Richard M. Leahy
University of Southern California
Imaging phantomAlgorithmOpticsPhysicsMathematical optimizationInverse problemIterative reconstructionMagnetic resonance imagingArtificial intelligenceNeurosciencePattern recognitionImage resolutionComputer visionMathematicsComputer scienceElectroencephalographyVoxelMagnetoencephalographyMedicineImage processingMaximum a posteriori estimation
421Publications
75H-index
20.8kCitations
Publications 409
Newest
#1Haleh Akrami (SC: University of Southern California)H-Index: 4
#2Anand A. Joshi (SC: University of Southern California)H-Index: 24
Last. Richard M. Leahy (SC: University of Southern California)H-Index: 75
view all 4 authors...
Despite impressive state-of-the-art performance on a wide variety of machine learning tasks in multiple applications, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as anomaly or lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. I...
#1Hossein Shahabi (SC: University of Southern California)H-Index: 1
#2Kenneth N. Taylor (Cleveland Clinic)H-Index: 3
Last. John C. Mosher (University of Texas at Austin)H-Index: 37
view all 12 authors...
OBJECTIVE To determine whether brain connectivity differs between focal cortical dysplasia (FCD) types I and II. METHODS We compared cortico-cortical evoked potentials (CCEPs) as measures of effective brain connectivity in 25 FCD patients with drug-resistant focal epilepsy who underwent intracranial evaluation with stereo-electroencephalography (SEEG). We analyzed the amplitude and latency of CCEP responses following ictal-onset single-pulse electrical stimulation (iSPES). RESULTS In comparison ...
Source
#1Bokkyu Kim (State University of New York Upstate Medical University)H-Index: 2
#2Nicolas Schweighofer (SC: University of Southern California)H-Index: 40
Last. Carolee J. Winstein (SC: University of Southern California)H-Index: 64
view all 5 authors...
Background and purpose null The corticospinal tract (CST) is a crucial brain pathway for distal arm and hand motor control. We aimed to determine whether a diffusion tensor imaging (DTI)-derived CST metric predicts distal upper extremity (UE) motor improvements in chronic stroke survivors. null Methods null We analyzed clinical and neuroimaging data from a randomized controlled rehabilitation trial. Participants completed clinical assessments and neuroimaging at baseline and clinical assessments...
Source
#1Haleh Akrami (SC: University of Southern California)H-Index: 4
#2Anand A. Joshi (SC: University of Southern California)H-Index: 24
Last. Richard M. Leahy (SC: University of Southern California)H-Index: 75
view all 4 authors...
The Variational AutoEncoder (VAE) has become one of the most popular models for anomaly detection in applications such as lesion detection in medical images. The VAE is a generative graphical model that is used to learn the data distribution from samples and then generate new samples from this distribution. By training on normal samples, the VAE can be used to detect inputs that deviate from this learned distribution. The VAE models the output as a conditionally independent Gaussian characterize...
Source
#1Kenneth N. Taylor (Cleveland Clinic)H-Index: 3
#2Anand A. Joshi (SC: University of Southern California)H-Index: 24
Last. Dileep Nair (Cleveland Clinic)H-Index: 36
view all 10 authors...
Objective Stereotactic electroencephalography (SEEG) has been widely used to explore the epileptic network and localize the epileptic zone in patients with medically intractable epilepsy. Accurate anatomical labeling of SEEG electrode contacts is critically important for correctly interpreting epileptic activity. We present a method for automatically assigning anatomical labels to SEEG electrode contacts using a 3D-segmented cortex and coregistered postoperative CT images. Method Stereotactic el...
Source
#1Roni Setton (Montreal Neurological Institute and Hospital)H-Index: 4
Last. Nathan Spreng RH-Index: 1
view all 20 authors...
The intrinsic network architecture of the brain is continuously shaped by biological and behavioral factors from younger to older adulthood. Differences in functional networks can reveal how a lifetime of learning and lived experience can alter large-scale neurophysiological dynamics, offering a powerful lens into brain and cognitive aging. Quantifying these differences has been hampered by significant methodological challenges. Here, we use multi-echo fMRI and multi-echo ICA processing, individ...
Source
#1Daeun Kim (SC: University of Southern California)H-Index: 6
#2Stephen F. Cauley (Harvard University)H-Index: 26
Last. Justin P. Haldar (SC: University of Southern California)H-Index: 30
view all 5 authors...
PURPOSE In many MRI scenarios, magnetization is often excited from spatial regions that are not of immediate interest. Excitation of uninteresting magnetization can complicate the design of efficient imaging methods, leading to either artifacts or acquisitions that are longer than necessary. While there are many hardware- and sequence-based approaches for suppressing unwanted magnetization, this paper approaches this longstanding problem from a different and complementary angle, using beamformin...
Source
#1Lars Benschop (UGent: Ghent University)H-Index: 2
#2Tasha Poppa (UGent: Ghent University)H-Index: 1
Last. Marie-Anne Vanderhasselt (UGent: Ghent University)H-Index: 41
view all 8 authors...
Abstract Introduction : Prior resting state fMRI studies have revealed that elevated connectivity between the default mode network (DMN) and subgenual prefrontal cortex (sgPFC) connectivity may underly maladaptive rumination, which is a major risk factor for depression. To further evaluate such relationship, we investigated whether posterior regions of the DMN, showed elevated connectivity with the sgPFC in remitted depressed patients (rMDD) and whether this connectivity was related to maladapti...
Source
#1Takfarinas Medani (SC: University of Southern California)H-Index: 3
#2Juan García-Prieto (Harvard University)H-Index: 7
Last. Richard M. Leahy (SC: University of Southern California)H-Index: 75
view all 10 authors...
Human brain activity generates scalp potentials (electroencephalography – EEG), intracranial potentials (iEEG), and external magnetic fields (magnetoencephalography – MEG), all capable of being recorded, often simultaneously, for use in research and clinical purposes. The so-called forward problem is modeling these fields at their sensors for a given putative neural source configuration. While early approaches modeled the head as a simple set of isotropic spheres, today’s ubiquitous magnetic res...
Source
#1Anand A. Joshi (SC: University of Southern California)H-Index: 24
#2Soyoung Choi (SC: University of Southern California)H-Index: 12
Last. Richard M. Leahy (SC: University of Southern California)H-Index: 75
view all 5 authors...
Due to the spontaneous nature of resting fMRI (rs-fMRI) signals, cross-subject comparison and group studies of rs-fMRI are challenging. Existing group comparison methods typically reduce the fMRI time series either to lower-dimensional connectivity features or use ICA to reduce dimensionality. We previously developed BrainSync, an orthogonal transformation that allows direct comparison of fMRI time-series across subjects.1 This orthogonal transform performs a temporal alignment of time-series at...
Source
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.