A5004173270- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Augmented Reality Applications
- Sparse and Compressive Sensing Techniques
- Retinal Imaging and Analysis
- International Student and Expatriate Challenges
- Facial Trauma and Fracture Management
- Robotics and Sensor-Based Localization
- Glaucoma and retinal disorders
- Optical Coherence Tomography Applications
- Palliative Care and End-of-Life Issues
- Management and Organizational Studies
- Patient-Provider Communication in Healthcare
- Virtual Reality Applications and Impacts
- Health Literacy and Information Accessibility
- Retinal and Optic Conditions
- Knowledge Management and Sharing
- Photoacoustic and Ultrasonic Imaging
- Ocular Disorders and Treatments
- DNA and Biological Computing
Johns Hopkins University
2020-2024
University of Florida
2015-2016
In magnetic resonance (MR) imaging, a lack of standardization in acquisition often causes pulse sequence-based contrast variations MR images from site to site, which impedes consistent measurements automatic analyses. this paper, we propose an unsupervised image harmonization approach, CALAMITI (Contrast Anatomy Learning and Analysis for Intensity Translation Integration), aims alleviate multi-site imaging. Designed using information bottleneck theory, learns globally disentangled latent...
The lack of standardization and consistency acquisition is a prominent issue in magnetic resonance (MR) imaging. This often causes undesired contrast variations the acquired images due to differences hardware parameters. In recent years, image synthesis-based MR harmonization with disentanglement has been proposed compensate for variations. general idea disentangle anatomy information from achieve cross-site harmonization. Despite success existing methods, we argue that major improvements...
Optical coherence tomography angiography (OCTA) is an imaging modality that can be used for analyzing retinal vasculature. Quantitative assessment of en face OCTA images requires accurate segmentation the capillaries. Using deep learning approaches this task faces two major challenges. First, acquiring sufficient manual delineations training take hundreds hours. Second, suffer from numerous contrast-related artifacts are currently inherent to and vary dramatically across scanners. We propose...
Abstract Producing spatial transformations that are diffeomorphic is a key goal in deformable image registration. As transformation should have positive Jacobian determinant $$\vert J\vert $$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mo>|</mml:mo> <mml:mi>J</mml:mi> </mml:mrow> </mml:math> everywhere, the number of pixels (2D) or voxels (3D) with <0$$ <mml:mo><</mml:mo> <mml:mn>0</mml:mn> has been used to test for diffeomorphism and also measure...
The orbital floor is a thin boney plate that supports the eye and its muscles. When sufficiently large, fracture of leads to malposition or entrapment eye, necessitating surgical reconstruction. To reconstruct floor, surgeon must retract eyeball dissect deeply through small incision in order safely place synthetic beneath thus replacing fractured bone. Conventionally, accuracy implant placement relies on surgeon's expertise. Intraoperative imaging navigation are rarely used due their cost...
In view of the current situation information expression in passive two-dimensional display space, from perspective improving users' willingness to use Augmented Reality technology is integrated with virtual space containing rich information, supplemented by Machine Learning construct an immersive environment interactive function. Under development Unity3D, Vuforia, ARCore and Arm NN are adopted integrate markers, applications functions image recognition, plane object recognition command...
Augmented Reality could realize the integration of virtuality and reality bring users an enhanced information space feeling. In this context, design interactive application based on mobile terminal is described. Under integrated development environment Unity3D, ARFoundation TensorFlowSharp are adopted to integrate virtual with markers, functions command interaction, plane recognition, image recognition object implemented. The scheme introduced, realization processes discussed in detail. test...