Extracting useful information from high-dimensional data is an important focus of today's statistical research and practice. Penalized loss function minimization has been shown to be effective for this task both theoretically and empirically. With the virtues of both regularization and sparsity, the L1-penalized squared error minimization method Lasso has been popular in regression models and beyond.In this paper, we combine different norms including L1 to form an intelligent penalty in order to add side information to the fitting of a regression or classification model to obtain reasonable estimates. Specifically, we introduce the Composite Absolute Penalties (CAP) family, which allows given grouping and hierarchical relationships between the predictors to be expressed. CAP penalties are built by defining groups and combining the properties of norm penalties at the across-group and within-group levels. Grouped selection occurs for nonoverlapping groups. Hierarchical variable selection is reached by defining groups with particular overlapping patterns. We propose using the BLASSO and cross-validation to compute CAP estimates in general. For a subfamily of CAP estimates involving only the L1 and L∞ norms, we introduce the iCAP algorithm to trace the entire regularization path for the grouped selection problem. Within this subfamily, unbiased estimates of the degrees of freedom (df) are derived so that the regularization parameter is selected without crossvalidation. CAP is shown to improve on the predictive performance of the LASSO in a series of simulated experiments, including cases with p ≫ n and possibly mis-specified groupings. When the complexity of a model is properly calculated, iCAP is seen to be parsimonious in the experiments.

No abstract

A numerical model based on one-dimensional balance laws and ad hoc zero-dimensional boundary conditions is tested against experimental data. The study concentrates on the circle of Willis, a vital subnetwork of the cerebral vasculature. The main goal is to obtain efficient and reliable numerical tools with predictive capabilities. The flow is assumed to obey the Navier-Stokes equations, while the mechanical reactions of the arterial walls follow a viscoelastic model. Like many previous studies, a dimension reduction is performed through averaging. Unlike most previous work, the resulting model is both calibrated and validated against in vivo data, more precisely transcranial Doppler data of cerebral blood velocity. The network considered has three inflow vessels and six outflow vessels. Inflow conditions come from the data, while outflow conditions are modeled. Parameters in the outflow conditions are calibrated using a subset of the data through ensemble Kalman filtering techniques. The rest of the data is used for validation. The results demonstrate the viability of the proposed approach.

Cerebral autoregulation (CA) is an most important mechanism responsible for the relatively constant blood flow supply to brain when cerebral perfusion pressure varies. Its assessment in nonacute cases has been relied on the quantification of the relationship between noninvasive beat-to-beat blood pressure (BP) and blood flow velocity (BFV). To overcome the nonstationary nature of physiological signals such as BP and BFV, a computational method called multimodal pressure-flow (MMPF) analysis was recently developed to study the nonlinear BP-BFV relationship during the Valsalva maneuver (VM). The present study aimed to determine (i) whether this method can estimate autoregulation from spontaneous BP and BFV fluctuations during baseline rest conditions; (ii) whether there is any difference between the MMPF measures of autoregulation based on intra-arterial BP (ABP) and based on cerebral perfusion pressure (CPP); and (iii) whether the MMPF method provides reproducible and reliable measure for noninvasive assessment of autoregulation. To achieve these aims, we analyzed data from existing databases including: (i) ABP and BFV of 12 healthy control, 10 hypertensive, and 10 stroke subjects during baseline resting conditions and during the Valsalva maneuver, and (ii) ABP, CPP, and BFV of 30 patients with traumatic brain injury (TBI) who were being paralyzed, sedated, and ventilated. We showed that autoregulation in healthy control subjects can be characterized by specific phase shifts between BP and BFV oscillations during the Valsalva maneuver, and the BP-BFV phase shifts were reduced in hypertensive and stroke subjects (P < 0.01), indicating impaired autoregulation. Similar results were found during baseline condition from spontaneous BP and BFV oscillations. The BP-BFV phase shifts obtained during baseline and during VM were highly correlated (R > 0.8, P < 0.0001), showing no statistical difference (pairedt test P > 0.47). In TBI patients there were strong correlations between phases of ABP and CPP oscillations (R = 0.99, P < 0.0001) and, thus, between ABP-BFV and CPP-BFV phase shifts (P < 0.0001, R = 0.76). By repeating the MMPF 4 times on data of TBI subjects, each time on a selected cycle of spontaneous BP and BFV oscillations, we showed that MMPF had better reproducibility than traditional autoregulation index. These results indicate that the MMPF method, based on instantaneous phase relationships between cerebral blood flow velocity and peripheral blood pressure, has better performance than the traditional standard method, and can reliably assess cerebral autoregulation dynamics from ambulatory blood pressure and cerebral blood flow during supine rest conditions.

