method-for-simultaneous-fmrieeg-data-collection-during-focused

Method for Simultaneous fMRI/EEG Data Collection during a Focused Attention Suggestion for Differential Thermal Sensation

In the present work, we demonstrate a method for concurrent collection of EEG/fMRI data. In our setup, EEG data are collected using a high-density ...

University of California, Los Angeles

The analysis of fMRI data is challenging because they consist generally of a relatively modest signal contained in a high-dimensional space: a single scan can contain millions of voxel recordings over space and time. We present a method for classification and discrimination among fMRI that is based on modeling the scans as distance matrices, where each matrix measures the divergence of spatial network signals that fluctuate over time. We used single-subject independent components analysis (ICA), decomposing an fMRI scan into a set of statistically independent spatial networks, to extract spatial networks and time courses from each subject that have unique relationship with the other components within that subject. Mathematical properties of these relationships reveal information about the infrastructure of the brain by measuring the interaction between and strength of the components. Our technique is unique, in that it does not require spatial alignment of the scans across subjects. Instead, the classifications are made solely on the temporal activity taken by the subject's unique ICs. Multiple scans are not required and multivariate classification is implementable, and the algorithm is effectively blind to the subject-uniform underlying task paradigm. Classification accuracy of up to 90% was realized on a resting-scanned schizophrenia/normal dataset and a tasked multivariate Alzheimer's/old/young dataset. We propose that the ICs represent a plausible set of imaging basis functions consistent with network-driven theories of neural activity in which the observed signal is an aggregate of independent spatial networks having possibly dependent temporal activity.

Classification of spatially unaligned fMRI scans.

Nocturnal reflux is a largely undiagnosed and unmanaged condition predisposing to multiple esophageal complications. We evaluated the effects of rabeprazole and pantoprazole on nocturnal intragastric pH and gastric acid output during Day 1 of therapy following the consumption of standard meals.

Comparative efficacy of rabeprazole and pantoprazole in the control of nocturnal Acid output and intragastric acidity.

Machine learning methods have been applied to classifying fMRI scans by studying locations in the brain that exhibit temporal intensity variation between groups, frequently reporting classification accuracy of 90% or better. Although empirical results are quite favorable, one might doubt the ability of classification methods to withstand changes in task ordering and the reproducibility of activation patterns over runs, and question how much of the classification machines' power is due to artifactual noise versus genuine neurological signal. To examine the true strength and power of machine learning classifiers we create and then deconstruct a classifier to examine its sensitivity to physiological noise, task reordering, and across-scan classification ability. The models are trained and tested both within and across runs to assess stability and reproducibility across conditions. We demonstrate the use of independent components analysis for both feature extraction and artifact removal and show that removal of such artifacts can reduce predictive accuracy even when data has been cleaned in the preprocessing stages. We demonstrate how mistakes in the feature selection process can cause the cross-validation error seen in publication to be a biased estimate of the testing error seen in practice and measure this bias by purposefully making flawed models. We discuss other ways to introduce bias and the statistical assumptions lying behind the data and model themselves. Finally we discuss the complications in drawing inference from the smaller sample sizes typically seen in fMRI studies, the effects of small or unbalanced samples on the Type 1 and Type 2 error rates, and how publication bias can give a false confidence of the power of such methods. Collectively this work identifies challenges specific to fMRI classification and methods affecting the stability of models.

Common component classification: what can we learn from machine learning?

Independent component analysis (ICA) is a popular method for the analysis of functional magnetic resonance imaging (fMRI) signals that is capable of revealing connected brain systems of functional significance. To be computationally tractable, estimating the independent components (ICs) inevitably requires one or more dimension reduction steps. Whereas most algorithms perform such reductions in the time domain, the input data are much more extensive in the spatial domain, and there is broad consensus that the brain obeys rules of localization of function into regions that are smaller in number than the number of voxels in a brain image. These functional units apparently reorganize dynamically into networks under different task conditions. Here we develop a new approach to ICA, producing group results by bagging and clustering over hundreds of pooled single-subject ICA results that have been projected to a lower-dimensional subspace. Averages of anatomically based regions are used to compress the single subject-ICA results prior to clustering and resampling via bagging. The computational advantages of this approach make it possible to perform group-level analyses on datasets consisting of hundreds of scan sessions by combining the results of within-subject analysis, while retaining the theoretical advantage of mimicking what is known of the functional organization of the brain. The result is a compact set of spatial activity patterns that are common and stable across scan sessions and across individuals. Such representations may be used in the context of statistical pattern recognition supporting real-time state classification.

