A5084862802- Radiomics and Machine Learning in Medical Imaging
- Cardiac Imaging and Diagnostics
- Advanced X-ray and CT Imaging
- Cardiovascular Disease and Adiposity
- Gastric Cancer Management and Outcomes
- Radiation Dose and Imaging
- Gastrointestinal Tumor Research and Treatment
- Medical Imaging Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Cardiovascular Function and Risk Factors
- Cardiovascular Effects of Exercise
- Gastrointestinal disorders and treatments
- Coronary Interventions and Diagnostics
- Colorectal Cancer Surgical Treatments
- Advanced MRI Techniques and Applications
- Lung Cancer Treatments and Mutations
- Venous Thromboembolism Diagnosis and Management
- Cardiac and Coronary Surgery Techniques
- Meningioma and schwannoma management
- Acute Myocardial Infarction Research
- Cardiac Valve Diseases and Treatments
- Cerebrovascular and Carotid Artery Diseases
- Bone health and osteoporosis research
- MRI in cancer diagnosis
- Dental Radiography and Imaging
Siemens Healthcare (United States)
2021-2025
Siemens (China)
2020-2025
Beijing Forestry University
2025
Ruijin Hospital
2021-2024
Shanghai Jiao Tong University
2021-2024
Siemens Healthcare (Germany)
2021-2024
Hefei University of Technology
2005
Background: Use of virtual monoenergetic images (VMIs) from multi-energy CT scans can mitigate inconsistencies in traditional attenuation measurements that result variation scan-related factors. Photon-counting detector (PCD) systems produce VMIs as standard image output under flexible scanning conditions.
Purpose: To develop a machine learning-derived radiomics approach to simultaneously discriminate epidermal growth factor receptor (EGFR), Kirsten rat sarcoma viral oncogene (KRAS), Erb-B2 tyrosine kinase 2 (ERBB2), and tumor protein 53 (TP53) genetic mutations in patients with non-small cell lung cancer (NSCLC). Methods: This study included consecutive from April 2018 June 2020 who had histologically confirmed NSCLC, underwent pre-surgical contrast-enhanced CT post-surgical next-generation...
This study aimed to evaluate the feasibility of differentiating atrial fibrillation (AF) subtype and preliminary explore prognostic value AF recurrence after ablation using radiomics models based on epicardial adipose tissue around left atrium (LA-EAT) cardiac CT images.The images 314 patients were collected wherein 251 63 cases randomly enrolled in training validation cohorts, respectively. Mutual information random forest algorithm used screen for radiomic features construct signature....
Background Traditional energy-integrating detector CT has limited utility in accurately quantifying liver fat due to protocol-induced value shifts, but this limitation can be addressed by using photon-counting (PCD) CT, which allows for a standardized value. Purpose To develop and validate universal MRI conversion formula enhance quantification accuracy across various PCD protocols relative proton density fraction (PDFF). Materials Methods In prospective study, the feasibility of was...
To establish a radiomic approach to identify epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients based on CT images, and distinguish exon-19 deletion exon-21 L858R mutation.
Identification of vulnerable plaque is essential for pre-estimation the risk cardiovascular disease (CVD) and stratification major adverse cardiac events (MACEs) risks. This study aimed to evaluate diagnostic ability coronary computed tomography angiography (CCTA)-derived qualitative quantitative features in detecting optical coherence (OCT)-defined plaques. A total 31 patients who underwent both CCTA OCT were retrospectively included this study. The results blindly analyzed on a...
Radiomics research in esophageal cancer (EC) has made considerable advancements. However, manual segmentation, which is relied upon clinical and scientific workflows, remains time-consuming inconsistent. This study aimed to develop validate a deep learning (DL) model for the automatic detection segmentation of EC lesions contrast-enhanced computed tomography (CT) images. We retrospectively collected CT data patients with confirmed by pathology from January 2017 September 2021 at three...
A new diffusion-weighted imaging (DWI) technique, known as zoomed-field-of-view echo-planar DWI (z-DWI), has been developed to reduce geometric distortions and susceptibility artifacts achieve higher spatial resolution. However, it remains unclear whether z-DWI, compared with the traditional can enhance diagnostic performance of deep-learning-based computer-aided diagnosis (DL-CAD) radiologists using DL-CAD in detecting prostate cancer (PCa). This study aims evaluate compare PI-RADS scores...
Recently, with the gradual development of machine learning technology, more and people are trying to apply technology in various fields, finance is one important fields. This work investigates optimization cryptocurrency portfolios by combining Long Short-Term Memory (LSTM) time series forecasting traditional portfolio methods. The focus paper on using historical price data from past six years Bitcoin (BTC), Ethereum (ETH), Litecoin (LTC) train LSTM models, which then used predict prices...
To clarify the fat attenuation index (FAI) change trend of peri-saphenous vein graft (SVG) and determine association between FAI disease progression based on CCTA images. Patients with venous coronary artery bypass grafts (CABGs) were consecutively enrolled in this retrospective study. In study 1, 72 patients who had undergone 3, 5 years examinations without occlusion recruited, generalized estimation equation was used to analyze peri-SVG over time. 2, 42 84 as controls propensity...
To develop and validate a dual-energy computed tomography (DECT) derived radiomics model to predict peritoneal metastasis (PM) in patients with gastric cancer (GC).This retrospective study recruited 239 GC (non-PM = 174, PM 65) histopathological confirmation for status from January 2015 December 2019. All were randomly divided into training cohort (n 160) testing 79). Standardized iodine-uptake (IU) images 120-kV-equivalent mixed (simulating conventional CT images) portal-venous delayed...
To prolong the survival, value of a computed tomography-based radiomic score (RS) in stratifying survival and guiding personalized chemotherapy strategies far-advanced gastric cancer (FGC) was investigated.This retrospective multicenter study enrolled 283 FGC patients (cT4a/bNxM0-1) from three centers. Patients one center were randomly divided into training (n = 166) internal validation 83) cohorts, whereas external cohort 34) consisted two other The RS calculated for each patient to predict...
The aim was to determine whether the dual-energy CT radiomics model derived from an iodine map (IM) has incremental diagnostic value for based on 120-kV equivalent mixed images (120 kVp) in preoperative restaging of serosal invasion with locally advanced gastric cancer (LAGC) after neoadjuvant chemotherapy (NAC). A total 155 patients (110 training cohort and 45 testing cohort) LAGC who had standard NAC before surgery were retrospectively enrolled. All analyzed by two radiologists manual...
The aim of this study was to develop and validate a radiomics model predict treatment response in patients with advanced gastric cancer (AGC) sensitive neoadjuvant therapies verify its generalization among different regimens, including chemotherapy (NAC) molecular targeted therapy. A total 373 AGC receiving were enrolled from five cohorts. Four cohorts received regimens NAC, three retrospective (training cohort internal external validation cohorts) prospective Dragon III (NCT03636893)....
The purpose is to establish and validate a machine-learning-derived radiomics approach determine the existence of atrial fibrillation (AF) by analyzing epicardial adipose tissue (EAT) in CT images.
To evaluate the performance of calcium quantification on photon-counting detector CT (PCD-CT) with high-pitch at low radiation doses compared to third-generation dual-source energy-integrating (EID-CT).