A5112049384- Neural dynamics and brain function
- Photoreceptor and optogenetics research
- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Functional Brain Connectivity Studies
- Radiomics and Machine Learning in Medical Imaging
- Advanced Fluorescence Microscopy Techniques
- Cardiac Imaging and Diagnostics
- Advanced Image Processing Techniques
- Geological Modeling and Analysis
- Neuroscience and Neuropharmacology Research
- Medical Image Segmentation Techniques
- Energy, Environment, Economic Growth
- Photoacoustic and Ultrasonic Imaging
- Neuroscience and Neural Engineering
- Advanced Neuroimaging Techniques and Applications
- Radiation Dose and Imaging
- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- MRI in cancer diagnosis
- Energy and Environment Impacts
- Artificial Intelligence in Healthcare and Education
- EEG and Brain-Computer Interfaces
- Radiology practices and education
- Energy, Environment, and Transportation Policies
Stanford University
2013-2025
VIS Systems (Poland)
2018
University of California, Los Angeles
2013-2015
Xiamen University
2015
To develop a super-resolution technique using convolutional neural networks for generating thin-slice knee MR images from thicker input slices, and compare this method with alternative through-plane interpolation methods.We implemented 3D network entitled DeepResolve to learn residual-based transformations between high-resolution lower-resolution thick-slice at the same center locations. was trained 124 double echo in steady-state (DESS) data sets 0.7-mm slice thickness tested on 17...
Over 85 million computed tomography (CT) scans are performed annually in the US, of which approximately one quarter focus on abdomen. Given current shortage both general and specialized radiologists, there is a large impetus to use artificial intelligence alleviate burden interpreting these complex imaging studies while simultaneously using images extract novel physiological insights. Prior state-of-the-art approaches for automated medical image interpretation leverage vision language models...
Central thalamus plays a critical role in forebrain arousal and organized behavior. However, network-level mechanisms that link its activity to brain state remain enigmatic. Here, we combined optogenetics, fMRI, electrophysiology, video-EEG monitoring characterize the central thalamus-driven global networks responsible for switching state. 40 100 Hz stimulations of caused widespread activation forebrain, including frontal cortex, sensorimotor striatum, transitioned asleep rats. In contrast,...
Background Super‐resolution is an emerging method for enhancing MRI resolution; however, its impact on image quality still unknown. Purpose To evaluate super‐resolution using quantitative and qualitative metrics of cartilage morphometry, osteophyte detection, global blurring. Study Type Retrospective. Population In all, 176 studies subjects at varying stages osteoarthritis. Field Strength/Sequence Original‐resolution 3D double‐echo steady‐state (DESS) DESS with 3× thicker slices...
Potential approaches for abbreviated knee MRI, including prospective acceleration with deep learning, have achieved limited clinical implementation.
A fine-tuned, open-source large language model (Mistral-7B; Mistral AI) effectively extracted clinical history elements from imaging orders with substantial agreement radiologists and rivaled a closed-source (GPT-4 Turbo; OpenAI).
To propose a novel compressed sensing (CS) high spatial resolution functional MRI (fMRI) method and demonstrate the advantages limitations of using CS for fMRI.A randomly undersampled variable density spiral trajectory enabling an acceleration factor 5.3 was designed with balanced steady state free precession sequence to achieve data acquisition. A modified k-t SPARSE then implemented applied strategy optimize regularization parameters consistent, quality reconstruction.The proposed improves...
The investigation of the functional connectivity precise neural circuits across entire intact brain can be achieved through optogenetic magnetic resonance imaging (ofMRI), which is a novel technique that combines relatively high spatial resolution high-field fMRI with precision stimulation. Fiber optics enable delivery specific wavelengths light deep into in vivo are implanted regions interest order to specifically stimulate targeted cell types have been genetically induced express...
The investigation of the functional connectivity precise neural circuits across entire intact brain can be achieved through optogenetic magnetic resonance imaging (ofMRI), which is a novel technique that combines relatively high spatial resolution high-field fMRI with precision stimulation. Fiber optics enable delivery specific wavelengths light deep into in vivo are implanted regions interest order to specifically stimulate targeted cell types have been genetically induced express...
Over 85 million computed tomography (CT) scans are performed annually in the US, of which approximately one quarter focus on abdomen. Given current radiologist shortage, there is a large impetus to use artificial intelligence alleviate burden interpreting these complex imaging studies. Prior state-of-the-art approaches for automated medical image interpretation leverage vision language models (VLMs). However, VLMs generally limited 2D images and short reports, do not electronic health record...
Deep-learning (DL) can be used to extend compressed sensing (CS) learn the regularization function in a data-driven manner. In contrast, super resolution (SR) algorithms have been transform rapidly-acquired low-resolution images into higher-resolution images. This work compares DL-CS with DL-SR for accelerated MRI on test dataset of 50 patients conventional image quality metrics and clinically-relevant quantitative T 2 relaxation measurements. We demonstrate that DLCS approaches outperform DLSR MRI.
Obtaining magnetic resonance images (MRI) with high resolution and generating quantitative image-based biomarkers for assessing tissue biochemistry is crucial in clinical research applications. How- ever, acquiring requires signal-to-noise ratio (SNR), which at odds high-resolution MRI, especially a single rapid sequence. In this paper, we demonstrate how super-resolution can be utilized to maintain adequate SNR accurate quantification of the T2 relaxation time biomarker, while...