Large Sample Group Independent Component Analysis of Functional Magnetic Resonance Imaging Using Anatomical Atlas-Based Reduction and Bootstrapped Clustering.

Interictal electroencephalography (EEG) has clinically meaningful limitations in its sensitivity and specificity in the diagnosis of epilepsy because of its dependence on the occurrence of epileptiform discharges. We have developed a computer-aided diagnostic (CAD) tool that operates on the absolute spectral energy of the routine EEG and has both substantially higher sensitivity and negative predictive value than the identification of interictal epileptiform discharges. Our approach used a multilayer perceptron to classify 156 patients admitted for video-EEG monitoring. The patient population was diagnostically diverse; 87 were diagnosed with either generalized or focal seizures. The remainder of the patients were diagnosed with nonepileptic seizures. The sensitivity was 92% (95% confidence interval [CI] 85-97%) and the negative predictive value was 82% (95% CI 67-92%). We discuss how these findings suggest that this CAD can be used to supplement event-based analysis by trained epileptologists.

Automated diagnosis of epilepsy using EEG power spectrum.

&#x53D1;&#x4F5C;&#x95F4;&#x671F;&#x8111;&#x7535;&#x56FE; &#xFF08;EEG&#xFF09; &#x7531;&#x4E8E;&#x5176;&#x4F9D;&#x8D56;&#x7684;&#x75EB;&#x6837;&#x653E;&#x7535;&#x53D1;&#x751F;&#x6709;&#x4E34;&#x5E8A;&#x610F;&#x4E49;&#x9650;&#x5236;&#x5728;&#x5176;&#x654F;&#x611F;&#x6027;&#x548C;&#x7279;&#x5F02;&#x6027;&#x5BF9;&#x766B;&#x75EB;&#x7684;&#x8BCA;&#x65AD;&#x3002;&#x6211;&#x4EEC;&#x5F00;&#x53D1;&#x4E86;&#x4E00;&#x4E2A;&#x8BA1;&#x7B97;&#x673A;&#x8F85;&#x52A9;&#x8BCA;&#x65AD; (CAD) &#x5DE5;&#x5177;&#xFF0C;&#x5BF9;&#x7EDD;&#x5BF9;&#x5149;&#x8C31;&#x80FD;&#x91CF;&#x7684;&#x5E38;&#x89C4;&#x8111;&#x7535;&#x56FE;&#x8FD0;&#x8425;&#xFF0C;&#x5E76;&#x62E5;&#x6709;&#x8F83;&#x9AD8;&#x7684;&#x7075;&#x654F;&#x5EA6;&#x548C;&#x6D88;&#x6781;&#x9884;&#x6D4B;&#x503C;&#x6BD4;&#x53D1;&#x4F5C;&#x95F4;&#x75EB;&#x6837;&#x653E;&#x7535;&#x7684;&#x9274;&#x5B9A;&#x3002;&#x6211;&#x4EEC;&#x7684;&#x65B9;&#x6CD5;&#x7528;&#x4E8E;&#x591A;&#x5C42;&#x611F;&#x77E5;&#x5668;&#x5206;&#x7C7B;&#x89C6;&#x9891;&#x8111;&#x7535;&#x76D1;&#x6D4B; 156 &#x75C5;&#x4EBA;&#x3002;&#x75C5;&#x4EBA;&#x7684;&#x4EBA;&#x53E3;&#x662F;&#x7167;&#x5C04;&#x591A;&#x79CD;&#x591A;&#x6837; &#xFF1B;87 &#x88AB;&#x8BCA;&#x65AD;&#x60A3;&#x6709;&#x5C40;&#x7076;&#x6027;&#x6216;&#x5E7F;&#x4E49;&#x7684;&#x7F09;&#x83B7;&#x91CF;&#x3002;&#x5176;&#x4F59;&#x7684;&#x75C5;&#x4EBA;&#x88AB;&#x8BCA;&#x65AD;&#x4E3A;&#x975E;&#x766B;&#x75EB;&#x53D1;&#x4F5C;&#x3002;&#x7075;&#x654F;&#x5EA6;&#x662F; 92%&#xFF08;95%&#x7F6E;&#x4FE1;&#x533A;&#x95F4; [CI] 85-97%&#xFF09; &#x548C;&#x9634;&#x6027;&#x9884;&#x6D4B;&#x503C;&#x4E3A; 82%&#xFF08;95%CI 67 92%&#xFF09;&#x3002;&#x6211;&#x4EEC;&#x5C06;&#x8BA8;&#x8BBA;&#x5982;&#x4F55;&#x8FD9;&#x4E9B;&#x7814;&#x7A76;&#x7ED3;&#x679C;&#x8868;&#x660E;&#x6B64; CAD &#x53EF;&#x7528;&#x4E8E;&#x8865;&#x5145;&#x57FA;&#x4E8E;&#x4E8B;&#x4EF6;&#x7684;&#x5206;&#x6790;&#x7531;&#x53D7;&#x8FC7;&#x8BAD;&#x7EC3;&#x7684; epileptologists&#x3002;

