Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it provides an imperative and Pythonic programming style that supports code as a model, makes debugging easy and is consistent with other popular scientific computing libraries, while remaining efficient and supporting hardware accelerators such as GPUs. In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture. We emphasize that every aspect of PyTorch is a regular Python program under the full control of its user. We also explain how the careful and pragmatic implementation of the key components of its runtime enables them to work together to achieve compelling performance. We demonstrate the efficiency of individual subsystems, as well as the overall speed of PyTorch on several common benchmarks.
We present a modeling framework designed for patient-specific computational hemodynamics to be performed in the context of large-scale studies. The framework takes advantage of the integration of image processing, geometric analysis and mesh generation techniques, with an accent on full automation and high-level interaction. Image segmentation is performed using implicit deformable models taking advantage of a novel approach for selective initialization of vascular branches, as well as of a strategy for the segmentation of small vessels. A robust definition of centerlines provides objective geometric criteria for the automation of surface editing and mesh generation. The framework is available as part of an open-source effort, the Vascular Modeling Toolkit, a first step towards the sharing of tools and data which will be necessary for computational hemodynamics to play a role in evidence-based medicine.
Background and Purpose-That certain vessels might be at so-called geometric risk of atherosclerosis rests on assumptions of wide interindividual variations in disturbed flow and of a direct relationship between disturbed flow and lumen geometry. In testing these often-implicit assumptions, the present study aimed to determine whether investigations of local risk factors in atherosclerosis can indeed rely on surrogate geometric markers of disturbed flow. Methods-Computational fluid dynamics simulations were performed on carotid bifurcation geometries derived from MRI of 25 young adults. Disturbed flow was quantified as the surface area exposed to low and oscillatory shear beyond objectively-defined thresholds. Interindividual variations in disturbed flow were contextualized with respect to effects of uncertainties in imaging and geometric reconstruction. Relationships between disturbed flow and various geometric factors were tested via multiple regression. Results-Relatively wide variations in disturbed flow were observed among the 50 vessels. Multiple regression revealed a significant (PϽ0.002) relationship between disturbed flow and both proximal area ratio (Ϸ0.5) and bifurcation tortuosity (ϷϪ0.4), but not bifurcation angle, planarity, or distal area ratio. These findings were shown to be insensitive to assumptions about the flow conditions and to the choice of disturbed flow indicator and threshold. Conclusions-Certain geometric features of the young adult carotid bifurcation are robust surrogate markers of its exposure to disturbed flow. It may therefore be reasonable to consider large-scale retrospective or prospective imaging studies of local risk factors for atherosclerosis without the need for time-consuming and expensive flow imaging or CFD studies.
In ADPKD patients, 6-month somatostatin therapy is safe and may slow renal volume expansion. This may reflect an inhibited growth in particular of smallest cysts beyond the detection threshold of CT scan evaluation. Whether this effect may prove renoprotective in the long term should be tested in additional trials of longer duration.
There is well-documented evidence that vascular geometry has a major impact in blood flow dynamics and consequently in the development of vascular diseases, like atherosclerosis and cerebral aneurysmal disease. The study of vascular geometry and the identification of geometric features associated with a specific pathological condition can therefore shed light into the mechanisms involved in the pathogenesis and progression of the disease. Although the development of medical imaging technologies is providing increasing amounts of data on the three-dimensional morphology of the in vivo vasculature, robust and objective tools for quantitative analysis of vascular geometry are still lacking. In this paper, we present a framework for the geometric analysis of vascular structures, in particular for the quantification of the geometric relationships between the elements of a vascular network based on the definition of centerlines. The framework is founded upon solid computational geometry criteria, which confer robustness of the analysis with respect to the high variability of in vivo vascular geometry. The techniques presented are readily available as part of the VMTK, an open source framework for image segmentation, geometric characterization, mesh generation and computational hemodynamics specifically developed for the analysis of vascular structures. As part of the Aneurisk project, we present the application of the present framework to the characterization of the geometric relationships between cerebral aneurysms and their parent vasculature.
Background and Purpose-Retrospective analysis of clinical data has demonstrated major variations in carotid bifurcation geometry, in support of the notion that an individual's vascular anatomy or local hemodynamics may influence the development of atherosclerosis. On the other hand, anecdotal evidence suggests that vessel geometry is more homogenous in youth, which would tend to undermine this geometric risk hypothesis. The purpose of our study was to test whether the latter is indeed the case. Methods-Cross-sectional images of the carotid bifurcations of 25 young adults (24Ϯ4 years) and a control group of 25 older subjects (63Ϯ10 years) were acquired via MRI. Robust and objective techniques were developed to automatically characterize the 3D geometry of the bifurcation and the relative dimensions of the internal, external, and common carotid arteries (ICA, ECA, and CCA, respectively).
A variety of hemodynamic wall parameters (HWP) has been proposed over the years to quantify hemodynamic disturbances as potential predictors or indicators of vascular wall dysfunction. The aim of this study was to determine whether some of these might, for practical purposes, be considered redundant. Image-based computational fluid dynamics simulations were carried out for N=50 normal carotid bifurcations reconstructed from magnetic resonance imaging. Pairwise Spearman correlation analysis was performed for HWP quantifying wall shear stress magnitudes, spatial and temporal gradients, and harmonic contents. These were based on the spatial distributions of each HWP and, separately, the amount of the surface exposed to each HWP beyond an objectively-defined threshold. Strong and significant correlations were found among the related trio of time-averaged wall shear stress magnitude (TAWSS), oscillatory shear index (OSI), and relative residence time (RRT). Wall shear stress spatial gradient (WSSG) was strongly and positively correlated with TAWSS. Correlations with Himburg and Friedman's dominant harmonic (DH) parameter were found to depend on how the wall shear stress magnitude was defined in the presence of flow reversals. Many of the proposed HWP were found to provide essentially the same information about disturbed flow at the normal carotid bifurcation. RRT is recommended as a robust single metric of low and oscillating shear. On the other hand, gradient-based HWP may be of limited utility in light of possible redundancies with other HWP, and practical challenges in their measurement. Further investigations are encouraged before these findings should be extrapolated to other vascular territories.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.