Deep Learning-Assisted Diagnosis of Liver Tumors Using Non-Contrast Magnetic Resonance Imaging: A Multi-Center Study

2020 ◽  
Author(s):  
Shihui Zhen ◽  
Weizhi Luo ◽  
Zhiyu Jiang ◽  
Yankai Jiang ◽  
Jihong Sun ◽  
...  
2016 ◽  
Vol 37 (3) ◽  
pp. 1108-1119 ◽  
Author(s):  
Enedino Hernández-Torres ◽  
Nora Kassner ◽  
Nils Daniel Forkert ◽  
Luxi Wei ◽  
Vanessa Wiggermann ◽  
...  

Measurements of cerebral perfusion using dynamic susceptibility contrast magnetic resonance imaging rely on the assumption of isotropic vascular architecture. However, a considerable fraction of vessels runs in parallel with white matter tracts. Here, we investigate the effects of tissue orientation on dynamic susceptibility contrast magnetic resonance imaging. Tissue orientation was measured using diffusion tensor imaging and dynamic susceptibility contrast was performed with gradient echo planar imaging. Perfusion parameters and the raw dynamic susceptibility contrast signals were correlated with tissue orientation. Additionally, numerical simulations were performed for a range of vascular volumes of both the isotropic vascular bed and anisotropic vessel components, as well as for a range of contrast agent concentrations. The effect of the contrast agent was much larger in white matter tissue perpendicular to the main magnetic field compared to white matter parallel to the main magnetic field. In addition, cerebral blood flow and cerebral blood volume were affected in the same way with angle-dependent variations of up to 130%. Mean transit time and time to maximum of the residual curve exhibited weak orientation dependency of 10%. Numerical simulations agreed with the measured data, showing that one-third of the white matter vascular volume is comprised of vessels running in parallel with the fibre tracts.


2012 ◽  
Vol 32 (suppl_1) ◽  
Author(s):  
Jie Sun ◽  
Niranjan Balu ◽  
Dongxiang Xu ◽  
Daniel Hippe ◽  
Thomas Hatsukami ◽  
...  

Background: Carotid magnetic resonance imaging (MRI) is emerging as an effective tool for monitoring plaque progression noninvasively. However, data from multi-center studies are scarce. Intraplaque hemorrhage (IPH) has been shown to promote plaque growth. In this multi-center study over 6 months, we sought to study plaque progression in subjects with and without IPH. Methods: As the placebo arm of a multi-center clinical trial, 59 subjects with 16-79% carotid stenosis by ultrasound and a lipid core (LC) on baseline MRI completed a follow-up MRI at the end of a 6-month period. Thirty-nine (66.1%) were on concurrent rosuvastatin therapy. Lumen, wall and LC volumes, and IPH presence were measured on both scans blinded to time sequence at a core lab. Plaque progression was calculated as annualized changes within the common coverage between scans using the carotid bifurcation as a landmark. Results: IPH was present on 14 slices from 3 (5.1%) subjects at baseline. Subjects without IPH (n=56) showed a significant reduction in LC volume (p=0.031), a trend towards reduction in wall volume (p=0.215) and no apparent change in lumen volume (p=0.910). Although all subjects with IPH were on rosuvastatin during the study period, compared to subjects without IPH, they had increased LC (62.9±46.2 mm3/year vs. -8.8±29.9 mm3/year, p<0.001) and wall (100.1±78.1 mm3/year vs. -12.7±75.8 mm3/year, p=0.015) volumes, but decreased lumen volume (-93.4±114.7 mm3/year vs. 0.90±59.7 mm3/year, p=0.014). Conclusion: This multi-center study over 6 months demonstrated significant regression in LC volume in plaques without IPH. By contrast, plaques with IPH may be poorly controlled despite statin therapy.


Sign in / Sign up

Export Citation Format

Share Document