&#x81EA;&#x52A8;&#x7684;&#x8BCA;&#x65AD;&#x7684;&#x766B;&#x75EB;&#x8111;&#x7535;&#x56FE;&#x529F;&#x7387;&#x8C31;&#x3002;

Intercritiques &eacute;lectroenc&eacute;phalographie (EEG) a des limitations cliniquement significatives dans sa sensibilit&eacute; et sp&eacute;cificit&eacute; dans le diagnostic de l&#39;&eacute;pilepsie en raison de sa d&eacute;pendance sur l&#39;occurrence de d&eacute;charges &eacute;pileptiformes. Nous avons d&eacute;velopp&eacute; un outil de diagnostic assist&eacute; par ordinateur (CAD) qui exploite l&#39;&eacute;nergie spectrale absolue de la routine EEG et a la fois sensiblement plus grande sensibilit&eacute; et une valeur pr&eacute;dictive n&eacute;gative que l&#39;identification des d&eacute;charges &eacute;pileptiformes intercritiques. Notre approche a utilis&eacute; un perceptron multicouche pour classer les 156 patients admis pour la surveillance de vid&eacute;o-EEG. La population de patients &eacute;tait diagnostique diverse ; 87 ont &eacute;t&eacute; diagnostiqu&eacute;s avec des convulsions g&eacute;n&eacute;ralis&eacute;es ou focales. Le reste des patients ont &eacute;t&eacute; diagnostiqu&eacute; avec des convulsions &eacute;pileptiques. La sensibilit&eacute; &eacute;tait de 92 % (intervalle de confiance de 95 % [IC] 85-97 %) et la valeur pr&eacute;dictive n&eacute;gative &eacute;tait de 82 % (95 % CI 67-92 %). Nous discutons comment ces r&eacute;sultats sugg&egrave;rent que cette CAD peut &ecirc;tre utilis&eacute; pour compl&eacute;ter l&#39;analyse bas&eacute;e sur des &eacute;v&eacute;nements par les &eacute;pileptologues form&eacute;s.

Automatis&eacute; de diagnostic de l&#39;&eacute;pilepsie en utilisant le spectre de puissance d&#39;EEG.

Interiktale Elektroenzephalographie (EEG) hat klinisch sinnvolle Einschr&auml;nkungen in seiner Sensitivit&auml;t und Spezifit&auml;t bei der Diagnose von Epilepsie aufgrund der Abh&auml;ngigkeit von dem Vorkommen des Epileptiform Entladungen. Wir haben eine computergest&uuml;tzte Diagnose (CAD)-Tool entwickelt, das auf die absolute spektrale Energie der Routine-EEG und hat wesentlich h&ouml;here Sensitivit&auml;t und negativen Vorhersagewert als die Identifizierung von interiktale Epileptiform Entladungen. Unser Ansatz verwendet eine mehrschichtige Perceptron, um 156 Patienten zugelassen f&uuml;r Video-EEG-&Uuml;berwachung zu klassifizieren. Die Patientengruppe war diagnostisch vielf&auml;ltig; 87 wurden generalisierte oder fokale Anf&auml;lle diagnostiziert. Der Rest der Patienten wurden mit nonepileptic Anf&auml;lle diagnostiziert. Die Empfindlichkeit wurde 92 % (95 % Konfidenzintervall [CI] 85-97 %) und der negative Vorhersagewert war 82 % (95 % CI 67-92 %). Wir diskutieren, wie diese Forschungsergebnisse legen nahe, diese CAD kann verwendet werden um ereignisbasierte Analyse zu erg&auml;nzen durch ausgebildete Epileptologists.

Automatisierte Diagnose der Epilepsie mit EEG-Leistungsspektrum.

