A5102835648- Medical Image Segmentation Techniques
- Morphological variations and asymmetry
- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neuroimaging Techniques and Applications
- Advanced MRI Techniques and Applications
- Image Retrieval and Classification Techniques
- Medical Imaging and Analysis
- 3D Shape Modeling and Analysis
- Functional Brain Connectivity Studies
- Cell Image Analysis Techniques
- MRI in cancer diagnosis
- AI in cancer detection
- Advanced X-ray and CT Imaging
- Lung Cancer Diagnosis and Treatment
- Generative Adversarial Networks and Image Synthesis
- Topological and Geometric Data Analysis
- Radiation Therapy and Dosimetry
- Advanced Vision and Imaging
- Image Processing and 3D Reconstruction
- Computer Graphics and Visualization Techniques
- Markov Chains and Monte Carlo Methods
- Digital Image Processing Techniques
- Robotics and Sensor-Based Localization
University of Utah
2016-2025
AISSMS Institute of Information Technology
2023
University of California, Los Angeles
2022
Florida State University
2022
University of Virginia
2022
Symbiosis International University
2022
University of Copenhagen
2021
Armed Forces College of Medicine
2021
Indian Navy
2021
Georgia Institute of Technology
2020
This paper describes the generation of large deformation diffeomorphisms phi:Omega=[0,1]3<-->Omega for landmark matching generated as solutions to transport equation dphi(x,t)/dt=nu(phi(x,t),t),epsilon[0,1] and phi(x,0)=x, with image map defined phi(.,1) therefore controlled via velocity field nu(.,t),epsilon[0,1]. Imagery are assumed characterized sets landmarks {xn, yn, n=1, 2, ..., N}. The optimal diffeomorphic match is constructed minimize a running smoothness cost parallelLnu parallel2...
Theories of the pathophysiology schizophrenia have implicated hippocampus, but controversy remains regarding hippocampal abnormalities in patients with schizophrenia. In vivo studies anatomy using high resolution magnetic resonance scanning and manual methods for volumetric measurement yielded inconclusive results, perhaps because normal variability volume error involved techniques. To resolve this controversy, dimensional transformations a computerized brain template were used to compare...
This paper presents diffeomorphic transformations of three-dimensional (3-D) anatomical image data the macaque occipital lobe and whole brain cryosection imagery deep structures in human brains as imaged via magnetic resonance imagery. These are generated a hierarchical manner, accommodating both global local detail. The initial low-dimensional registration is accomplished by constraining transformation to be basis. basis defined Green's function elasticity operator placed at predefined...
This paper presents a comprehensive review of the latest development in Generative AI and Big Data with application Finance. 2025 is year Agentic AI, marking pivotal shift generative (Gen AI) its integration big data. explores synergies between Gen data, particularly financial risk management, proposing strategies for deeper integration. By citing white papers focusing on developments over past two years, we expand scope research this transformative domain. Recent advancements such as GPT-4,...
Four‐dimensional (4D) radiotherapy is the explicit inclusion of temporal changes in anatomy during imaging, planning, and delivery radiotherapy. Temporal anatomic can occur for many reasons, though focus current investigation respiration motion lung tumors. The aim this study was to develop 4D treatment‐planning methodology DMLC‐based respiratory tracking. A computed tomography (CT) scan consisting a series eight 3D CT image sets acquired at different phases used treatment planning....
During early postnatal development, corticospinal (CS) system stimulation, electrical or transcranial magnetic, is minimally effective in producing muscle contraction, despite having axon terminals that excite spinal neurons. Later, after stimulation becomes more effective, the cortical motor representation develops, and movements controls maturity are expressed. We determined whether development of temporal facilitation (response enhancement produced by second a pair pyramidal tract...
To test automated three-dimensional magnetic resonance (MR) imaging morphometry of the human hippocampus, to determine potential gain in precision compared with conventional manual morphometry.A canonical MR image atlas was used as a deformable template and automatically matched images 10 individuals (five healthy five schizophrenic subjects). A subvolume containing hippocampus defined by using 16 landmarks that constrained search for hippocampal boundaries. Transformation performed global...
Regression analysis is a powerful tool for the study of changes in dependent variable as function an independent regressor variable, and particular it applicable to anatomical growth shape change. When underlying process can be modeled by parameters Euclidean space, classical regression techniques are have been studied extensively. However, recent work suggests that attempts describe shapes using flat spaces undermines our ability represent natural biological variability. In this paper we...
In this paper, we present and validate a framework, based on deformable image registration, for automatic processing of serial three-dimensional CT images used in image-guided radiation therapy. A major assumption registration has been that, if two are being registered, every point one corresponds appropriately to some the other. For intra-treatment prostate, however, is violated by variable presence bowel gas. The framework presented here explicitly extends previous algorithms accommodate...
The looming potential of deformable alignment tools to play an integral role in adaptive radiotherapy suggests a need for objective assessment these complex algorithms. Previous studies this area are based on the ability reproduce analytically generated deformations applied sample image data, or use contours bifurcations as ground truth evaluation accuracy. In study, phantom was embedded with 48 small plastic markers, placed regions varying from high contrast roughly uniform regional...
The strong radiative forcing by atmospheric methane has stimulated interest in identifying natural and anthropogenic sources of this potent greenhouse gas. Point are important targets for quantification, have potential emissions reduction. Methane point source plume detection concentration retrieval been previously demonstrated using data from the Airborne Visible InfraRed Imaging Spectrometer Next Generation (AVIRIS-NG). Current quantitative methods tradeoffs between computational...
This paper develops mathematical representations for neuro-anatomically significant substructures of the brain and their variability in a population. The focus is on neuro-anatomical variation geometry "shape" two-dimensional surfaces brain. As examples, we cortical hippocampal an ensemble Macaque monkeys human MRI brains. "shapes" are quantified via construction templates; variations represented by defining probabilistic deformations template. Methods empirically estimating probability...
Principal component analysis has proven to be useful for understanding geometric variability in populations of parameterized objects. The statistical framework is well understood when the parameters objects are elements a Euclidean vector space. This certainly case described via landmarks or as dense collection boundary points. We have been developing representations geometry based on medial axis description m-rep. Although this effective, not naturally In paper we show that descriptions...
This paper presents a multiscale framework based on medial representation for the segmentation and shape characterization of anatomical objects in medical imagery. The procedure is Bayesian deformable templates methodology which prior information about geometry incorporated via construction exemplary templates. variability accommodated by defining probabilistic transformations these transformations, thus, defined are parameterized directly terms natural operations, such as growth bending,...