A5004575115- Computer Graphics and Visualization Techniques
- Data Visualization and Analytics
- 3D Shape Modeling and Analysis
- Functional Brain Connectivity Studies
- Computational Geometry and Mesh Generation
- Advanced Numerical Analysis Techniques
- Advanced Vision and Imaging
- Advanced Neuroimaging Techniques and Applications
- Bioinformatics and Genomic Networks
- Cell Image Analysis Techniques
- Medical Image Segmentation Techniques
- Digital Image Processing Techniques
- Face recognition and analysis
- Data Mining Algorithms and Applications
- Complex Network Analysis Techniques
- Biomedical Text Mining and Ontologies
- Alzheimer's disease research and treatments
- Advanced Text Analysis Techniques
- Image Processing and 3D Reconstruction
- Orthodontics and Dentofacial Orthopedics
- Dementia and Cognitive Impairment Research
- Neonatal and fetal brain pathology
- Medical Imaging Techniques and Applications
- Face and Expression Recognition
- Explainable Artificial Intelligence (XAI)
Indiana University – Purdue University Indianapolis
2016-2025
Indiana University Indianapolis
2024-2025
University of Indianapolis
2013-2023
Indiana University School of Medicine
2017
North Carolina State University
2014
Purdue University West Lafayette
2010-2013
Indiana University
2011-2012
Sun Yat-sen University
2012
Åbo Akademi University
2008
National University of Singapore
1995-2002
Confocal and two-photon fluorescence microscopy have advanced the exploration of complex, three-dimensional biological structures at submicron resolution. We developed a voxel-based (3-D) imaging program (Voxx) capable near real-time rendering that runs on inexpensive personal computers. This low-cost interactive 3-D system provides powerful tool for analyzing complex in cells tissues encourages more thorough image data.
Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment memory and other cognitive functions.Multivariate regression models have been studied in AD for revealing relationships between neuroimaging measures scores to understand how structural changes brain can influence status.Existing methods, however, do not explicitly model dependence relation among multiple derived from a single test.It has found such deteriorate performance these methods.To...
Predicting cognitive performance of subjects from their magnetic resonance imaging (MRI) measures and identifying relevant biomarkers are important research topics in the study Alzheimer's disease. Traditionally, this task is performed by formulating a linear regression problem. Recently, it found that using sparse model can achieve better prediction accuracy. However, most existing studies only focus on exploitation sparsity coefficients, ignoring useful structure information coefficients....
Transfer function design is an integrated component in volume visualization and data exploration. The common trial-and-error approach for transfer searching a very difficult time consuming process. A goal oriented parameterized model therefore crucial guiding the process better more meaningful results. paper presents image based that integrates 3D processing tools into pipeline to facilitate search defines as sequence of procedures, allows users adjust set qualitative descriptive parameters...
Computer vision and pattern recognition systems play an important role in our lives by means of automated face detection, gesture recognition, estimation gender age. This paper addresses the problem classification using frontal facial images. We have developed classifiers with performance superior to existing classifiers. experiment on 500 images (250 females 250 males) randomly withdrawn from FERET database. Independent component analysis (ICA) is used represent each image as a feature...
Structured Abstract Authors – Fang S, McLaughlin J, Huang Autti‐Rämö I, Fagerlund Å, Jacobson SW, Robinson LK, Hoyme HE, Mattson SN, Riley E, Zhou F, Ward R, Moore ES, Foroud T, and the Collaborative Initiative on Fetal Alcohol Spectrum Disorders. Objectives Use three‐dimensional (3D) facial laser scanned images from children with fetal alcohol syndrome (FAS) controls to develop an automated diagnosis technique that can reliably accurately identify individuals prenatally exposed alcohol....
Machine learning algorithms and traditional data mining process usually require a large volume of to train the algorithm-specific models, with little or no user feedback during model building process. Such "big data" based automatic strategy is sometimes unrealistic for applications where collection processing very expensive difficult, such as in clinical trials. Furthermore, expert knowledge can be valuable some fields biomedical sciences. In this paper, we propose new visual analytics...
Rendering deformable volume data currently needs separate processes for deformation and rendering, is expensive in terms of both computational memory costs. Recognizing the importance unifying these processes, we present a new approach to direct rendering volumes without explicitly constructing intermediate deformed volumes. The done by radial basis function that piecewise linearly approximated an adaptive subdivision octree encoded target volume. blocks are then projected, reverse morphed...
Volume morphing is a technique used for generating smooth 3D image transformations and deformations. In this paper, several algorithms are developed that create new forms simulate shape deformation growth in biomedical applications. Three-dimensional biological point landmarks their movements defined to guide the transformation using scattered data interpolation algorithm. Two types of algorithms, Shepard-based radial basis function approach, investigated detail applied volume predictions...
Transfer function design is an integrated component in volume visualization and data exploration. The common trial-and-error approach for transfer searching a very difficult time consuming process. A goal oriented parameterized model therefore crucial guiding the process better more meaningful results. paper presents image based that integrates 3D processing tools into pipeline to facilitate search defines as sequence of procedures, allows users adjust set qualitative descriptive parameters...
Article Free Access Share on Fast CSG voxelization by frame buffer pixel mapping Authors: Shiaofen Fang Department of Computer and Information Science, Indiana University Purdue Indianapolis 723 W. Michigan St., SL 280, Indianapolis, IN INView Profile , Duoduo Liao IndianapolisView Authors Info & Claims VVS '00: Proceedings the 2000 IEEE symposium Volume visualizationOctober Pages 43–48https://doi.org/10.1145/353888.353896Published:09 October 2000Publication History...
In this paper, we will present an unsupervised approach for segmenting medical volume images based on texture properties. The properties of the data are defined spatial frequencies as implemented using a statistical method known Gabor filters. Each filter in bank is tuned to detect patterns specific frequency and orientation when convolved with volume. convolution performed Fourier domain resulting response image feature which added our vector. vector thus passed into...
Abstract This paper presents a new approach to the voxelization of threedimensional synthetic objects. It makes use existing graphics hardware on standard workstations, such as polygon-based geometry engine and frame buffer operations, is able generate voxel-based volume representations general curves, surfaces, or solid objects efficiently. On workstation with hardwaresupported texture mapping, result may also be written directly three-dimensional memory object, interactively rendered by...
CSG modeling using volumetric techniques is a new and promising approach. Due to the need for large volume data processing, however, it difficult perform interactive without special hardware systems. In this paper, we present fast technique standard graphics hardware. The algorithm builds pipeline by slice sweeping, significant improvement over our earlier work on model voxelization. To achieve modeling, makes use of OpenGL features apply acceleration object slicing other operations. Two...