A5038840367- Chronic Obstructive Pulmonary Disease (COPD) Research
- AI in cancer detection
- Cell Image Analysis Techniques
- Medical Image Segmentation Techniques
- Image Processing Techniques and Applications
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Lung Cancer Diagnosis and Treatment
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Respiratory Support and Mechanisms
- COVID-19 diagnosis using AI
- Transplantation: Methods and Outcomes
- Advanced Image Processing Techniques
- Asthma and respiratory diseases
- Cystic Fibrosis Research Advances
- Visual Attention and Saliency Detection
- Image Retrieval and Classification Techniques
- Inhalation and Respiratory Drug Delivery
- Image and Signal Denoising Methods
- Delphi Technique in Research
- Advanced X-ray and CT Imaging
- Vehicle License Plate Recognition
- Medical Imaging Techniques and Applications
University of Michigan
2018-2025
Emory University
2025
The Wallace H. Coulter Department of Biomedical Engineering
2025
Georgia Institute of Technology
2025
Emory and Henry College
2025
Michigan United
2021-2024
Michigan Medicine
2020-2021
Cornell University
2017-2018
University of Arizona
2010-2016
Parkland Memorial Hospital
1995
Nonlocal texture similarity and local intensity smoothness are both essential for solving most image inpainting problems. In this paper, we propose a novel algorithm that is capable of reproducing the underlying textural details using nonlocal measure also smoothing pixel seamlessly in order to achieve natural-looking inpainted images. For matching texture, Gaussian-weighted obtain multiple candidate patches each target patch. To compute intensity, apply -trimmed mean filter inpaint patch...
To help prevent motor vehicle accidents, there has been significant interest in finding an automated method to recognize signs of driver distraction, such as talking passengers, fixing hair and makeup, eating drinking, using a mobile phone. In this paper, we present supervised learning called Drive-Net for distraction detection. uses combination convolutional neural network (CNN) random decision forest classifying images driver. We compare the performance our proposed two other popular...
Early detection of lung cancer is critical for improvement patient survival. To address the clinical need efficacious treatments, genetically engineered mouse models (GEMM) have become integral in identifying and evaluating molecular underpinnings this complex disease that may be exploited as therapeutic targets. Assessment GEMM tumor burden on histopathological sections performed by manual inspection both time consuming prone to subjective bias. Therefore, an interplay needs challenges...
Parametric response mapping (PRM) is a novel computed tomography (CT) technology that has shown potential for assessment of bronchiolitis obliterans syndrome (BOS) after hematopoietic stem cell transplantation (HCT). The primary aim this study was to evaluate whether variations in image acquisition under real-world conditions affect the PRM measurements clinically diagnosed BOS. CT scans were obtained retrospectively from 72 HCT recipients with BOS and graft-versus-host disease Fred...
Abstract Background Small airways disease (SAD) is a major cause of airflow obstruction in COPD patients and has been identified as precursor to emphysema. Although the amount SAD lungs can be quantified using our Parametric Response Mapping (PRM) approach, full breadth this readout measure emphysema progression yet explored. We evaluated topological features PRM-derived normal parenchyma surrogates predictors spirometric decline. Methods PRM metrics lung (PRM Norm ) functional fSAD were...
Accurate detection of individual cell nuclei in microscopy images is an essential and fundamental task for many biological studies. In particular, multivariate fluorescence used to observe different aspects cells cultures. Manual by visual inspection time consuming, prone induce subjective bias. This makes automatic large-scale, objective studies Blur, clutter, bleed-through, imaging noise touching partially overlapping with varying sizes shapes make automated a challenging using image...
Denoising is a fundamental task in image processing, aimed at estimating an unknown from its noisy observation. In this paper, we develop computationally simple paradigm for denoising using superpixel grouping and principal component analysis (PCA) of similar patches within the superpixels. Our method comprises three steps. First, perform segmentation on images. Next, superpixels are grouped order to preserve local structures. Finally, each group factorized by PCA transform estimated...