Interittale elettroencefalografia (EEG) &egrave; clinicamente significative limitazioni nella sua sensibilit&agrave; e specificit&agrave; nella diagnosi di epilessia a causa della sua dipendenza sull&#39;occorrenza degli scarichi epileptiform. Abbiamo sviluppato uno strumento di diagnostica computerizzata (CAD) che opera sull&#39;assoluta energia spettrale dell&#39;EEG di routine e ha sia sostanzialmente pi&ugrave; alta sensibilit&agrave; e valore predittivo negativo rispetto l&#39;identificazione degli scarichi epileptiform interictali. Il nostro approccio utilizzato un percettrone multistrato per classificare 156 pazienti ricoverati per il monitoraggio video-EEG. La popolazione di pazienti era diagnosticamente diversificata; 87 sono stati diagnosticati con convulsioni focali o generalizzate. Il resto dei pazienti sono stato diagnosticato con convulsioni nonepileptic. La sensibilit&agrave; era 92% (95% intervallo di confidenza [CI] 85-97%) e il valore predittivo negativo era 82% (95% CI 67-92%). Discutiamo di come questi risultati suggeriscono che questo CAD pu&ograve; essere utilizzato per integrare l&#39;analisi basata su evento di epileptologists addestrato.

Automatizzato diagnosi di epilessia utilizzando lo spettro di potenza EEG.

&#x767A;&#x4F5C;&#x9593;&#x6B20;&#x671F;&#x8133;&#x6CE2; (EEG) &#x81E8;&#x5E8A;&#x7684;&#x306B;&#x6709;&#x610F;&#x7FA9;&#x306A;&#x5236;&#x9650;&#x305D;&#x306E;&#x611F;&#x5EA6;&#x3068;&#x7279;&#x7570;&#x6027;&#x3066;&#x3093;&#x304B;&#x3093;&#x306E;&#x8A3A;&#x65AD;&#x306B;&#x304A;&#x3051;&#x308B;&#x3066;&#x3093;&#x304B;&#x3093;&#x653E;&#x96FB;&#x306E;&#x767A;&#x751F;&#x306B;&#x4F9D;&#x5B58;&#x306E;&#x305F;&#x3081;&#x304C;&#x3042;&#x308A;&#x307E;&#x3059;&#x3002;&#x6211;&#x3005; &#x306F;&#x3001;&#x30EB;&#x30FC;&#x30C1;&#x30F3;&#x306E;&#x8133;&#x6CE2;&#x306E;&#x7D76;&#x5BFE;&#x30B9;&#x30DA;&#x30AF;&#x30C8;&#x30EB;&#x306E;&#x30A8;&#x30CD;&#x30EB;&#x30AE;&#x30FC;&#x3067;&#x52D5;&#x4F5C;&#x3057;&#x3001;&#x5927;&#x5E45;&#x306B;&#x9AD8;&#x3044;&#x611F;&#x5EA6;&#x3068;&#x767A;&#x4F5C;&#x9593;&#x6B20;&#x671F;&#x3066;&#x3093;&#x304B;&#x3093;&#x653E;&#x96FB;&#x306E;&#x540C;&#x5B9A;&#x3088;&#x308A;&#x306E;&#x8CA0;&#x306E;&#x4E88;&#x6E2C;&#x5024;&#x306E;&#x4E21;&#x65B9;&#x304C;&#x3042;&#x308A;&#x307E;&#x3059;&#x30B3;&#x30F3;&#x30D4;&#x30E5;&#x30FC;&#x30BF;&#x30FC;&#x652F;&#x63F4;&#x8A3A;&#x65AD; (CAD) &#x30C4;&#x30FC;&#x30EB;&#x3092;&#x958B;&#x767A;&#x3057;&#x307E;&#x3057;&#x305F;&#x3002;&#x6211;&#x3005; &#x306E;&#x30A2;&#x30D7;&#x30ED;&#x30FC;&#x30C1;&#x306F;&#x30D3;&#x30C7;&#x30AA;&#x8133;&#x6CE2;&#x30E2;&#x30CB;&#x30BF;&#x30EA;&#x30F3;&#x30B0;&#x306E;&#x305F;&#x3081;&#x5165;&#x9662; 156 &#x60A3;&#x8005;&#x3092;&#x5206;&#x985E;&#x3059;&#x308B;&#x306E;&#x306B;&#x591A;&#x5C64;&#x30D1;&#x30FC;&#x30BB;&#x30D7;&#x30C8;&#x30ED;&#x30F3;&#x3092;&#x4F7F;&#x7528;&#x3057;&#x307E;&#x3057;&#x305F;&#x3002;&#x60A3;&#x8005;&#x96C6;&#x56E3;&#x306F;&#x8A3A;&#x65AD;&#x591A;&#x69D8;&#x3060;&#x3063;&#x305F;;87 &#x4E00;&#x822C;&#x5316;&#x307E;&#x305F;&#x306F;&#x7126;&#x70B9;&#x767A;&#x4F5C;&#x3068;&#x8A3A;&#x65AD;&#x3055;&#x308C;&#x307E;&#x3057;&#x305F;&#x3002;&#x60A3;&#x8005;&#x306E;&#x6B8B;&#x308A;&#x306E;&#x90E8;&#x5206;&#x306F;&#x3001;nonepileptic &#x306E;&#x767A;&#x4F5C;&#x3067;&#x8A3A;&#x65AD;&#x3055;&#x308C;&#x307E;&#x3057;&#x305F;&#x3002;&#x611F;&#x5EA6;&#x306F; 92% (95% &#x4FE1;&#x983C;&#x533A;&#x9593; [CI] 85-97%) &#x3055;&#x308C;&#x8CA0;&#x306E;&#x4E88;&#x6E2C;&#x5024; 82% (95% CI 67 92%) &#x3060;&#x3063;&#x305F;&#x3002;&#x6211;&#x3005; &#x306F;&#x3069;&#x306E;&#x3088;&#x3046;&#x306B;&#x3053;&#x306E; CAD &#x30A4;&#x30D9;&#x30F3;&#x30C8;&#x306B;&#x57FA;&#x3065;&#x3044;&#x3066;&#x5206;&#x6790;&#x3092;&#x88DC;&#x5B8C;&#x3059;&#x308B;&#x305F;&#x3081;&#x306B;&#x8A13;&#x7DF4;&#x3092;&#x53D7;&#x3051;&#x305F; epileptologists &#x306B;&#x3088;&#x3063;&#x3066;&#x4F7F;&#x7528;&#x3053;&#x3068;&#x304C;&#x3067;&#x304D;&#x307E;&#x3059;&#x793A;&#x5506;&#x3092;&#x8B70;&#x8AD6;&#x3057;&#x307E;&#x3059;&#x3002;

