A5075744244- Brain Tumor Detection and Classification
- Advanced Neuroimaging Techniques and Applications
- Medical Image Segmentation Techniques
- Face and Expression Recognition
- Functional Brain Connectivity Studies
- Advanced MRI Techniques and Applications
- MRI in cancer diagnosis
- Radiomics and Machine Learning in Medical Imaging
- Sparse and Compressive Sensing Techniques
- Neonatal and fetal brain pathology
- Image Retrieval and Classification Techniques
- Domain Adaptation and Few-Shot Learning
- Medical Imaging Techniques and Applications
- Neurological Disease Mechanisms and Treatments
- Image and Video Quality Assessment
- Neural dynamics and brain function
- Advanced Image Fusion Techniques
- Medical Imaging and Analysis
- Dental Radiography and Imaging
- Advanced Image and Video Retrieval Techniques
- EEG and Brain-Computer Interfaces
- AI in cancer detection
- Dementia and Cognitive Impairment Research
- Advanced Neural Network Applications
- Text and Document Classification Technologies
University of North Carolina at Chapel Hill
2014-2024
Imaging Center
2013-2024
University of North Carolina Health Care
2020
Laboratoire d’Imagerie Biomédicale
2015
University of Malaya
2004-2011
Accurate classification of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI), plays a critical role in possibly preventing progression memory improving quality life for AD patients. Among many research tasks, it is particular interest to identify noninvasive imaging biomarkers diagnosis. In this paper, we present robust deep learning system different stages patients based on MRI PET scans. We utilized the dropout technique improve classical by weight...
Abstract In this article, the authors aim to maximally utilize multimodality neuroimaging and genetic data for identifying Alzheimer's disease (AD) its prodromal status, Mild Cognitive Impairment (MCI), from normal aging subjects. Multimodality such as MRI PET provide valuable insights into brain abnormalities, while single nucleotide polymorphism (SNP) information about a patient's AD risk factors. When these are used together, accuracy of diagnosis may be improved. However, heterogeneous...
Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray (GM), and cerebrospinal fluid is an indispensable foundation for early studying growth patterns morphological changes in neurodevelopmental disorders. Nevertheless, the isointense phase (approximately 6-9 months age), due to inherent myelination maturation process, WM GM exhibit similar levels intensity both T1-weighted T2-weighted MR images, making tissue very challenging. Although many efforts...
The fusion of complementary information contained in multi-modality data [e.g., magnetic resonance imaging (MRI), positron emission tomography (PET), and genetic data] has advanced the progress automated Alzheimer's disease (AD) diagnosis. However, based AD diagnostic models are often hindered by missing data, i.e., not all subjects have complete data. One simple solution used many previous studies is to discard samples with modalities. this significantly reduces number training samples,...
Image quality assessment is one of the challenging field digital image processing system. It can be done subjectively or objectively. PSNR most popular and widely used objective metric but it not correlate well with subjective assessment. Thus, there are a lot metrics (IQM) developed in past few decades to replace PSNR. This paper provides literature review current measures. The purpose this collect reported group them according their strategies techniques.
Discriminative methods commonly produce models with relatively good generalization abilities. However, this advantage is challenged in real-world applications (e.g., medical image analysis problems), which there often exist outlier data points (sample-outliers) and noises the predictor values (feature-noises). Methods robust to both types of these deviations are somewhat overlooked literature. We further argue that denoising can be more effective, if we learn model using all available...
Abstract Autism spectrum disorder (ASD) is a wide range of disabilities that cause life‐long cognitive impairment and social, communication, behavioral challenges. Early diagnosis medical intervention are important for improving the life quality autistic patients. However, in current practice, often has to be delayed until symptoms become evident during childhood. In this study, we demonstrate feasibility using machine learning techniques identifying high‐risk ASD infants at as early six...
Brain-wide and genome-wide association (BW-GWA) study is presented in this paper to identify the associations between brain imaging phenotypes (i.e., regional volumetric measures) genetic variants [i.e., single nucleotide polymorphism (SNP)] Alzheimer's disease (AD). The main challenges of include data heterogeneity, complex phenotype-genotype associations, high-dimensional (e.g., thousands SNPs), existence phenotype outliers. Previous BW-GWA studies, while addressing some these challenges,...
Cephalometric analysis relies on accurate detection of craniomaxillofacial (CMF) landmarks from cone-beam computed tomography (CBCT) images. However, due to the complexity CMF bony structures, it is difficult localize efficiently and accurately. In this paper, we propose a deep learning framework tackle challenge by jointly digitalizing 105 CBCT By explicitly local geometrical relationships between landmarks, our approach extends Mask R-CNN for end-to-end prediction landmark locations....
Abstract Brain atlases are spatial references for integrating, processing, and analyzing brain features gathered from different individuals, sources, scales. Here we introduce a collection of joint surface–volume that chart postnatal development the human in spatiotemporally dense manner two weeks to years age. Our month-specific normative patterns capture key traits early therefore conducive identifying aberrations normal developmental trajectories. These will enhance our understanding...
In this paper, we propose a multi-view learning method using Magnetic Resonance Imaging (MRI) data for Alzheimer's Disease (AD) diagnosis. Specifically, extract both Region-Of-Interest (ROI) features and Histograms of Oriented Gradient (HOG) from each MRI image, then mapping HOG onto the space ROI to make them comparable impose high intra-class similarity with low inter-class similarity. Finally, mapped original are input support vector machine AD The purpose is provide complementary...
Accurate segmentation of organs at risk (OARs) from head and neck (H&N) CT images is crucial for effective H&N cancer radiotherapy. However, the existing deep learning methods are often not trained in an end-to-end fashion, i.e., they independently predetermine regions target before organ segmentation, causing limited information sharing between related tasks thus leading to suboptimal results. Furthermore, when conventional network used segment all OARs simultaneously, results favor big...
Compared to computed tomography (CT), magnetic resonance imaging (MRI) delineation of craniomaxillofacial (CMF) bony structures can avoid harmful radiation exposure. However, boundaries are blurry in MRI, and structural information needs be borrowed from CT during the training. This is challenging since paired MRI-CT data typically scarce. In this paper, we propose make full use unpaired data, which abundant, along with a single construct one-shot generative adversarial model for automated...
The O <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sup> -methylguanine-DNA methyltransferase (MGMT) promoter methylation and isocitrate dehydrogenase 1 (IDH1) mutation in high-grade gliomas (HGG) have proven to be the two important molecular indicators associated with better prognosis. Traditionally, statuses of MGMT IDH1 are obtained via surgical biopsy, which has limited their wider clinical implementation. Accurate presurgical...
Brain functional connectivity network (FCN) based on resting-state magnetic resonance imaging (rs-fMRI) has been widely used to identify neuropsychiatric disorders such as autism spectrum disorder (ASD). Most existing FCN-based methods only estimate the correlation between brain regions of interest (ROIs), without exploring more informative higher-level interactions among multiple ROIs which could be beneficial disease diagnosis. To fully explore discriminative information provided by...