that of CEUS (88.0%, 139/158 lesions); with the complementation of US post-CEUS the rate rose to 93.0% (147/158 lesions). US post-CEUS could improve the visibility of typical structures of focal liver lesions and might provide important complementary information for CEUS diagnosis. It also increases the visibility of small liver lesions compared with US pre-CEUS and helps to guide local interventional procedure.

scholarly journals Multiparametric Ultrasound Approach Using a Tree-Based Decision Classifier for Inconclusive Focal Liver Lesions Evaluated by Contrast Enhanced Ultrasound

2021 ◽  
Vol 11 (12) ◽  
pp. 1388
Author(s):  
Tudor Voicu Moga ◽  
Ciprian David ◽  
Alina Popescu ◽  
Raluca Lupusoru ◽  
Darius Heredea ◽  
...  
Keyword(s):  
Decision Tree ◽  
Focal Liver Lesions ◽  
Liver Lesions ◽  
Contrast Enhanced Ultrasound ◽  
Decision Tree Classifier ◽  
Binary Decision ◽  
Binary Decision Tree ◽  
Contrast Enhanced ◽  
Tree Classifier ◽  
Multiparametric Ultrasound

Background: Multiparametric ultrasound (MPUS) is a concept whereby the examiner is encouraged to use the latest features of an ultrasound machine. The aim of this study was to reanalyze inconclusive focal liver lesions (FLLs) that had been analyzed via contrast enhanced ultrasound (CEUS) using the MPUS approach with the help of a tree-based decision classifier. Materials and methods: We retrospectively analyzed FLLs that were inconclusive upon CEUS examination in our department, focusing our attention on samples taken over a period of two years (2017−2018). MPUS reanalysis followed a three-step algorithm, taking into account the liver stiffness measurement (LSM), time–intensity curve analysis (TIC), and parametric imaging (PI). After processing all steps of the algorithm, a binary decision tree classifier (BDTC) was used to achieve a software-assisted decision. Results: Area was the only TIC-CEUS parameter that showed a significant difference between malign and benign lesions with a cutoff of >−19.3 dB for washout phenomena (AUROC = 0.58, Se = 74.0%, Sp = 45.7%). Using the binary decision tree classifier (BDTC) algorithm, we correctly classified 71 out of 91 lesions according to their malignant or benignant status, with an accuracy of 78.0% (sensitivity = 62%, specificity = 45%, and precision = 80%). Conclusions: By reevaluating inconclusive FLLs that had been analyzed via CEUS using MPUS, we managed to determine that 78% of the lesions were malignant and, in 28% of them, we established the lesion type.

Characterization of Malignant Focal Liver Lesions with Contrast-Enhanced 40 MHz Ultrasound Imaging in Hepatitis B Virus X Transgenic Mice: A Feasibility Study

2008 ◽  
Vol 30 (4) ◽  
pp. 203-216 ◽  
Author(s):  
Ai-Ho Liao ◽  
Ya-Chien Cheng ◽  
Chien-Hsiu Weng ◽  
Ting-Fen Tsai ◽  
Wei-Hsiang Lin ◽  
...  
Keyword(s):  
Transgenic Mice ◽  
Liver Parenchyma ◽  
Liver Lesion ◽  
Focal Liver Lesion ◽  
Focal Liver Lesions ◽  
Liver Lesions ◽  
Preclinical Research ◽  
Post Contrast ◽  
Contrast Enhanced ◽  
B Virus