&#x8133;&#x6CE2;&#x30D1;&#x30EF;&#x30FC; &#x30B9;&#x30DA;&#x30AF;&#x30C8;&#x30EB;&#x3092;&#x7528;&#x3044;&#x305F;&#x3066;&#x3093;&#x304B;&#x3093;&#x306E;&#x8A3A;&#x65AD;&#x306E;&#x81EA;&#x52D5;&#x5316;&#x3002;

Interictal electroencephalography (&#xB1CC; &#xD30C;) epileptiform &#xBC29;&#xC804;&#xC758; &#xBC1C;&#xC0DD;&#xC5D0; &#xB300; &#xD55C; &#xADF8;&#xAC83;&#xC758; &#xC758;&#xC874; &#xB54C;&#xBB38;&#xC5D0; &#xAC10;&#xB3C4;&#xC5D0; &#xC784;&#xC0C1;&#xC801;&#xC73C;&#xB85C; &#xC758;&#xBBF8; &#xC788;&#xB294; &#xC81C;&#xD55C; &#xBC0F; &#xAC04; &#xC9C8;&#xC758; &#xC9C4;&#xB2E8;&#xC5D0; &#xD2B9;&#xC774;&#xC131;&#xC744;&#xAC00;&#xC9C0;&#xACE0;. &#xC6B0;&#xB9AC;&#xB294; &#xC77C;&#xC0C1;&#xC801;&#xC778; &#xB1CC; &#xD30C;&#xC758; &#xC808;&#xB300; &#xC2A4;&#xD399;&#xD2B8;&#xB7FC; &#xC5D0;&#xB108;&#xC9C0;&#xC5D0;&#xC11C; &#xC791;&#xB3D9; &#xD558; &#xACE0; &#xC2E4;&#xC9C8;&#xC801;&#xC73C;&#xB85C; &#xB354; &#xB192;&#xC740; &#xAC10;&#xB3C4; &#xBD80;&#xC815;&#xC801;&#xC778; &#xC608;&#xCE21; &#xAC12; interictal epileptiform &#xBC29;&#xC804;&#xC758; &#xC2E0;&#xBD84; (CAD) &#xCEF4;&#xD4E8;&#xD130; &#xBCF4;&#xC870; &#xC9C4;&#xB2E8; &#xB3C4;&#xAD6C;&#xB97C; &#xAC1C;&#xBC1C; &#xD588;&#xC2B5;&#xB2C8;&#xB2E4;. &#xC6B0;&#xB9AC;&#xC758; &#xC811;&#xADFC; &#xBC29;&#xBC95; &#xBE44;&#xB514;&#xC624;-&#xB1CC; &#xD30C; &#xBAA8;&#xB2C8;&#xD130;&#xB9C1;&#xC5D0; &#xB300; &#xD55C; &#xC778;&#xC815; 156 &#xD658;&#xC790; &#xBD84;&#xB958;&#xB97C; &#xB2E4;&#xC911; &#xACC4;&#xCE35; &#xD37C;&#xC149;&#xD2B8;&#xB860;&#xC744; &#xC0AC;&#xC6A9;. &#xD658;&#xC790; &#xC778;&#xAD6C;&#xB294; &#xB2E4;&#xC591; &#xD55C; &#xC9C4;&#xB2E8;; 87 &#xC77C;&#xBC18;&#xD654; &#xB610;&#xB294; &#xCD08;&#xC810; &#xBC1C;&#xC791; &#xC9C4;&#xB2E8; &#xD588;&#xB2E4;. &#xD658;&#xC790;&#xC758; &#xB098;&#xBA38;&#xC9C0; nonepileptic &#xBC1C;&#xC791; &#xC9C4;&#xB2E8; &#xD588;&#xB2E4;. &#xAC10;&#xB3C4; 92% (95% &#xC2E0;&#xB8B0; &#xAD6C;&#xAC04; [CI] 85-97%)&#xACFC; &#xBD80;&#xC815;&#xC801;&#xC778; &#xC608;&#xCE21; &#xAC12;&#xC740; 82% (95% CI 67-92%). &#xC774;&#xB7EC;&#xD55C; &#xC5F0;&#xAD6C; &#xACB0;&#xACFC; &#xD6C8;&#xB828; &#xB41C; epileptologists&#xC5D0; &#xC758;&#xD574;&#xC774; CAD &#xC774;&#xBCA4;&#xD2B8; &#xAE30;&#xBC18; &#xBD84;&#xC11D;&#xC744; &#xBCF4;&#xC644; &#xD558;&#xAE30; &#xC704;&#xD574; &#xC0AC;&#xC6A9;&#xD560; &#xC218; &#xC788;&#xC2B5;&#xB2C8;&#xB2E4; &#xC81C;&#xC548; &#xD558;&#xB294; &#xBC29;&#xBC95;&#xC744; &#xC0B4;&#xD3B4;&#xBD05;&#xB2C8;&#xB2E4;.

