A5081218376- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- Advanced X-ray and CT Imaging
- Digital Radiography and Breast Imaging
- Radiology practices and education
- Radiation Dose and Imaging
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Cardiac Imaging and Diagnostics
- Dementia and Cognitive Impairment Research
- Medical Imaging and Analysis
- Sarcoidosis and Beryllium Toxicity Research
- Global Cancer Incidence and Screening
- Machine Learning in Healthcare
- Lung Cancer Diagnosis and Treatment
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Dental Radiography and Imaging
- Brain Metastases and Treatment
- Nicotinic Acetylcholine Receptors Study
- Hip and Femur Fractures
- Periodontal Regeneration and Treatments
- Generative Adversarial Networks and Image Synthesis
- Dental Implant Techniques and Outcomes
- Coronary Interventions and Diagnostics
WinnMed
2021-2024
Mayo Clinic in Florida
2020-2024
Jacksonville College
2021-2023
The Ohio State University
2011-2022
The Ohio State University Wexner Medical Center
2012-2022
Park University
2022
Mayo Clinic Hospital
2021
Novartis (Switzerland)
2020
Eli Lilly (United States)
2020
Alzheimer’s Disease Neuroimaging Initiative
2020
Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications AI in healthcare have the potential to improve our ability detect, diagnose, prognose, and intervene on human disease. For models be used clinically, they need made safe, reproducible robust, underlying software framework must aware particularities (e.g. geometry, physiology, physics) medical data being processed. This work introduces MONAI, freely available, community-supported,...
Purpose To evaluate the performance of an artificial intelligence (AI) tool using a deep learning algorithm for detecting hemorrhage, mass effect, or hydrocephalus (HMH) at non-contrast material-enhanced head computed tomographic (CT) examinations and to determine detection suspected acute infarct (SAI). Materials Methods This HIPAA-compliant retrospective study was completed after institutional review board approval. A training validation dataset noncontrast-enhanced CT that comprised 100...
Brain Metastases (BM) complicate 20-40% of cancer cases. BM lesions can present as punctate (1 mm) foci, requiring high-precision Magnetic Resonance Imaging (MRI) in order to prevent inadequate or delayed treatment. However, lesion detection remains challenging partly due their structural similarities normal structures (e.g., vasculature). We propose a BM-detection framework using single-sequence gadolinium-enhanced T1-weighted 3D MRI dataset. The focuses on the smaller (<; 15 and consists...
We present a roadmap for integrating artificial intelligence (AI)-based image analysis algorithms into existing radiology workflows such that (1) radiologists can significantly benefit from enhanced automation in various imaging tasks due to AI, and (2) radiologists’ feedback is utilized further improve the AI application. This achieved by establishing three maturity levels where research enables visualization of AI-based results/annotations without generating new patient records; production...
The purpose of this study was to investigate the radiogenomic correlation between CT gray-level texture features and epidermal growth factor receptor (EGFR) mutation status in adenocarcinoma lung.This retrospective included 25 patients with exon 19 short inframe deletion (exon 19) 21 L858R point 21) EGFR mutations among 125 mutant lung. randomly formed control group consisted 20 selected from 126 mutation-negative (wild-type) adenocarcinomas. Five (contrast, correlation, inverse difference...
To delineate image data curation needs and describe a locally designed graphical user interface (GUI) to aid radiologists in annotation for artificial intelligence (AI) applications medical imaging.GUI components support analysis toolboxes, picture archiving communication system integration, third-party applications, processing of scripting languages, integration deep learning libraries. For clinical AI GUI included two-dimensional segmentation classification; three-dimensional...
Artificial intelligence (AI) has become commonplace in solving routine everyday tasks. Because of the exponential growth medical imaging data volume and complexity, workload on radiologists is steadily increasing. AI been shown to improve efficiency image generation, processing, interpretation, various such models have developed across research laboratories worldwide. However, very few these, if any, find their way into clinical use, a discrepancy that reflects divide between successful...
Consistency and duplicability in Computed Tomography (CT) output is essential to quantitative imaging for lung cancer detection monitoring. This study of CT-detected nodules investigated the reproducibility volume-, density-, texture-based features (outcome variables) over routine ranges radiation dose, reconstruction kernel, slice thickness. CT raw data 23 were reconstructed using 320 acquisition/reconstruction conditions (combinations 4 doses, 10 kernels, 8 thicknesses). Scans at 12.5%,...
Acute Proximal Femoral Fractures are a growing health concern among the aging population. These fractures often associated with significant morbidity and mortality as well reduced quality of life. Furthermore, increasing life expectancy owing to advances in healthcare, number proximal femoral may increase by factor 2 3, since majority occur patients over age 65. In this paper, we show that using transfer learning leveraging pre-trained models, can achieve very high accuracy detecting they be...
Purpose: Sharing medical images between institutions, or even inside the same institution, is restricted by various laws and regulations; research projects requiring large datasets may suffer as a result. These limitations might be addressed an abundant supply of synthetic data that (1) are representative (i.e., could produce comparable results original data) (2) do not closely resemble patient privacy protected). We introduce framework generates with these requirements leveraging generative...
Background: Postextraction alveolar bone loss, mostly affecting the buccal plate, occurs despite regenerative procedures. To better understand possible determinants, this prospective case series assesses gingival blood perfusion and tissue molecular responses in relation to postextraction outcomes. Methods: Adults scheduled receive grafting maxillary, non‐molar, single‐tooth extraction sites were recruited. Clinical documentation included following: 1) probing depth (PD); 2) keratinized...
Abstract Background This study aimed to determine and compare soft tissue healing outcomes following implant placement in grafted (GG) non‐grafted bone (NGG). Methods Patients receiving single a tooth‐bound maxillary non‐molar site were recruited. Clinical was documented. Volume content of wound fluid (WF; at 3, 6, 9 days) compared with adjacent gingival crevicular (GCF; baseline, 1, 4 months). Buccal flap blood perfusion recovery changes thickness recorded. Linear mixed model regression...
Summary Objective: To qualify the use of patient clinical records as non-human-subject for research purpose, electronic medical record data must be de-identified so there is minimum risk to protected health information exposure. This study demonstrated a robust framework structured de-identification that can applied any relational source needs de-identified. Methods: Using real world warehouse, pilot implementation limited subject areas were used demonstrate and evaluate this new process....
Radiology and Enterprise Medical Imaging Extensions (REMIX) is a platform originally designed to both support the medical imaging-driven clinical research operational needs of Department The Ohio State University Wexner Center. REMIX accommodates storage handling "big imaging data," as needed for large multi-disciplinary cancer-focused programs. evolving contains an array integrated tools/software packages following: (1) server management; (2) image reconstruction; (3) digital pathology; (4)...
Purpose: Our study investigates whether a machine-learning-based system can predict the rate of cognitive decline in mildly cognitively impaired patients by processing only clinical and imaging data collected at initial visit. Approach: We built predictive model based on supervised hybrid neural network utilizing three-dimensional convolutional to perform volume analysis magnetic resonance (MRI) integration nonimaging fully connected layer architecture. The experiments are conducted...