A5027841944- Radiomics and Machine Learning in Medical Imaging
- Glioma Diagnosis and Treatment
- MRI in cancer diagnosis
- Neural and Behavioral Psychology Studies
- Advanced Neuroimaging Techniques and Applications
- Ferroptosis and cancer prognosis
- Lanthanide and Transition Metal Complexes
- Functional Brain Connectivity Studies
- Advanced MRI Techniques and Applications
- Human-Automation Interaction and Safety
- Molecular Biology Techniques and Applications
- Visual perception and processing mechanisms
- Advanced X-ray and CT Imaging
- Cognitive Abilities and Testing
- Neurobiology of Language and Bilingualism
- Cancer Genomics and Diagnostics
- Tactile and Sensory Interactions
- Memory Processes and Influences
- Cognitive Science and Mapping
- Memory and Neural Mechanisms
- Bone and Joint Diseases
- Medical Imaging Techniques and Applications
Barrow Neurological Institute
2019-2023
Dignity Health
2023
Mayo Clinic in Florida
2019
WinnMed
2019
Arizona State University
2017-2018
Glioblastoma (GBM) is a heterogeneous and lethal brain cancer. These tumors are followed using magnetic resonance imaging (MRI), which unable to precisely identify tumor cell invasion, impairing effective surgery radiation planning. We present novel hybrid model, based on multiparametric intensities, combines machine learning (ML) with mechanistic model of growth provide spatially resolved density predictions. The ML component an data-driven graph-based semi-supervised we use the...
Sampling restrictions have hindered the comprehensive study of invasive non-enhancing (NE) high-grade glioma (HGG) cell populations driving tumor progression. Here, we present an integrated multi-omic analysis spatially matched molecular and multi-parametric magnetic resonance imaging (MRI) profiling across 313 multi-regional biopsies, including 111 from NE, 68 HGG patients. Whole exome RNA sequencing uncover unique genomic alterations to unresectable NE tumor, subclonal events, which inform...
<h3>BACKGROUND AND PURPOSE:</h3> MR imaging–based modeling of tumor cell density can substantially improve targeted treatment glioblastoma. Unfortunately, interpatient variability limits the predictive ability many approaches. We present a transfer learning method that generates individualized patient models, grounded in wealth population data, while also detecting and adjusting for variabilities based on each patient9s own histologic data. <h3>MATERIALS METHODS:</h3> recruited patients with...
Background Alzheimer's disease (AD) is a progressive neurodegenerative that affects aging populations. Current MRI techniques are often limited in their sensitivity to underlying neuropathological changes. Purpose To characterize differences voxel‐based morphometry (VBM), apparent diffusion coefficient (ADC), and intravoxel incoherent motion diffusion‐weighted imaging (IVIM‐DWI) metrics Additionally, investigate the connection between cognitive assessments neuroimaging metrics. Study Type...
Purpose Brain tumor dynamic susceptibility contrast (DSC) MRI is adversely impacted by T 1 and agent leakage effects that result in inaccurate hemodynamic metrics. While multi‐echo acquisitions remove effects, there no consensus on the optimal set of acquisition parameters. Using a computational approach, we systematically evaluated wide range strategies to determine DSC‐MRI perfusion protocol. Methods population‐based digital reference object (DRO), assessed influence preload dosing (no...
The present study examined the degree to which tests of visuospatial storage capacity tap into domain-general and attention processes. This was done by comparing performance memory tasks with on sound-based sensory discrimination tasks. We found that task- task both tapped a cross-modality factor (visual auditory). further this common variance could be explained control sustained attention. These factors accounted for roughly 60% in memory. indicates reflect more than modality-specific
The present study examines the idea that time-based forgetting of outdated information can lead to better memory currently relevant information. This was done using visual arrays task, along with a between-subjects manipulation both retention interval (1 s vs. 4 s) and time between two trials s). Consistent prior work [Shipstead, Z., & Engle, R. W. (2013). Interference within focus attention: Working tasks reflect more than temporary maintenance. Journal Experimental Psychology: Learning,...
Abstract INTRODUCTION Neuroimaging dogma for glioblastoma asserts that hyperintensity on T1Gd MRI reveals the bulk of tumor, while T2/FLAIR signal indicates edema. However, it is unclear whether this edema results from immune response or increased tumor cells. Further, one significant driver known sex differences in may be response, due to X-linkage many genes. Based this, we hypothesized assumptions regarding cellularity images should tailored biological patient. METHODS Using a...
Abstract High grade glioma (HGG) represents a group of devastating diseases with dismal prognosis. Surgical resection the contrast enhancing (CE) region HGG remains mainstay treatment, but recurrence inevitably arises from unresected non-contrast (NE) region, surgically inaccessible due to cancer cell invasion into healthy brain tissue. Due its critical role in recurrence, understanding NE is central improvement clinical outcomes. We reveal biological characteristics this through image...
Abstract High grade gliomas (HGG) are aggressive primary brain malignancies typified by diffuse invasion, genetic heterogeneity, and a universally fatal outcome. MRI-defined contrast-enhancing (CE) tumor burden serves as the clinical standard that guides maximal surgical resection post-therapy response assessment. However, HGGs also comprise an invasive non-enhancing (NE) margin extends beyond CE core harbors cells contribute to recurrence. Sampling restrictions have hindered comprehensive...
Abstract Dynamic susceptibility contrast (DSC) MRI measures of brain tumor cerebral blood volume (CBV) are able to predict grade, overall survival and response treatment. Wide-spread acceptance DSC-MRI has been challenged by the need balance agent dose CBV accuracy. The goal this study was identify validate single-dose, BTIP compliant, protocols. Using a validated, patient-based DRO, we evaluated accuracy across range acquisition parameters (field strength, TR, TE, flip angle, multi-echo...
Abstract INTRODUCTION The quantification of intratumoral heterogeneity – through radiomics-based approaches - can help resolve the regionally distinct genetic drug targets that may co-exist within a single Glioblastoma (GBM) tumor. While this offers potential diagnostic value under paradigm individualized oncology, clinical decision-making must also consider degree uncertainty associated with each model. In study, we evaluate performance novel machine-learning (ML) algorithm, called Gaussian...
Abstract BACKGROUND An important challenge in radiomics research is reproducibility. Images are collected on different image scanners and protocols, which introduces significant variability even for the same type of across institutions. In present proof-of-concept study, we address reproducibility issue by using domain adaptation – an algorithm that transforms radiomic features each new patient to align with distribution formed samples a training set. METHOD Our dataset included 18 patients...