A5078301136- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Glaucoma and retinal disorders
- Cerebral Venous Sinus Thrombosis
- Ophthalmology and Eye Disorders
- COVID-19 Clinical Research Studies
- Medical Imaging and Analysis
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Ocular Diseases and Behçet’s Syndrome
- Autism Spectrum Disorder Research
- Retinal Imaging and Analysis
- Sepsis Diagnosis and Treatment
- Medical Image Segmentation Techniques
- Child Nutrition and Feeding Issues
- Chronic Disease Management Strategies
- Genetics and Neurodevelopmental Disorders
- Dementia and Cognitive Impairment Research
- Traumatic Brain Injury and Neurovascular Disturbances
- Advanced Neural Network Applications
- Genetic Associations and Epidemiology
- Artificial Intelligence in Healthcare
- Distributed and Parallel Computing Systems
- Frailty in Older Adults
- Genomics and Rare Diseases
Siemens Healthcare (United States)
2020-2025
Siemens (United States)
2020-2024
Vanderbilt University
2014-2022
Siemens (Germany)
2020
Vanderbilt University Medical Center
2020
University of Cincinnati
2014
Purpose To present a method that automatically segments and quantifies abnormal CT patterns commonly in COVID-19, namely ground-glass opacities consolidations. Materials Methods In this retrospective study, the proposed takes as input noncontrast chest lesions, lungs, lobes three dimensions, based on dataset of 9749 volumes. The outputs two combined measures severity lung lobe involvement, quantifying both extent COVID-19 abnormalities presence high opacities, deep learning reinforcement...
The optic nerve (ON) plays a critical role in many devastating pathological conditions. Segmentation of the ON has ability to provide understanding anatomical development and progression diseases ON. Recently, methods have been proposed segment but progress toward full automation limited. We optimize registration fusion for new multi-atlas framework automated segmentation ONs, eye globes, muscles on clinically acquired computed tomography (CT) data. Briefly, approach consists determining...
OBJECTIVE: To extract pulmonary and cardiovascular metrics from chest CTs of patients with coronavirus disease 2019 (COVID-19) using a fully automated deep learning-based approach assess their potential to predict patient management. MATERIALS AND METHODS: All initial who tested positive for severe acute respiratory syndrome 2 at our emergency department between March 25 April 25, 2020, were identified (n = 120). Three management groups defined: group 1 (outpatient), (general ward), 3...
The Coronavirus Disease (COVID-19) has affected 1.8 million people and resulted in more than 110,000 deaths as of April 12, 2020. Several studies have shown that tomographic patterns seen on chest Computed Tomography (CT), such ground-glass opacities, consolidations, crazy paving pattern, are correlated with the disease severity progression. CT imaging can thus emerge an important modality for management COVID-19 patients. AI-based solutions be used to support based quantitative reporting...
We examined medical records to determine health conditions associated with dementia at varied intervals prior diagnosis in participants from the Baltimore Longitudinal Study of Aging (BLSA).Data were available for 347 Alzheimer's disease (AD), 76 vascular (VaD), and 811 control without dementia. Logistic regressions performed associating International Classification Diseases, 9th Revision (ICD-9) codes status across all time points, 5 1 year(s) diagnosis, year controlling age, sex, follow-up...
Composite models that combine medical imaging with electronic records (EMR) improve predictive power when compared to traditional use alone. The digitization of EMR provides potential access a wealth information, but presents new challenges in algorithm design and inference. Previous studies, such as Phenome Wide Association Study (PheWAS), have shown data can be used investigate the relationship between genotypes clinical conditions. Here, we introduce Phenome-Disease extend statistical...
Individuals with autism spectrum disorder experience a significant number of co-occurring medical conditions, yet little is known about these conditions beyond prevalence. Using large-scale de-identified records, we can use novel phecode-based tool to characterize in disorder. We hypothesized that individuals an increased burden as measured by presence, frequency, and duration visits related conditions. Secondarily, age at first encounter for (early, <5; late, >5) would be associated...
Pathologies of the optic nerve and orbit impact millions Americans quantitative assessment orbital structures on 3-D imaging would provide objective markers to enhance diagnostic accuracy, improve timely intervention, eventually preserve visual function. Recent studies have shown that multi-atlas methodology is suitable for identifying structures, but challenges arise in identification individual extraocular rectus muscles control eye movement. This increasingly problematic diseased eyes,...
Increasing reliance on electronic medical records at large centers provides unique opportunities to perform population level analyses exploring disease progression and etiology. The massive accumulation of diagnostic, procedure, laboratory codes in one place has enabled the exploration co-occurring conditions, their risk factors, potential prognostic factors. While most readily identifiable associations are (now) well known scientific community, there is no doubt many more relationships...
Early detection of risk is critical in determining the course treatment traumatic brain injury (TBI). Computed tomography (CT) acquired at admission has shown latent prognostic value prior studies; however, no robust clinical predictions have been achieved based on imaging data large-scale TBI analysis. The major challenge lies lack consistent and complete medical records for patients, an inherent bias associated with limited number patients samples high-risk outcomes available datasets....
A key obstacle to developing automated histopathology assessment tools is the difficulty of defining quantifiable image features that could serve as fundamental data elements capable distinguishing disease types and subtypes. variety feature extraction selection methods for histology images have been proposed. However, comparisons different descriptor approaches remains challenging because varying datasets emphases chosen by authors. As an example how a shared reference atlas accelerate...
With the injection of contrast material into blood vessels, multi-phase contrasted CT images can enhance visibility vessel networks in human body. Reconstructing 3D geometric morphology liver vessels from enable multiple preoperative surgical planning applications. Automatic reconstruction remains a challenging problem due to morphological complexity and inconsistent intensities among different images. On other side, high integrity is required for avoid decision making biases. In this paper,...
The authors present a case of Solitary extramedullary non mucosal plasmacytoma the Thyroid gland in 72 year old male who presented with an asymptomatic right thyroid lobe swelling.Histopathological examination operative specimen together immunocytochemical staining confirmed diagnosis plasmacytoma.Haematological work up for Multiple myeloma was negative.The diagnostic criteria solitary and its management aspects are discussed.
Purpose: The authors sought to examine relationships between CT metrics derived via an automated method and clinical parameters of extraocular muscle changes in thyroid eye disease (TED). Methods: images 204 orbits the setting TED were analyzed with segmentation tool developed at institution. Labels applied orbital structures interest on study images, which then registered against a previously established atlas manually indexed from 35 healthy individuals. Point-wise correspondences compared...
Eye diseases and visual impairment affect millions of Americans induce billions dollars in annual economic burdens. Expounding upon existing knowledge eye could lead to improved treatment disease prevention. This research investigated the relationship between structural metrics orbit function measurements a cohort 470 patients from retrospective study ophthalmology records for (with thyroid disease, orbital inflammation, optic nerve edema, glaucoma, intrinsic disease), clinical imaging,...
We examine imaging and electronic medical records (EMR) of 588 subjects over five major disease groups that affect optic nerve function. An objective evaluation the role EMR data in diagnosis these conditions would improve understanding diseases help early intervention. developed an automated image processing pipeline identifies orbital structures within human eyes from computed tomography (CT) scans, calculates structural size, performs volume measurements. customized EMR-based phenome-wide...