Dr. Guillermo A. Cecchi Profile

Dr. Guillermo A. Cecchi

at IBM Thomas J Watson Research Ctr

SPIE Involvement:

Author

Publications (11)

Proceedings Article | 15 March 2019 Paper

Predicting conversion to psychosis in clinical high risk patients using resting-state functional MRI features

Jolie McDonnell, William Hord, Jenna Reinen, Pablo Polosecki, Irina Rish, Guillermo Cecchi

Proceedings Volume 10953, 109532A (2019) https://doi.org/10.1117/12.2525341

KEYWORDS: Data modeling, Functional magnetic resonance imaging, Control systems, Magnetic resonance imaging, Feature extraction, Data conversion, Machine learning, Brain, Statistical modeling, Brain imaging

Read Abstract +

Proceedings Article | 13 March 2017 Presentation + Paper

Learning discriminative functional network features of schizophrenia

Mina Gheiratmand, Irina Rish, Guillermo Cecchi, Matthew Brown, Russell Greiner, Pouya Bashivan, Pablo Polosecki, Serdar Dursun

Proceedings Volume 10137, 101371A (2017) https://doi.org/10.1117/12.2264102

KEYWORDS: Functional magnetic resonance imaging, Brain, Control systems, Feature extraction, Data modeling, Statistical analysis, Statistical modeling, Neuroimaging, Psychiatry, Data acquisition

Read Abstract +

Associating schizophrenia with disrupted functional connectivity is a central idea in schizophrenia research. However, identifying neuroimaging-based features that can serve as reliable “statistical biomarkers” of the disease remains a challenging open problem. We argue that generalization accuracy and stability of candidate features (“biomarkers”) must be used as additional criteria on top of standard significance tests in order to discover more robust biomarkers. Generalization accuracy refers to the utility of biomarkers for making predictions about individuals, for example discriminating between patients and controls, in novel datasets. Feature stability refers to the reproducibility of the candidate features across different datasets. Here, we extracted functional connectivity network features from fMRI data at both high-resolution (voxel-level) and a spatially down-sampled lower-resolution (“supervoxel” level). At the supervoxel level, we used whole-brain network links, while at the voxel level, due to the intractably large number of features, we sampled a subset of them. We compared statistical significance, stability and discriminative utility of both feature types in a multi-site fMRI dataset, composed of schizophrenia patients and healthy controls. For both feature types, a considerable fraction of features showed significant differences between the two groups. Also, both feature types were similarly stable across multiple data subsets. However, the whole-brain supervoxel functional connectivity features showed a higher cross-validation classification accuracy of 78.7% vs. 72.4% for the voxel-level features. Cross-site variability and heterogeneity in the patient samples in the multi-site FBIRN dataset made the task more challenging compared to single-site studies. The use of the above methodology in combination with the fully data-driven approach using the whole brain information have the potential to shed light on “biomarker discovery” in schizophrenia.

Proceedings Article | 29 March 2016 Paper

Evaluating effects of methylphenidate on brain activity in cocaine addiction: a machine-learning approach

Irina Rish, Pouya Bashivan, Guillermo Cecchi, Rita Goldstein

Proceedings Volume 9788, 97880O (2016) https://doi.org/10.1117/12.2218212

KEYWORDS: Brain, Magnetic resonance imaging, Functional magnetic resonance imaging, Machine learning, Brain imaging, Brain mapping, Image processing, Image segmentation, Image registration, Mental disorders, Biological research, Feature extraction, Feature selection, Statistical modeling, Error control coding, Principal component analysis

Read Abstract +

Proceedings Article | 14 April 2012 Paper

Schizophrenia classification using functional network features

Irina Rish, Guillermo Cecchi, Kyle Heuton

Proceedings Volume 8317, 83170W (2012) https://doi.org/10.1117/12.911773

KEYWORDS: Data modeling, Brain, Feature extraction, Functional magnetic resonance imaging, Statistical analysis, Statistical modeling, Error analysis, Magnetorheological finishing, Feature selection, Matrices

Read Abstract +

Proceedings Article | 14 February 2012 Paper

Sparse regression analysis of task-relevant information distribution in the brain

Irina Rish, Guillermo Cecchi, Kyle Heuton, Marwan Baliki, A. Vania Apkarian

Proceedings Volume 8314, 831412 (2012) https://doi.org/10.1117/12.911318

KEYWORDS: Brain, Visualization, Functional magnetic resonance imaging, Brain mapping, Analytical research, Statistical analysis, Feature selection, Process modeling, Visual process modeling, Holography

Read Abstract +

Proceedings Article | 15 March 2011 Paper

Fast computation of functional networks from fMRI activity: a multi-platform comparison

