A5074384370- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- COVID-19 diagnosis using AI
- Advanced X-ray and CT Imaging
- Cardiac Imaging and Diagnostics
- Medical Imaging Techniques and Applications
- Osteoarthritis Treatment and Mechanisms
- Trauma Management and Diagnosis
- Artificial Intelligence in Healthcare and Education
- AI in cancer detection
- Advanced Neural Network Applications
- Hepatocellular Carcinoma Treatment and Prognosis
- MRI in cancer diagnosis
- Colorectal Cancer Screening and Detection
- Traumatic Brain Injury and Neurovascular Disturbances
- Image and Signal Denoising Methods
- Advanced Image Processing Techniques
- Coronary Interventions and Diagnostics
- Anomaly Detection Techniques and Applications
- Anatomy and Medical Technology
- Spinal Fractures and Fixation Techniques
- Ocular Surface and Contact Lens
- Pelvic and Acetabular Injuries
- Human Pose and Action Recognition
United Imaging Healthcare (China)
2019-2024
ShanghaiTech University
2021-2023
Shanghai Jiao Tong University
2003-2022
Shanghai First People's Hospital
2022
Nara Institute of Science and Technology
2020
National Institutes of Health
2016
Microsoft (United States)
2015
Siemens (Germany)
2010-2014
Siemens (United States)
2014
Rensselaer Polytechnic Institute
2008-2011
The coronavirus disease (COVID-19) is rapidly spreading all over the world, and has infected more than 1,436,000 people in 200 countries territories as of April 9, 2020. Detecting COVID-19 at early stage essential to deliver proper healthcare patients also protect uninfected population. To this end, we develop a dual-sampling attention network automatically diagnose from community acquired pneumonia (CAP) chest computed tomography (CT). In particular, propose novel online module with 3D...
The worldwide spread of coronavirus disease (COVID-19) has become a threatening risk for global public health. It is great importance to rapidly and accurately screen patients with COVID-19 from community acquired pneumonia (CAP). In this study, total 1658 1027 CAP underwent thin-section CT. All images were preprocessed obtain the segmentations both infections lung fields, which used extract location-specific features. An infection Size Aware Random Forest method (iSARF) was proposed, in...
Recently, the outbreak of Coronavirus Disease 2019 (COVID-19) has spread rapidly across world. Due to large number affected patients and heavy labor for doctors, computer-aided diagnosis with machine learning algorithm is urgently needed, could largely reduce efforts clinicians accelerate process. Chest computed tomography (CT) been recognized as an informative tool disease. In this study, we propose conduct COVID-19 a series features extracted from CT images. To fully explore multiple...
Chest computed tomography (CT) becomes an effective tool to assist the diagnosis of coronavirus disease-19 (COVID-19). Due outbreak COVID-19 worldwide, using computed-aided technique for classification based on CT images could largely alleviate burden clinicians. In this paper, we propose <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</b> daptive xmlns:xlink="http://www.w3.org/1999/xlink">F</b> eature...
Abstract Objectives To develop radiomics-based nomograms for preoperative microvascular invasion (MVI) and recurrence-free survival (RFS) prediction in patients with solitary hepatocellular carcinoma (HCC) ≤ 5 cm. Methods Between March 2012 September 2019, 356 pathologically confirmed HCC cm who underwent gadoxetate disodium–enhanced MRI were retrospectively enrolled. MVI was graded as M0, M1, or M2 according to the number distribution of invaded vessels. Radiomics features extracted from...
The automatic detection of lung nodules attached to other pulmonary structures is a useful yet challenging task in CAD systems. In this paper, we propose stratified statistical learning approach recognize whether candidate nodule detected CT images connects any three major anatomies, namely vessel, fissure and wall, or solitary with background parenchyma. First, develop fully automated voxel-by-voxel labeling/segmentation method nodule, fissure, wall parenchyma given 3D image, via unified...
Coronary artery segmentation is critical for coronary disease diagnosis but challenging due to its tortuous course with numerous small branches and inter-subject variations. Most existing studies ignore important anatomical information vascular topologies, leading less desirable performance that usually cannot satisfy clinical demands. To deal these challenges, in this paper we propose an anatomy- topology-preserving two-stage framework segmentation. The proposed consists of dependency...
BACKGROUND We aimed to develop and evaluate a deep learning-based method for fully automatic segmentation of knee joint MR imaging quantitative computation osteoarthritis (OA)-related biomarkers. MATERIAL AND METHODS This retrospective study included 843 volumes proton density-weighted fat suppression imaging. A convolutional neural network with multiclass gradient harmonized Dice loss was trained evaluated on 500 137 volumes, respectively. To assess potential morphologic biomarkers OA, the...
Background CT imaging of chronic total occlusion (CTO) is useful in guiding revascularization, but manual reconstruction and quantification are time consuming. Purpose To develop validate a deep learning (DL) model for automated CTO reconstruction. Materials Methods In this retrospective study, DL segmentation was developed using coronary angiography images from training set 6066 patients (582 with CTO, 5484 without CTO) validation 1962 (208 1754 CTO). The algorithm validated an external...
Accurate segmentation of the spinal canals in computed tomography (CT) images is an important task many related studies. In this paper, we propose automatic method and apply it to our highly challenging image cohort that acquired from multiple clinical sites CT channel PET-CT scans. To end, adapt interactive random-walk solvers be a fully cascaded pipeline. The pipeline initialized with robust voxelwise classification using Haar-like features probabilistic boosting tree. Then, topology canal...
The computer aided diagnosis (CAD) problems of detecting potentially diseased structures from medical images are typically distinguished by the following challenging characteristics: extremely unbalanced data between negative and positive classes; stringent real-time requirement online execution; multiple candidates generated for same malignant structure that highly correlated spatially close to each other. To address all these problems, we propose a novel learning formulation combine...