Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

Background and Purpose—The authors present an overview of the current evidence and management recommendations for evaluation and treatment of adults with acute ischemic stroke. The intended audienc...

/pdf/guidelines-for-the-early-management-of-patients-with-acute-19udbft6e7.pdf

Guidelines for the Early Management of Patients With Acute Ischemic Stroke A Guideline for Healthcare Professionals From the American Heart Association/American Stroke Association

We present a technique for automatically assigning a neuroanatomical label to each location on a cortical surface model based on probabilistic information estimated from a manually labeled training set. This procedure incorporates both geometric information derived from the cortical model, and neuroanatomical convention, as found in the training set. The result is a complete labeling of cortical sulci and gyri. Examples are given from two different training sets generated using different neuroanatomical conventions, illustrating the flexibility of the algorithm. The technique is shown to be comparable in accuracy to manual labeling.

/pdf/automatically-parcellating-the-human-cerebral-cortex-16g7uhc9ep.pdf

Automatically Parcellating the Human Cerebral Cortex

A new peak-based quantitative spectra matching method using affinity matrix spectral analysis is proposed. An affinity matrix is generated to describe similarity between 2D HSQC peaks given their spatial location. Application of the approach gives best matched peaks of two different spectra with the same or different number of peaks. Results were validated against a previously published method. The new algorithm was found to be an order of magnitude faster in finding matched peaks, in comparison to our previously reported technique. This speed-up allows large number of peaks to be matched quickly, meaning that structures of high complexity can be compared across large structure databases. Matching examples are provided for 15N HSQC spectra of protein samples, which we use to establish performance.

A Rapid Procedure for Spectral Similarity Matching of Heteronuclear Single Quantum Coherence Spectra

To the Editor:

We read with great interest the article by de Abreu et al1 on the topic of identifying the stroke mechanism in patients with sinus rhythm. These investigators raise 2 important issues: (1) the need to identify the mechanisms of stroke, and (2) therapy of patients with abnormal cardiac echo findings. The rationale for this study appears to be a lack of emphasis in the current guidelines that echocardiography is “an essential test.”2,3 They have identified a significant proportion of hospitalized stroke patients with some echocardiographic abnormalities. However, based only on a prevalence study of echocardiographic features, they draw rather strong conclusions regarding the need for routine echocardiography in acute ischemic stroke patients.

We agree that echocardiography can assist in clarifying the mechanism of ischemic stroke. However, we dispute the claim that echocardiography is an essential test in all ischemic stroke patients including those in sinus rhythm. The need for routine echocardiography ischemic stroke needs to be supported by strong evidence for a benefit from therapy, namely prophylactic anticoagulation. Of all the cardiac conditions listed in Table 2 of the article, only anterior wall dyskinesis or reduced ejection fraction from a recent anterior myocardial infarction can justify the use of warfarin, albeit for 3 months only.4 Although there is level I evidence that anticoagulation prevents stroke in …

Therapeutic Implications for Routine Transthoracic Echocardiography in Acute Ischemic Stroke Patients

This data set contains a Turbo Spin Echo (TSE) model of the human brain in a slab acquired across the hippocampus

David C. Reutens

Papers

A Rapid Procedure for Spectral Similarity Matching of Heteronuclear Single Quantum Coherence Spectra

Therapeutic Implications for Routine Transthoracic Echocardiography in Acute Ischemic Stroke Patients

Turbo Spin Echo average 7T model

Field strength influences on gradient recalled echo MRI signal compartment frequency shifts.

Measures of Subjective Memory for People with Epilepsy: A Systematic Review of Measurement Properties