A5070828127- Radiomics and Machine Learning in Medical Imaging
- Metabolism, Diabetes, and Cancer
- Liver Disease Diagnosis and Treatment
- Antioxidant Activity and Oxidative Stress
- Consumer Attitudes and Food Labeling
- AI in cancer detection
- Nutritional Studies and Diet
- Hepatitis B Virus Studies
- Cancer, Lipids, and Metabolism
- Colorectal Cancer Screening and Detection
- Pancreatic and Hepatic Oncology Research
- Hepatitis C virus research
- Diabetes Treatment and Management
- Blood Pressure and Hypertension Studies
- Hepatocellular Carcinoma Treatment and Prognosis
- MRI in cancer diagnosis
- Cardiovascular Health and Disease Prevention
- Sodium Intake and Health
- Liver Disease and Transplantation
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Medical Imaging Techniques and Applications
- Organ Transplantation Techniques and Outcomes
- Testicular diseases and treatments
- Advanced Radiotherapy Techniques
- Renal Transplantation Outcomes and Treatments
Chinese University of Hong Kong
2022-2025
University of Hong Kong
2011-2025
University of Hong Kong - Shenzhen Hospital
2024
Queen Mary Hospital
2020
Northumbria University
2015-2019
Xi’an Children’s Hospital
2016
Xi'an Jiaotong University
2016
Queen Elizabeth Hospital
2007-2011
Hong Kong Polytechnic University
2011
Objective Whether varying degrees of glycaemic control impact colonic neoplasm risk in patients with diabetes mellitus (DM) remains uncertain. Design Patients newly diagnosed DM were retrieved from 2005 to 2013. Optimal at baseline was defined as mean haemoglobin A1c (HbA1c)<7%. Outcomes interest included colorectal cancer (CRC) and adenoma development. We used propensity score (PS) matching competing models estimate subdistribution HRs (SHRs). further analysed the combined effect...
Background Patients with type 2 diabetes mellitus (T2DM) have higher pancreatic cancer (PC) risk. While aspirin has chemopreventive effects on digestive cancers, its effect PC among patients T2DM is unclear. Methods This retrospective cohort study identified newly diagnosed adult in Hong Kong between 2001 and 2015 from a territory-wide healthcare registry. Exclusion criteria were history of PC, cyst, IgG4 disease, or pancreatectomy. To address reverse causality T2DM, we excluded within 1...
Background: Hepatocellular carcinoma (HCC) recurrence frequently occurs after curative surgery. Histological microvascular-invasion (MVI) predicts but cannot provide pre-operative prognostication, whereas clinical prediction scores have variable performances. Methods: Recurr-NET, a multimodal multiphasic residual-network random survival forest deep-learning model incorporating CT and parameters, was developed to predict HCC recurrence. Pre-operative triphasic scans were retrieved from...
An abstract is not available for this content. As you have access to content, full HTML content provided on page. A PDF of also in through the ‘Save PDF’ action button.
In this work, we propose a new segmentation network by integrating DenseUNet and bidirectional LSTM together with attention mechanism, termed as DA-BDense-UNet. allows learning enough diverse features enhancing the representative power of networks regulating information flow. Bidirectional is responsible to explore relationships between encoded up-sampled in encoding decoding paths. Meanwhile, introduce gates (AG) into diminish responses unrelated background regions magnify salient...
Purpose: To evaluate the radiation dose and image quality on Varian cone beam computed tomography (CBCT) system of software Version 1.4.13. This study investigated organ absorbed dose, total effective CBCT for 200 degrees head‐and‐neck 360 pelvic scanning protocols.Methods: A calibrated Farmer chamber two standard cylindrical Perspex CT dosimetry phantoms with diameter 16 cm head 32 body were used to measure weighted index (CBCTDIw) system. The different organs was measured in a female...
Background: Glycemic control in patients with diabetes mellitus (DM) has well-established health benefits, but it remains uncertain if risk of hepatocellular carcinoma (HCC) and liver-related mortality would be reduced.Methods: We identified newly-diagnosed DM from a population-wide registry, using mean hemoglobin A1c (HbA1c) measurements <7% within three-year lead-in period to define optimal glycemic control. By applying propensity score balance covariates, we analyzed variability via...