Travel planning is a complex and dynamic process influenced by multiple factors, including user preferences, real-time availability of flights accommodations, weather conditions, local attractions. Traditional itinerary planners lack adaptability, leading to suboptimal recommendations. This research presents an AI-powered travel system that leverages machine learning, data aggregation, predictive analytics generate personalized itineraries. The integrates Natural Language Processing for...
Abstract Chronic obstructive pulmonary disease (COPD) is complex, and its course difficult to predict due diverse pathophysiology. Small airway (SAD), a key component of COPD potential target for emerging therapeutics, may be reversible in mild COPD, but left unchecked, worsen, leading loss emphysema. The dual nature SAD complicates clinical management patients, necessitating more accurate monitoring methods. To meet this need, we developed elastic Parametric Response Mapping (ePRM), tiered...
An ambulance siren produces a sound pressure level of around 100 dB. This results in continuous exposure noise inside the for patient and further deteriorates patient’s health. Feedback active control (ANC) with virtual sensing technique (VST) has been applied to various applications minimize noise. The advantage feedback ANC over feedforward is that it generates its own reference using error signal. In contrast, requires achieve good attenuation can increase complexity algorithm....
Abstract Background Efforts to phenotype veterans that developed respiratory symptoms following deployments the Southwest Asia Theater of Military Operation have been limited by insensitivity current non-invasive testing objectively identify deployment-related constrictive bronchiolitis and other features chronic lung injury. In this study, we derived a quantitative CT (QCT)-based radiographic biopsy-proven (DRCB) assessed its ability assist in phenotyping non-biopsied formerly deployed...
Abstract The 3D spatial organization of genes and other genetic elements within the nucleus is important for regulating gene expression. Understanding how this established maintained throughout life a cell key to elucidating many layers regulation. Quantitative methods studying nuclear will lead insights into molecular mechanisms that maintain as well serve diagnostic tools pathologies caused by loss structure. However, biologists currently lack automated high throughput quantitative...
Accurate detection and localization of vehicles in aerial images has a wide range applications including urban planning, military reconnaissance, visual surveillance, realtime traffic management. Automated imagery is challenging task, due to the density on road, complexity surrounding environment areas, low spatial resolution image sensor array. We propose an automated method for detecting varying sizes low-resolution imagery. First, we develop new vehicle enhancement filter involving...
The lamina cribrosa (LC) is a connective tissue in the posterior eye with complex mesh-like trabecular microstructure, through which all retinal ganglion cell axons and central vessels pass. Recent studies have demonstrated that changes structure of LC correlate glaucomatous damage. Thus, accurate segmentation reconstruction utmost importance. This paper presents new automated method for segmenting microstructure anterior images obtained via multiphoton microscopy using combination ideas. In...
Background Radiologic evidence of air trapping (AT) on expiratory computed tomography (CT) scans is associated with early pulmonary dysfunction in patients cystic fibrosis (CF). However, standard techniques for quantitative assessment AT are highly variable, resulting limited efficacy monitoring disease progression. Objective To investigate the effectiveness a convolutional neural network (CNN) model quantifying and AT, to compare it other measures obtained from threshold-based techniques....
Chronic obstructive pulmonary disease (COPD) exhibits considerable progression heterogeneity. We hypothesized that elastic principal graph analysis (EPGA) would identify distinct clinical phenotypes and their longitudinal relationships.
This paper presents a new method of producing high-resolution image from single low-resolution without any external training sets. We use dictionary-based regression model for practical super-resolution using local self-similar example patches within the image. Our is inspired by observation that can be well represented as sparse linear combination elements chosen over-complete dictionary and patch in have good matches around its corresponding location A first-order approximation nonlinear...
Accurate segmentation of 3-D cell nuclei in microscopy images is an essential task many biological studies. Traditional image methods are challenged by the complexity and variability microscope images, so there a need to improve accuracy reliability, as well level automation. In this paper we present novel automated algorithm for robust using combination ideas. Our includes following steps: denoising, binarization, seed detection fast radial symmetric transform (FRST), initial random walker...