&#xAC04; &#xC9C8; &#xB1CC; &#xD30C; &#xD30C;&#xC6CC; &#xC2A4;&#xD399;&#xD2B8;&#xB7FC;&#xC744; &#xC0AC;&#xC6A9; &#xD558; &#xC5EC; &#xC790;&#xB3D9;&#xD654; &#xB41C; &#xC9C4;&#xB2E8;&#xC785;&#xB2C8;&#xB2E4;.

La electroencefalograf&iacute;a (EEG) interictal tiene cl&iacute;nicamente significativas limitaciones en su sensibilidad y especificidad en el diagn&oacute;stico de epilepsia por su dependencia de la ocurrencia de descargas epileptiformes. Hemos desarrollado una herramienta de diagn&oacute;stico asistido por ordenador (CAD) que act&uacute;a sobre la energ&iacute;a espectral absoluta de la rutina de EEG con tanto substancialmente m&aacute;s alta sensibilidad y valor predictivo negativo que la identificaci&oacute;n de descargas epileptiformes interictales. Nuestro enfoque utiliza un perceptr&oacute;n multicapa para clasificar 156 pacientes ingresados para la supervisi&oacute;n del v&iacute;deo-EEG. La poblaci&oacute;n de pacientes fue de diagn&oacute;stico diversa; 87 fueron diagnosticados con convulsiones generalizadas o focales. El resto de los pacientes fueron diagnosticado con asimientos nonepileptic. La sensibilidad fue de 92% (intervalo de confianza [IC] del 95% 85-97%) y el valor predictivo negativo fue de 82% (95% CI 67-92%). Discutimos c&oacute;mo estos resultados sugieren que este CAD puede utilizarse para complementar el an&aacute;lisis basado en eventos por epileptologists entrenado.

Diagn&oacute;stico automatizado de epilepsia utilizando el espectro de energ&iacute;a de EEG.

Although the placebo effect is known to have a strong impact on the outcomes of clinical trials, methods for measuring it are limited to physiological observations. We propose a method of localizing, identifying and measuring placebo and treatment-induced networks in the brain using functional neuroimaging. Measuring the relative activation of these "placebo" brain networks serves as a proxy for the placebo effect contained within the variable of interest (depression rating, blood pressure, etc). Analogous to the difference between a paired and unpaired t-test, this allows for a sharp gain in power and reduction in the sample sizes needed in clinical trials, potentially leading to a drastically smaller sample sizes for establishing efficacy, a shorter time-to-market for a drug, and a drastic reduction in the cost of bringing new drugs into the market.

Reducing clinical trial costs by detecting and measuring the placebo effect and treatment effect using brain imaging.