A. Ravishankar Rao, Rajesh Bordawekar, Guillermo Cecchi

Proceedings Volume 7962, 79624L (2011) https://doi.org/10.1117/12.878368

KEYWORDS: Functional magnetic resonance imaging, Network security, Brain, Image analysis, Statistical analysis, Analytical research, Medical imaging, Neuroimaging, Scanners, Visualization

Read Abstract +

Proceedings Article | 4 March 2011 Paper

Characteristics of voxel prediction power in full-brain Granger causality analysis of fMRI data

Rahul Garg, Guillermo Cecchi, A. Ravishankar Rao

Proceedings Volume 7965, 796502 (2011) https://doi.org/10.1117/12.878311

KEYWORDS: Brain, Data modeling, Functional magnetic resonance imaging, Stochastic processes, Brain mapping, Machine learning, Analytical research, Neuroimaging, Matrices, Visualization

Read Abstract +

Proceedings Article | 13 February 2008 Paper

Statistics of natural scenes and the cortical representation of color

G. Cecchi, A. Rao, Y. Xiao, E. Kaplan

Proceedings Volume 6806, 680607 (2008) https://doi.org/10.1117/12.769003

KEYWORDS: Visualization, Visual cortex, Statistical analysis, Spatial frequencies, Image filtering, Neurons, Optical recording, Databases, Data processing, Brain mapping

Read Abstract +

Proceedings Article | 16 February 2006 Paper

Translation invariance in a network of oscillatory units

A. Ravishankar Rao, Guillermo Cecchi, Charles Peck, James Kozloski

Proceedings Volume 6064, 60641I (2006) https://doi.org/10.1117/12.648229

KEYWORDS: Visual system, Visualization, Neurons, Deconvolution, Oscillators, Image segmentation, Neural networks, Machine learning, Chemical elements, Superposition

Read Abstract +

One of the important features of the human visual system is that it is able to recognize objects in a scale and translational invariant manner. However, achieving this desirable behavior through biologically realistic networks is a challenge. The synchronization of neuronal firing patterns has been suggested as a possible solution to the binding problem (where a biological mechanism is sought to explain how features that represent an object can be scattered across a network, and yet be unified). This observation has led to neurons being modeled as oscillatory dynamical units. It is possible for a network of these dynamical units to exhibit synchronized oscillations under the right conditions. These network models have been applied to solve signal deconvolution or blind source separation problems. However, the use of the same network to achieve properties that the visual sytem exhibits, such as scale and translational invariance have not been fully explored. Some approaches investigated in the literature (Wallis, 1996) involve the use of non-oscillatory elements that are arranged in a hierarchy of layers. The objects presented are allowed to move, and the network utilizes a trace learning rule, where a time averaged output value is used to perform Hebbian learning with respect to the input value. This is a modification of the standard Hebbian learning rule, which typically uses instantaneous values of the input and output. In this paper we present a network of oscillatory amplitude-phase units connected in two layers. The types of connections include feedforward, feedback and lateral. The network consists of amplitude-phase units that can exhibit synchronized oscillations. We have previously shown that such a network can segment the components of each input object that most contribute to its classification. Learning is unsupervised and based on a Hebbian update, and the architecture is very simple. We extend the ability of this network to address the problem of translational invariance. We show that by adopting a specific treatment of the phase values of the output layer, the network exhibits translational invariant object representation. The scheme used in training is as follows. The network is presented with an input, which then moves. During the motion the amplitude and phase of the upper layer units is not reset, but continues with the past value before the introduction of the object in the new position. Only the input layer is changed instantaneously to reflect the moving object. The network behavior is such that it categorizes the translated objects with the same label as the stationary object, thus establishing an invariant categorization with respect to translation. This is a promising result as it uses the same framework of oscillatory units that achieves synchrony, and introduces motion to achieve translational invariance.

Proceedings Article | 9 February 2006 Paper

Inference and segmentation in cortical processing

Yuan Liu, Guillermo Cecchi, A. Ravishankar Rao, James Kozloski, Charles Peck

Proceedings Volume 6057, 60570Y (2006) https://doi.org/10.1117/12.650804

KEYWORDS: Neural networks, Superposition, Deconvolution, Network architectures, Neurons, Visual process modeling, Evolutionary algorithms, Machine learning, Brain, Visual cortex

Read Abstract +

Proceedings Article | 18 March 2005 Paper

A model of the formation of a self-organized cortical representation of color

A. Ravishankar Rao, Guillermo Cecchi, Charles Peck, James Kozloski

Proceedings Volume 5666, (2005) https://doi.org/10.1117/12.585526

KEYWORDS: RGB color model, Cones, Brain mapping, Visualization, Data processing, Retina, Neurons, Signal processing, Spatial filters, Data modeling

Read Abstract +

Showing 5 of 11 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years