OBJECTIVETo investigate the effects of inflammation on perfusion regulation and brain volumes in type 2 diabetes.RESEARCH DESIGN AND METHODSA total of 147 subjects (71 diabetic and 76 nondiabetic, aged 65.2 ± 8 years) were studied using 3T anatomical and continuous arterial spin labeling magnetic resonance imaging. Analysis focused on the relationship between serum soluble vascular and intercellular adhesion molecules (sVCAM and sICAM, respectively, both markers of endothelial integrity), regional vasoreactivity, and tissue volumes.RESULTSDiabetic subjects had greater vasoconstriction reactivity, more atrophy, depression, and slower walking. Adhesion molecules were specifically related to gray matter atrophy (P = 0.04) and altered vasoreactivity (P = 0.03) in the diabetic and control groups. Regionally, sVCAM and sICAM were linked to exaggerated vasoconstriction, blunted vasodilatation, and increased cortical atrophy in the frontal, temporal, and parietal lobes (P = 0.04–0.003). sICAM correlated with worse functionality.CONCLUSIONSDiabetes is associated with cortical atrophy, vasoconstriction, and worse performance. Adhesion molecules, as markers of vascular health, have been indicated to contribute to altered vasoregulation and atrophy.

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.

In this paper, we present two new algorithms for cell image segmentation. First, we demonstrate that pixel classification-based color image segmentation in color space is equivalent to performing segmentation on grayscale image through thresholding. Based on this result, we develop a supervised learning-based two-step procedure for color cell image segmentation, where color image is first mapped to grayscale via a transform learned through supervised learning, thresholding is then performed on the grayscale image to segment objects out of background. Experimental results show that the supervised learning-based two-step procedure achieved a boundary disagreement (mean absolute distance) of 0.85 while the disagreement produced by the pixel classification-based color image segmentation method is 3.59. Second, we develop a new marker detection algorithm for watershed-based separation of overlapping or touching cells. The merit of the new algorithm is that it employs both photometric and shape information and combines the two naturally in the framework of pattern classification to provide more reliable markers. Extensive experiments show that the new marker detection algorithm achieved 0.4% and 0.2% over-segmentation and under-segmentation, respectively, while reconstruction-based method produced 4.4% and 1.1% over-segmentation and under-segmentation, respectively.

Objective: It is unknown if impaired cerebral vasoreactivity recovers after ischemic stroke, and whether it compromises perfusion in regions surrounding infarct and other vascular territories. We investigated the regional differences in CO 2 vasoreactivity (CO 2 VR) and their relationships to peri-infarct T2 hyperintensities (PIHs), chronic infarct volumes, and clinical outcomes. Methods:We studied 39 subjects with chronic large middle cerebral artery territory infarcts and 48 matched controls. Anatomic and three-dimensional continuous arterial spin labeling imaging at 3-Tesla MRI were used to measure regional cerebral blood flow (CBF) and CO 2 VR during normocapnia, hypercapnia, and hypocapnia in main arteries distributions. Results:Stroke patients showed a significantly lower augmentation of blood flow at increased CO 2 but greater reduction of blood flow with decreased CO 2 than the control group. This altered vasoregulatory response was observed both ipsilateral and contralateral to the stroke. Lower CO 2 VR on the stroke side was associated with PIHs, greater infarct volume, and worse outcomes. The cases with PIHs (n ϭ 27) had lower CBF during all conditions bilaterally (p Ͻ 0.0001) compared to cases with infarct only. Conclusions: Perfusion augmentation is inadequate in multiple vascular territories in patients withlarge artery ischemic infarcts, but vasoconstriction is preserved. Peri-infarct T2 hyperintensities are associated with lower blood flow. Strategies aimed to preserve vasoreactivity after an ischemic stroke should be tested for their effect on long-term outcomes. Neurology ® 2009;72:643-649 GLOSSARY ACA ϭ anterior cerebral artery; ADC ϭ apparent diffusion coefficient; BP ϭ blood pressure; CASL ϭ continuous arterial spin labeling; CBF ϭ cerebral blood flow; CO 2 VR ϭ CO 2 vasoreactivity; DWI ϭ diffusion-weighted image; FLAIR ϭ fluidattenuated inversion recovery; FOV ϭ field of view; GM ϭ gray matter; LDL ϭ low-density lipoprotein; MCA ϭ middle cerebral artery; MP-RAGE ϭ magnetization prepared rapid gradient echo; mRS ϭ modified Rankin Scale; NIHSS ϭ NIH Stroke Scale; PCA ϭ posterior cerebral artery; PIHs ϭ peri-infarct T2 hyperintensities; TE ϭ echo time; TI ϭ inversion time; TR ϭ repetition time; WBC ϭ white blood cell; WM ϭ white matter.Perfusion in regions surrounding ischemic areas is associated with recovery.1 Cerebral vasoregulation maintains steady cerebral blood flow (CBF) in response to changes in CO 2 , but systemic blood pressure (BP) is compromised by microvascular disease and further impaired by stroke.2 It is not known whether cerebral vasoregulation recovers in older people with ischemic stroke or whether vascular beds in the infarcted hemisphere remain challenged to maintain perfusion. Unrecognized brain infarctions and peri-infarct hyperintensities (PIHs) are common MRI findings during later stages after stroke.3 It is unknown if the distribution of impaired vasoreactivity extends beyond the infarct region into surrounding gray and white matter and compromises perfusion i...