Interictal FDG-PET (iPET) is a core tool for localizing the epileptogenic focus, potentially before structural MRI, that does not require rare and transient epileptiform discharges or seizures on EEG. The visual interpretation of iPET is challenging and requires years of epilepsy-specific expertise. We have developed an automated computer-aided diagnostic (CAD) tool that has the potential to work both independent of and synergistically with expert analysis. Our tool operates on distributed metabolic changes across the whole brain measured by iPET to both diagnose and lateralize temporal lobe epilepsy (TLE). When diagnosing left TLE (LTLE) or right TLE (RTLE) vs. non-epileptic seizures (NES), our accuracy in reproducing the results of the gold standard long term video-EEG monitoring was 82% [95% confidence interval (CI) 69-90%] or 88% (95% CI 76-94%), respectively. The classifier that both diagnosed and lateralized the disease had overall accuracy of 76% (95% CI 66-84%), where 89% (95% CI 77-96%) of patients correctly identified with epilepsy were correctly lateralized. When identifying LTLE, our CAD tool utilized metabolic changes across the entire brain. By contrast, only temporal regions and the right frontal lobe cortex, were needed to identify RTLE accurately, a finding consistent with clinical observations and indicative of a potential pathophysiological difference between RTLE and LTLE. The goal of CADs is to complement - not replace - expert analysis. In our dataset, the accuracy of manual analysis (MA) of iPET (∼80%) was similar to CAD. The square correlation between our CAD tool and MA, however, was only 30%, indicating that our CAD tool does not recreate MA. The addition of clinical information to our CAD, however, did not substantively change performance. These results suggest that automated analysis might provide clinically valuable information to focus treatment more effectively.

Computer-Aided Diagnosis and Localization of Lateralized Temporal Lobe Epilepsy Using Interictal FDG-PET.

The current study explores relationships between mindfulness, emotional regulation, impulsivity, and stress proneness in a sample of participants recruited in a Diagnostic and Statistical Manual of Mental Disorder Fifth Edition Field Trial for Hypersexual Disorder and healthy controls to assess whether mindfulness attenuates symptoms of hypersexuality.

Mindfulness, Emotional Dysregulation, Impulsivity, and Stress Proneness Among Hypersexual Patients.

The recent Chu et al. (2012) manuscript discusses two key findings regarding feature selection (FS): (1) data driven FS was no better than using whole brain voxel data and (2) a priori biological knowledge was effective to guide FS. Use of FS is highly relevant in neuroimaging-based machine learning, as the number of attributes can greatly exceed the number of exemplars. We strongly endorse their demonstration of both of these findings, and we provide additional important practical and theoretical arguments as to why, in their case, the data-driven FS methods they implemented did not result in improved accuracy. Further, we emphasize that the data-driven FS methods they tested performed approximately as well as the all-voxel case. We discuss why a sparse model may be favored over a complex one with similar performance. We caution readers that the findings in the Chu et al. report should not be generalized to all data-driven FS methods.

The utility of data-driven feature selection: Re: Chu et al. 2012.

The complex task of assessing the veracity of a statement is thought to activate uniquely distributed brain regions based on whether a subject believes or disbelieves a given assertion. In the current work, we present parallel machine learning methods for predicting a subject's decision response to a given propositional statement based on independent component (IC) features derived from EEG and fMRI data. Our results demonstrate that IC features outperformed features derived from event related spectral perturbations derived from any single spectral band, yet were similar to accuracy across all spectral bands combined. We compared our diagnostic IC spatial maps with our conventional general linear model (GLM) results, and found that informative ICs had significant spatial overlap with our GLM results, yet also revealed unique regions like amygdala that were not statistically significant in GLM analyses. Overall, these results suggest that ICs may yield a parsimonious feature set that can be used along with a decision tree structure for interpretation of features used in classifying complex cognitive processes such as belief and disbelief across both fMRI and EEG neuroimaging modalities.

Single trial decoding of belief decision making from EEG and fMRI data using independent components features.

