A5102027990- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- MRI in cancer diagnosis
- Advanced Radiotherapy Techniques
- Head and Neck Cancer Studies
- Brain Tumor Detection and Classification
- Advanced MRI Techniques and Applications
- Lung Cancer Diagnosis and Treatment
- Lung Cancer Treatments and Mutations
- Ocular Surface and Contact Lens
- Gastric Cancer Management and Outcomes
- Atomic and Subatomic Physics Research
- Ophthalmology and Visual Impairment Studies
- Pancreatic and Hepatic Oncology Research
- Advanced X-ray and CT Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Retinal Development and Disorders
- Esophageal Cancer Research and Treatment
- Visual perception and processing mechanisms
- Corneal surgery and disorders
- Neural dynamics and brain function
Hong Kong Polytechnic University
2005-2024
St. Paul's Co-educational College
2024
Chinese University of Hong Kong
2022-2023
University of Hong Kong
2022-2023
Sun Yat-sen University
2022
Queen Mary Hospital
2022
Sun Yat-sen University Cancer Center
2022
Queen Elizabeth Hospital
2022
To investigate the role of different multi-organ omics-based prediction models for pre-treatment Adaptive Radiotherapy (ART) eligibility in patients with nasopharyngeal carcinoma (NPC).Pre-treatment contrast-enhanced computed tomographic and magnetic resonance images, radiotherapy dose contour data 135 NPC treated at Hong Kong Queen Elizabeth Hospital were retrospectively analyzed extraction multi-omics features, namely Radiomics (R), Morphology (M), Dosiomics (D), Contouromics (C), from a...
Significant lymph node shrinkage is common in patients with nasopharyngeal carcinoma (NPC) throughout radiotherapy (RT) treatment, causing ill-fitted thermoplastic masks (IfTMs). To deal this, an ad hoc adaptive (ART) may be required to ensure accurate and safe radiation delivery maintain treatment efficacy. Presently, the entire procedure for evaluating eligible ART candidate time-consuming, resource-demanding, highly inefficient. In artificial intelligence paradigm, pre-treatment...
Deep learning model has shown the feasibility of providing spatial lung perfusion information based on CT images. However, performance this method cancer patients is yet to be investigated. This study aims develop a transfer framework evaluate deep CT-to-perfusion mapping specifically patients.SPECT/CT scans 33 and 137 non-cancer were retrospectively collected from two hospitals. To adapt patients, was developed utilize features learned patients. These images processed extract...
Recently, deep learning has been demonstrated to be feasible in eliminating the use of gadoliniumbased contrast agents (GBCAs) through synthesizing gadolinium-free contrast-enhanced MRI (GFCE-MRI) from contrast-free sequences, providing community with an alternative get rid GBCAs-associated safety issues patients. Nevertheless, generalizability assessment GFCE-MRI model largely challenged by high inter-institutional heterogeneity data, on top scarcity multi-institutional data itself....
Tumor delineation plays a critical role in radiotherapy for hepatocellular carcinoma (HCC) patients. The incorporation of MRI might improve the ability to correctly identify tumor boundaries and consistency. In this study, we evaluated novel Multisource Adaptive Fusion (MAMF) method HCC patients delineation. Ten with were included study retrospectively. Contrast-enhanced T1-weighted at portal-venous phase (T1WPP), contrast-enhanced 19-min delayed (T1WDP), T2-weighted (T2W),...
This study aims to investigate the feasibility of improving prognosis stratification N staging system Nasopharyngeal Carcinoma (NPC) from quantitative spatial characterizations metastatic lymph node (LN) for NPC in a multi-institutional setting. A total 194 and 284 patients were included two local hospitals as discovery validation cohort. Spatial relationships between LN surrounding organs quantified by both distance angle histograms, followed principal component analysis. Independent...
Abstract The development of the pigmented corneal arc and a white lesion near inner margin in girl wearing overnight orthokeratology (ortho‐k) lenses for myopic control is reported. was examined before followed up every 6 months after treatment over 3‐year period. initial spherical equivalent refractive error keratometric readings (flattest/steepest meridians) were −2.37 D 45.00 D/46.75 respectively right eye −3.12 45.25 D/46.00 left eye. She ortho‐k four‐zone design made Boston XO material...
Abstract Introduction: The multifocal visual‐evoked potential (mfVEP) has been widely used in the study of diseases visual system. However, sensitivity mfVEP objective detection relative field defects not determined. This investigates variations responses while simulating by using different luminous transmission masks [neutral density (ND) filters] on stimulus pattern. Methods: Simulated with four transmissions were obtained 0.2, 0.4, 0.6, and 0.8 ND filters, 5 degrees size, at two retinal...
To evaluate the potential clinical role and effectiveness of respiratory 4D-gating F-18 FDG PET/CT scan for liver malignancies, relative to routine (3D) scan.This study presented a prospective 16 patients who received known or suspected malignant lesions. Ethics approvals were obtained from ethics committees Hong Kong Baptist Hospital The Polytechnic University. Liver lesions compared between gated ungated image sets, in terms 1) volume measurement PET image, 2) accuracy maximum standardized...
This study aims to evaluate the repeatability of radiomics and dosiomics features via image perturbation patients with cervical cancer. A total 304 cancer planning CT images dose maps were retrospectively included. Random translation, rotation, contour randomization applied before feature extraction. The was assessed using intra-class correlation coefficient (ICC). Pearson (r) adopted quantify between characteristics repeatability. In general, lower compared features, especially after...
<p>In this study, we aimed at investigating generalizability of GFCE-MRI model using data from seven institutions by manipulating heterogeneity training MRI under two popular normalization approaches. A multimodality-guided synergistic neural network (MMgSN-Net) was applied to map T1-weighted and T2-weighted contrast-enhanced (CE-MRI) for synthesis in patients with nasopharyngeal carcinoma. three were used separately generate uni-institution models jointly a tri-institution model....
<p>In this study, we aimed at investigating generalizability of GFCE-MRI model using data from seven institutions by manipulating heterogeneity training MRI under two popular normalization approaches. A multimodality-guided synergistic neural network (MMgSN-Net) was applied to map T1-weighted and T2-weighted contrast-enhanced (CE-MRI) for synthesis in patients with nasopharyngeal carcinoma. three were used separately generate uni-institution models jointly a tri-institution model....
<p>In this study, we aimed at investigating generalizability of GFCE-MRI model using data from seven institutions by manipulating heterogeneity training MRI under two popular normalization approaches. A multimodality-guided synergistic neural network (MMgSN-Net) was applied to map T1-weighted and T2-weighted contrast-enhanced (CE-MRI) for synthesis in patients with nasopharyngeal carcinoma. three were used separately generate uni-institution models jointly a tri-institution model....