A5014545564- Morphological variations and asymmetry
- Medical Image Segmentation Techniques
- Optical Coherence Tomography Applications
- 3D Shape Modeling and Analysis
- Advanced Neuroimaging Techniques and Applications
- Orthopedic Surgery and Rehabilitation
- Advanced X-ray and CT Imaging
- Advanced Vision and Imaging
- Advanced MRI Techniques and Applications
- Glaucoma and retinal disorders
- Image Retrieval and Classification Techniques
- Photoacoustic and Ultrasonic Imaging
- Retinal Imaging and Analysis
- Corneal surgery and disorders
- Dental Radiography and Imaging
- Medical Imaging and Analysis
- AI in cancer detection
- Genetic Neurodegenerative Diseases
- Cell Image Analysis Techniques
- Image and Signal Denoising Methods
- Statistical and numerical algorithms
- Image Processing Techniques and Applications
- Imbalanced Data Classification Techniques
- Point processes and geometric inequalities
- Advanced Image Processing Techniques
New York University
2016-2024
Kitware (United States)
2023
Brooklyn Technical High School
2016
University of Utah
2011-2014
Advanced Imaging Research (United States)
2013-2014
University of Iowa
1996
Quantitative MRI can detect early changes in cartilage biochemical components, but its routine clinical implementation is challenging.
Deep networks are now ubiquitous in large-scale multi-center imaging studies. However, the direct aggregation of images across sites is contraindicated for downstream statistical and deep learning-based image analysis due to inconsistent contrast, resolution, noise. To this end, absence paired data, variations Cycle-consistent Generative Adversarial Networks have been used harmonize sets between a source target domain. Importantly, these methods prone instability, contrast inversion,...
A variety of regression schemes have been proposed on images or shapes, although available methods do not handle them jointly. In this paper, we present a framework for joint image and shape which incorporates as well anatomical information in consistent manner. Evolution is described by generative model that the analog linear regression, fully characterized baseline shapes (intercept) initial momenta vectors (slope). Further, our adopts control point parameterization deformations, where...
The skull of young children is made up bony plates that enable growth. Craniosynostosis a birth defect causes one or more sutures on an infant’s to close prematurely. Corrective surgery focuses cranial and orbital rim shaping return the normal shape. Functional problems caused by craniosynostosis such as speech motor delay can improve after surgical correction, but post-surgical analysis brain development in comparison with age-matched healthy controls necessary assess outcome. Full...
Static MRI and CT are both limited in their capacity usability the study of wrist kinematics living human subjects. 4D provides an effective means to addressing these limitations but it comes with its own set challenges, including low resolution anisotropic voxel size. In this paper, we describe our methodology effectively solve challenges quantify 3D dynamic data acquired from two volunteers using MRI.
The goal of longitudinal shape analysis is to understand how anatomical changes over time, in response biological processes, including growth, aging, or disease. In many imaging studies, it also critical these are affected by other factors, such as sex, disease diagnosis, IQ, etc. Current approaches have focused on modeling age-related changes, but not included the ability handle covariates. this paper, we present a novel Bayesian mixed-effects model that incorporates simultaneous...
Traditional longitudinal analysis begins by extracting desired clinical measurements, such as volume or head circumference, from discrete imaging data. Typically, the continuous evolution of a scalar measurement is estimated choosing 1D regression model, kernel fitting polynomial fixed degree. This type not only leads to separate models for each measurement, but there no clear anatomical biological interpretation aid in selection appropriate paradigm. In this paper, we propose consistent...
Convolutional neural network based segmentation models have shown success in teeth from cone beam computed tomography (CBCT) scans. However, trained often fail to generalize new acquisitions when scanner protocols shift and upgrade. This problem is well-known by the machine learning community as domain shift. To address this an unsupervised manner, we demonstrate first time application of 3D Fourier Domain Adaptation a tooth model source for adapted target domain. Our experiments that...
The analysis of medical image time-series is becoming increasingly important as longitudinal imaging studies are maturing and large scale open databases available. Image regression widely used for several purposes: a statistical representation hypothesis testing, to bring clinical scores images not acquired at the same time into temporal correspondence, or consistency filter enforce correlation. Geodesic most prominent method, but geodesic constraint limits flexibility therefore application...
Statistical shape analysis captures the geometric properties of a given set shapes, obtained from medical images, by means statistical methods. Orthognathic surgery is type craniofacial that aimed at correcting severe skeletal deformities in mandible and maxilla. Methods assuming spherical topology cannot represent class anatomical structures exhibiting complex geometries topologies, including mandible. In this paper we propose methodology based on non-rigid deformations 3D to be applied...
Longitudinal shape analysis has shown great potential to model anatomical processes from baseline follow-up observations. Shape regression estimates a continuous trajectory of time-discrete shapes quantify temporal changes. The need for alignment and point-to-point correspondences represent limitations current methodologies, present significant challenges in evaluation. We propose method that medial representations (CM-Rep) set observed shapes. To avoid the traditional step aligning...
Modeling subject-specific shape change is one of the most important challenges in longitudinal analysis disease progression. Whereas anatomical over time can be a function normal aging, anatomy also impacted by related degeneration. Anatomical may affected structural changes from neighboring shapes, which cause non-linear variations pose. In this paper, we propose framework to analyze coupling extrinsic modeling ambient space via spatiotemporal deformations with intrinsic properties medial...