Functional network connectivity (FNC) is a method of analyzing the temporal relationship of anatomical brain components, comparing the synchronicity between patient groups or conditions. We use functional-connectivity measures between independent components to classify between Schizophrenia patients and healthy controls during resting-state. Connectivity is measured using a variety of graph-theoretic connectivity measures such as graph density, average path length, and small-worldness. The Schizophrenia patients showed significantly less clustering (transitivity) among components than healthy controls (p < 0.05, corrected) with networks less likely to be connected, and also showed lower small-world connectivity than healthy controls. Using only these connectivity measures, an SVM classifier (without parameter tuning) could discriminate between Schizophrenia patients and healthy controls with 65% accuracy, compared to 51% chance. This implies that the global functional connectivity between resting-state networks is altered in Schizophrenia, with networks more likely to be disconnected and behave dissimilarly for diseased patients. We present this research finding as a tutorial using the publicly available COBRE dataset of 146 Schizophrenia patients and healthy controls, provided as part of the 1000 Functional Connectomes Project. We demonstrate preprocessing, using independent component analysis (ICA) to nominate networks, computing graph-theoretic connectivity measures, and finally using these connectivity measures to either classify between patient groups or assess between-group differences using formal hypothesis testing. All necessary code is provided for both running command-line FSL preprocessing, and for computing all statistical measures and SVM classification within R. Collectively, this work presents not just findings of diminished FNC among resting-state networks in Schizophrenia, but also a practical connectivity tutorial.

Decreased small-world functional network connectivity and clustering across resting state networks in schizophrenia: an fMRI classification tutorial.

In the multimodal neuroimaging framework, data on a single subject are collected from inherently different sources such as functional MRI, structural MRI, behavioral and/or phenotypic information. The information each source provides is not independent; a subset of features from each modality maps to one or more common latent dimensions, which can be interpreted using generative models. These latent dimensions, or "topics," provide a sparse summary of the generative process behind thefeatures for each individual. Topic modeling, an unsupervised generative model, has been used to map seemingly disparate features to a common domain. We use Non-Negative Matrix Factorization (NMF) to infer the latent structure of multimodal ADHD data containing fMRI, MRI, phenotypic and behavioral measurements. We compare four different NMF algorithms and find that the sparsest decomposition is also the most differentiating between ADHD and healthy patients. We identify dimensions that map to interpretable, recognizable dimensions such as motion, default mode network activity, and other such features of the input data. For example, structural and functional graph theory features related to default mode subnetworks clustered with the ADHD inattentive diagnosis. Structural measurements of the default mode network (DMN) regions such as the posterior cingulate, precuneus, and parahippocampal regions were all related to the ADHD-Inattentive diagnosis. Ventral DMN subnetworks may have more functional connections in ADHD-I, while dorsal DMN may have less. We also find that ADHD topics may be dependent upon diagnostic site, raising the possibility of the diagnostic differences across geographic locations. We assess our findings in light of theADHD-200 classification competition, and contrast our unsupervised, nominated topics with previously published supervised learning methods. Finally, we demonstrate the validity of these latent variables as biomarkers by using them for classification of ADHD in 730 patients. Cumulatively, this manuscript addresses how multimodal data in ADHD can be interpreted by latent dimensions.

Article	Year
Classification of spatially unaligned fMRI scans. NeuroImage\| PubMed ID: 19712744	2010
Comparative efficacy of rabeprazole and pantoprazole in the control of nocturnal Acid output and intragastric acidity. Gut and liver\| PubMed ID: 20485608	2008
Common component classification: what can we learn from machine learning? NeuroImage\| PubMed ID: 20599621	2011
Large Sample Group Independent Component Analysis of Functional Magnetic Resonance Imaging Using Anatomical Atlas-Based Reduction and Bootstrapped Clustering. International journal of imaging systems and technology\| PubMed ID: 22049263	2011
Automated diagnosis of epilepsy using EEG power spectrum. Epilepsia\| PubMed ID: 22967005	2012
Reducing clinical trial costs by detecting and measuring the placebo effect and treatment effect using brain imaging. Studies in health technology and informatics\| PubMed ID: 23400121	2013
Computer-Aided Diagnosis and Localization of Lateralized Temporal Lobe Epilepsy Using Interictal FDG-PET. Frontiers in neurology\| PubMed ID: 23565107	2013
Mindfulness, Emotional Dysregulation, Impulsivity, and Stress Proneness Among Hypersexual Patients. Journal of clinical psychology\| PubMed ID: 23852856	2013
The utility of data-driven feature selection: Re: Chu et al. 2012. NeuroImage\| PubMed ID: 23891886	2014
Single trial decoding of belief decision making from EEG and fMRI data using independent components features. Frontiers in human neuroscience\| PubMed ID: 23914164	2013
Decreased small-world functional network connectivity and clustering across resting state networks in schizophrenia: an fMRI classification tutorial. Frontiers in human neuroscience\| PubMed ID: 24032010	2013
Non-negative matrix factorization of multimodal MRI, fMRI and phenotypic data reveals differential changes in default mode subnetworks in ADHD. NeuroImage\| PubMed ID: 24361664	2013

Ariana Anderson

Biography

JoVE Journal Publications

Other Publications