A5054724759- Medical Imaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Computer Graphics and Visualization Techniques
- Advanced Radiotherapy Techniques
- Pressure Ulcer Prevention and Management
- Advanced X-ray and CT Imaging
- Diabetic Foot Ulcer Assessment and Management
- Advanced Vision and Imaging
- Wound Healing and Treatments
- Radiomics and Machine Learning in Medical Imaging
- Image Enhancement Techniques
- Medical Image Segmentation Techniques
- Image and Video Quality Assessment
- Data Visualization and Analytics
- Semiconductor materials and devices
- Radiation Dose and Imaging
- Integrated Circuits and Semiconductor Failure Analysis
- Semiconductor Quantum Structures and Devices
- Behavioral Health and Interventions
- Atomic and Subatomic Physics Research
- Lysosomal Storage Disorders Research
- Cardiac Imaging and Diagnostics
- Video Coding and Compression Technologies
- Physical Activity and Health
- Color Science and Applications
University of Massachusetts Chan Medical School
2016-2025
Worcester Polytechnic Institute
2006-2021
UMass Memorial Health Care
2020
Materials Technology (United Kingdom)
1993-2002
Unilever (United Kingdom)
1993
Hydro One (Canada)
1984
Abstract Background Radiomic analysis of quantitative features extracted from segmented medical images can be used for predictive modeling prognosis in brain tumor patients. Manual segmentation the components is time-consuming and poses significant reproducibility issues. We compare prediction overall survival (OS) recurrent high-grade glioma(HGG) patients undergoing immunotherapy, using deep learning (DL) classification networks along with radiomic signatures derived manual convolutional...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Goal:</i> Augment a small, imbalanced, wound dataset by using semi-supervised learning with secondary dataset. Then utilize the augmented for deep learning-based assessment. xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> The clinically-validated Photographic Wound Assessment Tool (PWAT) scores eight attributes: Size, Depth, Necrotic Tissue Type, Amount, Granulation type, Edges,...
Smartphone wound image analysis has recently emerged as a viable way to assess healing progress and provide actionable feedback patients caregivers between hospital appointments. Segmentation is key step, after which attributes of the segment (e.g. area tissue composition) can be analyzed. The Associated Hierarchical Random Field (AHRF) formulates segmentation problem graph optimization problem. Handcrafted features are extracted, then classified using machine learning classifiers. More deep...
Diabetes mellitus is a serious chronic disease that affects millions of people worldwide. In patients with diabetes, ulcers occur frequently and heal slowly. Grading staging diabetic the first step effective treatment wound depth granulation tissue amount are two important indicators healing progress. However, depths different severities can visually appear quite similar, making accurate machine learning classification challenging. this paper, we innovatively adopted fine-grained idea for...
Purpose GM1-gangliosidosis (GM1) leads to extensive neurodegenerative changes and atrophy that precludes the use of automated MRI segmentation techniques for generating brain volumetrics. We developed a standardized protocol MRIs patients with type II GM1 then assessed inter- intra-rater reliability this methodology. The volumetric data may be used as biomarker disease burden progression, methodology support research into natural history which is currently lacking in literature. Approach...
Head motion during PET brain imaging can cause significant degradation of image quality. Several authors have proposed ways to compensate for restore quality and improve quantitation. restraints reduce movement but are unreliable; thus the need alternative strategies such as data-driven estimation or external tracking. Herein, present a method using preprocessing technique that allows usage very short duration frames, reducing intraframe problem commonly observed in multiple frame...
Abstract Background and objectives Vascular disease is a known risk factor for Alzheimer’s (AD). Endothelial dysfunction has been linked to reduced cerebral blood flow. nitric oxide synthase pathway (eNOS) upregulation support endothelial health. This single-center, proof-of-concept study tested whether the use of three medications augment eNOS activity improves cognition flow (CBF). Methods Subjects with mild AD or cognitive impairment (MCI) were sequentially treated HMG-CoA reductase...
Respiratory motion induces artifacts in reconstructed cardiac perfusion SPECT images. Correction for respiratory often relies on a signal describing the heart displacements during breathing. However, using external tracking devices to estimate signals can add cost and operational complications clinical setting.
Respiratory motion of the heart impacts diagnostic accuracy myocardial-perfusion emission-imaging studies. Amplitude binning has come to be method choice for list-mode based acquisitions correction respiratory in PET and SPECT. In some subjects exhibits hysteretic behavior similar damped non-linear cyclic systems. The detection hysteresis between signals from surface movement patient's body used within chest remains an open area investigation. This study reports our investigation nine...
The development of methods for correcting patient motion in emission tomography has been receiving increased attention. Often the performance these is evaluated through simulations using digital anthropomorphic phantoms, such as commonly used extended cardiac torso (XCAT) phantom, which models both respiratory and based on human studies. However, non-rigid body motion, frequently seen clinical studies, not present standard XCAT phantom. In addition, phantom limited to a single generic trend....
Abstract Segmentation of glioma is crucial for quantitative brain tumor assessment, to guide therapeutic research and clinical management, but very time-consuming. Fully automated tools the segmentation multi-sequence MRI are needed. We developed pretrained a deep learning (DL) model using publicly available datasets A ( n = 210) B 369) containing FLAIR, T2WI, contrast-enhanced (CE)-T1WI. This was then fine-tuned with our institutional dataset 197) ADC, CE-T1WI, manually annotated by...
Deep learning (DL) is becoming increasingly important in generating attenuation maps for accurate correction (AC) cardiac perfusion SPECT imaging. Typically, DL models take inputs from initial reconstructed images, which are performed on the photopeak window and often also scatter windows. While prior studies have demonstrated improvements performance when images incorporated into input, comprehensive analysis of impact employing different windows remains unassessed. Additionally, existing...
Purpose: Binning list‐mode acquisitions as a function of surrogate signal related to respiration has been employed reduce the impact respiratory motion on image quality in cardiac emission tomography (SPECT and PET). Inherent amplitude binning is assumption that there monotonic relationship between heart. This not valid presence hysteresis when heart exhibits different with during inspiration expiration. The purpose this study was investigate novel approach using Bouc–Wen (BW) model provide...
Chronic wounds affect 6.5 million Americans. Wound assessment via algorithmic analysis of smartphone images has emerged as a viable option for remote assessment.We comprehensively score based on the clinically-validated Photographic Assessment Tool (PWAT), which assesses clinically important ranges eight wound attributes: Size, Depth, Necrotic Tissue Type, Amount, Granulation type, Edges, Periulcer Skin Viability. We proposed DenseNet Convolutional Neural Network (CNN) framework with...
Background Alcohol use disorder (AUD) is associated with severe chronic medical conditions and premature mortality. Expanding the reach or access to effective evidence-based treatments help persons AUD a public health objective. Mobile phone smartphone technology has potential increase dissemination of clinical behavioral interventions (mobile interventions) that initiation maintenance sobriety among individuals AUD. Studies about how this group uses their mobile attitudes toward may have...
Abstract Objective. Monte-Carlo simulation studies have been essential for advancing various developments in single photon emission computed tomography (SPECT) imaging, such as system design and accurate image reconstruction. Among the software available, Geant4 application tomographic (GATE) is one of most used toolkits nuclear medicine, which allows building systems attenuation phantom geometries based on combination idealized volumes. However, these volumes are inadequate modeling...
Ontario Hydro has had four or more years of service experience with gas-insulated substations (GIS) rated at 500 kV and 230 80 kA. Initially, the stations were fraught problems, due mainly to equipment being prototype. Most problems have now been corrected reliability maintainability are satisfactory, comparable rest system. A number proposals made improve future GIS.