Contrast-enhanced ultrasound (CEUS) imaging has been a reliable clinical method of detecting three vascular contrast phases and characterizing focal liver lesions. Previous results were all from human (i.e., clinical studies). The main purpose of this study was to extend this to small animals and to investigate the feasibility of using CEUS in preclinical research. Specifically, high-frequency (40 MHz) ultrasound liver imaging with albumin-shelled microbubbles was employed to detect the three vascular contrast phases and characterize focal liver lesions that developed in thirteen Hepatitis B virus X (HBx) transgenic mice at around 14 to 16 months of age. Previous studies indicated that 90–100% incidence of hepatocellular carcinoma (HCC) was observed in HBx transgenic male mice. After injecting the contrast agent, the time-intensity curves (TICs) of focal liver lesions, vessels in focal liver lesions and surrounding liver parenchyma tissues were measured for 30 minutes. The peak of mean intensity relative to the baseline increased 7.36 dB (p<0.02). On the other hand, the mean contrast between the focal liver lesion and the liver parenchyma increased by 7.74 (p<0.05) dB, thus allowing clear detection of the lesion margin. Histopathology investigations confirmed the development of the lesion in these mice. In addition, guidelines of European Federation of Societies for Ultrasound in Medicine and Biology were followed as an attempt to characterize features of the TICs in mice. The arterial phase was defined as 2 to 60 seconds post contrast injection, and the parenchyma phase was defined as the time period from 10 to 30 minutes post contrast injection. Comparing the imaging with the pathology results, the sensitivity, specificity and accuracy of CEUS for the detection of malignant focal liver lesion in HBx transgenic mice were 91%, 100% and 92%. These results demonstrated that high-frequency CEUS imaging potentially can be used for detecting the three vascular contrast phases of malignant focal liver lesions and characterizing malignant focal liver lesions in mice. Thus can be a valuable tool in preclinical research.

scholarly journals Diagnostic Efficacy and Safety of Gadoxetate Disodium vs Gadobenate Dimeglumine in Patients With Known or Suspected Focal Liver Lesions: Results of a Clinical Phase III Study

2019 ◽  
Vol 12 ◽  
pp. 1178623X1982797
Author(s):  
Christoph J Zech ◽  
Carsten Schwenke ◽  
Jan Endrikat
Keyword(s):  
Sensitivity And Specificity ◽  
Gadobenate Dimeglumine ◽  
Phase Iii ◽  
Focal Liver Lesions ◽  
Liver Lesions ◽  
Efficacy And Safety ◽  
Gadoxetate Disodium ◽  
Diagnostic Efficacy ◽  
Post Contrast ◽  
Phase Iii Study

Purpose: The aim of this study is to evaluate the diagnostic efficacy and safety of gadoxetate disodium vs gadobenate dimeglumine in patients with known or suspected focal liver lesions. Methods: This was a prospective, multicenter, double-blind, randomized, inter-individual Phase III study. The primary target—technical efficacy—was already published. Here, secondary efficacy parameters—sensitivity and specificity—and safety in specific patient populations are presented. Patients with suspected or known focal liver lesions scheduled for contrast-enhanced liver magnetic resonance imaging (MRI) were recruited and categorized in 4 a priori specified subgroups: (1) all patients, (2) patients with liver cancer (hepatocellular carcinoma [HCC]), (3) patients with cirrhosis, and (4) patients with HCC + cirrhosis. Dual multi-detector liver computed tomography (CT) served as standard of reference. Results: A total of 295 patients were included. While the overall increase in sensitivity across all 4 patient groups was comparable for gadoxetate disodium (increase from pre- to post-contrast ranging from 6.2% to 9.9%) and gadobenate dimeglumine (ranging from −2.9% to 10.0%), significant differences were seen for some of the subgroups. There was a significantly higher increase in sensitivity for gadoxetate disodium in patients with HCC (7%) and HCC + cirrhosis (12.8%) in comparison with gadobenate dimeglumine. Specificity decreased for both agents: gadoxetate disodium by −2.8% to −6.3% and gadobenate dimeglumine by −3.3% to −8.7%. Gadoxetate showed a significantly lower loss of specificity in all subgroups. Safety was comparable in both groups. Conclusions: Gadoxetate disodium proved to be an effective liver-specific MRI contrast agent. Some distinct advantages over gadobenate dimeglumine were demonstrated in patients with HCC and patients with HCC + liver cirrhosis for sensitivity and specificity in liver lesion detection.

Sign in / Sign up

Export Citation Format

Share Document