A5053971403- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Lung Cancer Diagnosis and Treatment
- Venous Thromboembolism Diagnosis and Management
- Acute Ischemic Stroke Management
- Medical Image Segmentation Techniques
- Face and Expression Recognition
- AI in cancer detection
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Infrared Target Detection Methodologies
- Topic Modeling
- Advanced Photonic Communication Systems
- Video Surveillance and Tracking Methods
- Advanced Battery Materials and Technologies
- Acute Myocardial Infarction Research
- Trauma Management and Diagnosis
- Myasthenia Gravis and Thymoma
- Image and Object Detection Techniques
- Remote-Sensing Image Classification
- Advanced X-ray and CT Imaging
University of Chinese Academy of Sciences
2024-2025
Capital Normal University
2023-2025
Shanghai Institute of Technical Physics
2024-2025
Chinese Academy of Sciences
2009-2025
InferVision (China)
2018-2024
Shandong University
2024
Nanjing Tech University
2021-2022
Taiyuan University of Science and Technology
2012-2022
Wuhan University
2021-2022
Ocean Institute
2020
Recently, the coronavirus disease 2019 (COVID-19) has caused a pandemic in over 200 countries, influencing billions of humans. To control infection, identifying and separating infected people is most crucial step. The main diagnostic tool Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Still, sensitivity RT-PCR test not high enough to effectively prevent pandemic. chest CT scan provides valuable complementary test, it can identify patients early-stage with sensitivity....
Objective: To identify predictors of pulmonary fibrosis development by combining follow-up thin-section CT findings and clinical features in patients discharged after treatment for COVID-19.Materials Methods: This retrospective study involved 32 confirmed COVID-19 who were divided into two groups according to the evidence on their latest imaging.Clinical data imaging all different stages collected analyzed comparison.Results: The showed 14 (male, 12; female, 2) no 18 10; 8).Compared with...
Plant leaf recognition is a computer vision task used to automatically recognize plant species. It very challenging since rich morphological variations, such as sizes, textures, shapes, venation, and so on. Most existing methods typically normalize all images the same size them at one scale, resulting in unsatisfactory performances. In this letter, multiscale fusion convolutional neural network (MSF-CNN) proposed for multiple scales. First, an input image down-sampled into multiples low...
Non-invasive prediction of isocitrate dehydrogenase (IDH) genotype plays an important role in tumor glioma diagnosis and prognosis. Recently, research has shown that radiology images can be a potential tool for prediction, fusion multi-modality data by deep learning methods further provide complementary information to enhance accuracy. However, it still does not have effective architecture predict IDH with three-dimensional (3D) multimodal medical images. In this paper, we proposed novel 3D...
Objective: To evaluate the performance of a convolutional neural network (CNN) model that can automatically detect and classify rib fractures, output structured reports from computed tomography (CT) images. Materials Methods:This study included 1079 patients (median age, 55 years; men, 718) three hospitals, between January 2011 2019, who were divided into monocentric training set (n = 876; median 582), five multicenter/multiparameter validation sets 173; 59 118) with different slice...
The ABC/2 method is usually applied to evaluate intracerebral hemorrhage (ICH) volume on computed tomography (CT), although it might be inaccurate and not applicable in estimating extradural or subdural (EDH, SDH) due their irregular hematoma shapes. This study aimed deep framework optimized for the segmentation quantification of ICH, EDH, SDH.The training datasets were 3,000 images retrospectively collected from a collaborating hospital (Hospital A) segmented by Dense U-Net framework. Three...
Although the thermal infrared remote sensing camera plays a pivotal role in Earth observation, and impacts target detection, surface temperature inversion, subsequent space missions significantly, imaging quality of is constrained by its optics, image sensors, electronics during on-orbit operation. At same time, traditional blind recovery algorithms, which require extensive time for estimating intricate blur kernels, encounter challenges due to varying atmospheric conditions other factors...
To develop and validate a general radiomics nomogram capable of identifying EGFR mutation status in non-small cell lung cancer (NSCLC) patients, regardless patient with either contrast-enhanced CT (CE-CT) or non-contrast-enhanced (NE-CT).A total 412 NSCLC patients were retrospectively enrolled this study. Patients' features not significantly different between NE-CT CE-CT defined as features, further used to construct the signature. Fivefold cross-validation was select best machine learning...
Background: Cerebral venous thrombosis (CVT) is a rare cerebrovascular disease. Routine brain magnetic resonance imaging commonly used to diagnose CVT. This study aimed develop and evaluate novel deep learning (DL) algorithm for detecting CVT using routine imaging. Methods: imaging, including T1-weighted, T2-weighted, fluid-attenuated inversion recovery images of patients suspected from April 2014 through December 2019 who were enrolled registry, collected. The divided into 2 data sets:...
The occurrence of hand, foot, and mouth disease (HFMD) is closely related to meteorological factors. However, location-specific characteristics, such as persistent air pollution, may increase the complexity impact factors on HFMD, studies across different areas populations are largely lacking. In this study, a two-stage multisite time-series analysis was conducted using data from 16 cities in Shandong Province 2015 2019. first stage, we obtained cumulative exposure–response curves number...
In order to simulate the complex aerodynamic heating environment in local interference zone of an aircraft, this paper establishes a sophisticated experimental simulation technology for based on arc flat plate free jet test technology. A water-cooled device is installed locally model, leaving certain gap between and therefore strip-shaped flow thermal established. Experimental research has found that diagonal shock wave formed near block, heat flux inside relatively large, similar results...
Respiratory muscle dysfunction in patients with idiopathic pulmonary fibrosis (IPF) is a big challenge for treatment and rehabilitation. To quantitatively assess diaphragm chest wall using dynamic Magnetic Resonance Imaging (Dyn-MRI) IPF. Ninety-six IPF 50 gender- age-matched controls were prospectively included underwent D-MRI fast spoiled gradient-recalled echo sequence. muscles function assessed thoracic anterior-posterior (AP), left-right (LR), cranial-caudal (CC) metrics. Moreover, lung...
Existing infrared small target detection methods often fail due to limited exploitation of spatiotemporal information, leading missed detections and false alarms. To address these limitations, we propose a novel framework called Spatial–Temporal Fusion Detection (STFD), which synergistically integrates three original components: gradient-enhanced spatial contrast, adaptive temporal intensity accumulation, regional contrast. In the domain, introduce Temporal Regional Contrast (TRC), first...