A5101838988- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Head and Neck Cancer Studies
- COVID-19 Clinical Research Studies
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Ocular Oncology and Treatments
- Human Pose and Action Recognition
- Congenital Heart Disease Studies
- Aortic Disease and Treatment Approaches
- Advanced Neural Network Applications
- 3D Shape Modeling and Analysis
- Thyroid Cancer Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- Cardiac Imaging and Diagnostics
- Brain Metastases and Treatment
- Bone health and osteoporosis research
- Natural Language Processing Techniques
- Respiratory Support and Mechanisms
- Aortic aneurysm repair treatments
- Cardiac Valve Diseases and Treatments
- Pancreatic and Hepatic Oncology Research
- Multimodal Machine Learning Applications
- Advanced MRI Techniques and Applications
- Coronary Artery Anomalies
First Affiliated Hospital of Jinan University
2025
Jilin Medical University
2025
Jilin University
2025
Guangdong Provincial People's Hospital
2019-2023
Guangdong Academy of Medical Sciences
2016-2023
Southern Medical University
2016-2023
Tsinghua University
2023
Guangdong General Hospital
2016-2020
Shantou University
2016-2019
Shantou University Medical College
2016-2019
Purpose: To identify MRI-based radiomics as prognostic factors in patients with advanced nasopharyngeal carcinoma (NPC).Experimental Design: One-hundred and eighteen (training cohort: n = 88; validation 30) NPC were enrolled. A total of 970 features extracted from T2-weighted (T2-w) contrast-enhanced T1-weighted (CET1-w) MRI. Least absolute shrinkage selection operator (LASSO) regression was applied to select for progression-free survival (PFS) nomograms. Nomogram discrimination calibration...
Background: Ultrasound (US) examination is helpful in the differential diagnosis of thyroid nodules (malignant vs. benign), but its accuracy relies heavily on examiner experience. Therefore, aim this study was to develop a less subjective diagnostic model aided by machine learning. Methods: A total 2064 (2032 patients, 695 male; Mage = 45.25 ± 13.49 years) met all following inclusion criteria: (i) hemi- or thyroidectomy, (ii) maximum nodule diameter 2.5 cm, (iii) conventional US and...
We aimed to identify a magnetic resonance imaging (MRI)-based model for assessment of the risk individual distant metastasis (DM) before initial treatment nasopharyngeal carcinoma (NPC).This retrospective cohort analysis included 176 patients with NPC. Using PyRadiomics platform, we extracted features primary tumors in all who did not exhibit DM treatment. Subsequently, used minimum redundancy-maximum relevance and least absolute shrinkage selection operator algorithms select strongest build...
Abstract Gliomas can be classified into five molecular groups based on the status of IDH mutation, 1p/19q codeletion, and TERT promoter whereas they need to obtained by biopsy or surgery. Thus, we aimed use MRI-based radiomics noninvasively predict assess their prognostic value. We retrospectively identified 357 patients with gliomas extracted radiomic features from preoperative MRI images. Single-layered signatures were generated using a single MR sequence Bayesian-regularization neural...
We aimed to investigate the potential of radiomic features magnetic resonance imaging (MRI) predict progression in patients with advanced nasopharyngeal carcinoma (NPC). One hundred and thirteen consecutive (01/2007-07/2013) (training cohort: n = 80; validation 33) NPC were enrolled. A total 970 initial extracted from T2-weighted (T2-w) (n 485) contrast-enhanced T1-weighted (CET1-w) MRI for each patient. used least absolute shrinkage selection operator (Lasso) method select that most...
Early radiation-induced temporal lobe injury (RTLI) diagnosis in nasopharyngeal carcinoma (NPC) is clinically challenging, and prediction models of RTLI are lacking. Hence, we aimed to develop radiomic for early detection RTLI.We retrospectively included a total 242 NPC patients who underwent regular follow-up magnetic resonance imaging (MRI) examinations, including contrast-enhanced T1-weighted T2-weighted imaging. For each MRI sequence, four non-texture 10,320 texture features were...
Background: To develop and validate a radiomic nomogram incorporating features with clinical variables for individual local recurrence risk assessment in nasopharyngeal carcinoma (NPC) patients before initial treatment. Methods: One hundred forty were randomly divided into training cohort (n = 80) validation 60). A total of 970 extracted from pretreatment magnetic resonance (MR) images NPC May 2007 to December 2013. Univariate multivariate analyses used selecting associated recurrence, was...
There is no consensus on specific prognostic biomarkers potentially improving survival of nasopharyngeal carcinoma (NPC), especially in advanced-stage disease. The value MRI-based radiomics signature unclear. A total 970 quantitative features were extracted from the tumor 100 untreated NPC patients (stage III-IVb) (discovery set: n = 70, validation 30). We then applied least absolute shrinkage and selection operator (lasso) regression to select that most associated with progression-free...
Type-B Aortic Dissection (TBAD) is one of the most serious cardiovascular events characterized by a growing yearly incidence, and severity disease prognosis. Currently, computed tomography angiography (CTA) has been widely adopted for diagnosis prognosis TBAD. Accurate segmentation true lumen (TL), false (FL), thrombus (FLT) in CTA are crucial precise quantification anatomical features. However, existing works only focus on TL FL without considering FLT. In this paper, we propose ImageTBAD,...
Recent work on 4D point cloud sequences has attracted a lot of attention. However, obtaining exhaustively labeled datasets is often very expensive and laborious, so it especially important to investigate how utilize raw unlabeled data. most existing self-supervised representation learning methods only consider geometry from static snapshot omitting the fact that sequential observations dynamic scenes could reveal more comprehensive geometric details. To overcome such issues, this paper...
Some epidemiologic surveillance studies have recorded adverse drug reactions to radiocontrast agents. We aimed investigate the incidence and management of acute (AARs) Ultravist-370 Isovue-370 in patients who underwent contrast-enhanced computed tomography (CT) scanning.Data from 137,473 were analyzed. They had undergone enhanced CT scanning with intravenous injection or during period January 1, 2006 December 31, 2012 our hospital. investigated classified AARs according American College...