A5018740222- Advanced Optical Imaging Technologies
- Augmented Reality Applications
- Surgical Simulation and Training
- Soft Robotics and Applications
- Virtual Reality Applications and Impacts
- Medical Image Segmentation Techniques
- Photoacoustic and Ultrasonic Imaging
- Robotics and Sensor-Based Localization
- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- Radiomics and Machine Learning in Medical Imaging
- Ultrasound Imaging and Elastography
- Optical Coherence Tomography Applications
- Anatomy and Medical Technology
- Advanced MRI Techniques and Applications
- Medical Imaging and Analysis
- Advanced Neural Network Applications
- AI in cancer detection
- Glioma Diagnosis and Treatment
- Photorefractive and Nonlinear Optics
- Advanced Fluorescence Microscopy Techniques
- Medical Imaging Techniques and Applications
- Dental Radiography and Imaging
- Robot Manipulation and Learning
- 3D Shape Modeling and Analysis
Tsinghua University
2016-2025
Shanghai Jiao Tong University
2024-2025
Beijing Institute of Technology
2023
University Town of Shenzhen
2019-2020
Beijing Tian Tan Hospital
2018
Capital Medical University
2018
Beijing Tsinghua Chang Gung Hospital
2017
The University of Tokyo
2008-2017
Systems Biology Institute
2017
Bunkyo University
2005-2007
Establishing correspondences between two images requires both local and global spatial context. Given putative of feature points in views, this paper, we propose Order-Aware Network, which infers the probabilities being inliers regresses relative pose encoded by essential matrix. Specifically, proposed network is built hierarchically comprises three novel operations. First, to capture context sparse correspondences, clusters unordered input learning a soft assignment These are canonical...
Computer-assisted oral and maxillofacial surgery (OMS) has been rapidly evolving since the last decade. State-of-the-art surgical navigation in OMS still suffers from bulky tracking sensors, troublesome image registration procedures, patient movement, loss of depth perception visual guidance, low accuracy. We present an augmented reality system with automatic marker-free using 3-D overlay stereo for dental surgery. A customized camera is designed to track both instrument. Image performed by...
This Roadmap article on three-dimensional integral imaging provides an overview of some the research activities in field imaging. The discusses various aspects including sensing 3D scenes, processing captured information, and display visualization information. paper consists a series 15 sections from experts presenting sensing, processing, displays, augmented reality, microscopy, object recognition, other applications. Each section represents vision its author to describe progress,...
A 3-D augmented reality navigation system using autostereoscopic images was developed for MRI-guided surgery. The are created by employing an animated image, integral videography (IV), which provides geometrically accurate spatial and reproduces motion parallax without any supplementary eyeglasses or tracking devices. spatially projected superimposed onto the surgical area viewed via a half-silvered mirror. fast image registration method intraoperative i.v. image-guided therapy. Preliminary...
This article describes a worm-like soft robot capable of operating in complicated tubular environments, such as the complex pipeline with different diameters, water, oil, and gas or clinical application natural orifice transluminal endoscopic surgery. The is completely robust, consists one multidegree freedom (DoF) extension module two clampers for locomotion steering. multi-DoF able to adjust heading direction three-dimensional space. clamper has basic expansion structure detachable sucking...
This study evaluated the use of an augmented reality navigation system that provides a markerless registration using stereo vision in oral and maxillofacial surgery.A feasibility was performed on subject, wherein camera used for tracking registration. The computed tomography data obtained from volunteer to create integral videography image 3-dimensional rapid prototype model jaw. overlay subject's anatomic site its 3D-IV were displayed real space 3D-AR display. Extraction characteristic...
Goal: Automatic segmentation of brainstem gliomas and prediction genotype (H3 K27M) mutation status based on magnetic resonance (MR) images are crucial but challenging tasks for computer-aided diagnosis in neurosurgery. In this paper, we present a novel cascaded deep convolutional neural network (CNN) to address these two simultaneously. Methods: Our task contains feature-fusion modules: the Gaussian-pyramid multiscale input features-fusion technique brainstem-region feature enhancement. The...
Objective: In this paper, we introduce an autonomous robotic ultrasound (US) imaging system based on reinforcement learning (RL). The proposed and framework are committed to controlling the US probe perform fully of a soft, moving marker-less target only single RGB images scene. Methods: We propose several different approaches methods achieve following objectives: real-time controlling, soft surface constant force tracking automatic imaging. First, express state task, representation model...
Integral videography (IV) is an animated extension of integral photography. Despite IV's many advantages, the quality its spatial images has thus far been poor; pixel pitch display and lens are considered to be main factors affecting IV image format. Our solution for increasing density use multiple projectors create a high-resolution project resultant onto small screen by using long-zoom-lens projection optics. We manufactured array device, here we present experimental results on two SXGA...
This research aimed to propose a three-dimensional (3D) augmented reality navigation method with point cloud-based image-patient registration that could merge virtual images in the real environment for dental implants using 3D image overlay and evaluate its feasibility.A total of 12 rapid prototyping mandibular models were fabricated printing divided into two groups: reality-guided group traditional two-dimensional (2D) image-guided group. A preoperative image-to-patient was introduced...
Autism spectrum disorder (ASD) is an intricate neuropsychiatric brain characterized by social deficits and repetitive behaviors. Deep learning approaches have been applied in clinical or behavioral identification of ASD; most erstwhile models are inadequate their capacity to exploit the data richness. On other hand, classification techniques often solely rely on region-based summary and/or functional connectivity analysis magnetic resonance imaging (fMRI). Besides, biomedical modeling...
Accurate ultrasound (US) image segmentation is important for disease screening, diagnosis, and prognosis assessment. However, US images typically have shadow artifacts ambiguous boundaries that affect segmentation. Recently, Segmenting Anything Model (SAM) from Meta AI has demonstrated remarkable potential in a wide range of applications. The purpose this paper was to conduct an initial evaluation the ability SAM segment images, particularly event boundaries. We evaluated SAM's performance...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Microvascular perfusion can be observed in real time with contrast-enhanced ultrasound (CEUS), which is a novel technology for visualizing the dynamic patterns of parenchymal perfusion. Automatic lesion segmentation and differential diagnosis malignant benign based on CEUS are crucial but challenging tasks computer-aided thyroid nodule....
Accurate ultrasound (US) image segmentation is crucial for the screening and diagnosis of diseases. However, it faces two significant challenges: 1) pixel-level annotation a time-consuming laborious process; 2) presence shadow artifacts leads to missing anatomy ambiguous boundaries, which negatively impact reliable results. To address these challenges, we propose novel semi-supervised aware network with boundary refinement (SABR-Net). Specifically, add imitation regions original US, design...