A5033570466- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neuroimaging Techniques and Applications
- Prostate Cancer Treatment and Research
- Neurological disorders and treatments
- Traumatic Brain Injury and Neurovascular Disturbances
- Functional Brain Connectivity Studies
- Long-Term Effects of COVID-19
- Glioma Diagnosis and Treatment
- Healthcare and Venom Research
- Pain Management and Placebo Effect
- MRI in cancer diagnosis
- Botulinum Toxin and Related Neurological Disorders
- Brain Metastases and Treatment
- Thermal Regulation in Medicine
- Intracerebral and Subarachnoid Hemorrhage Research
- Head and Neck Cancer Studies
- Medical Imaging and Analysis
- Advanced Radiotherapy Techniques
- Neural dynamics and brain function
- Pain Mechanisms and Treatments
- Traumatic Brain Injury Research
- Advanced MRI Techniques and Applications
- Cerebrospinal fluid and hydrocephalus
- Radiation Dose and Imaging
Central South University
2020-2025
Xiangya Hospital Central South University
2020-2025
Johns Hopkins Medicine
2024
Johns Hopkins University
2022-2024
Xidian University
2024
University of Virginia
2024
Columbia University
2024
Brown University
2024
Second Xiangya Hospital of Central South University
2024
Johns Hopkins Hospital
2022
Uptake segmentation and classification on PSMA PET/CT are important for automating whole-body tumor burden determinations. We developed evaluated an automated deep learning (DL)-based framework that segments classifies uptake PET/CT. identified 193 [18F] DCFPyL scans of patients with biochemically recurrent prostate cancer from two institutions, including 137 training internally testing, 56 another institution external testing. Two radiologists segmented labelled foci as suspicious or...
Background Differential diagnosis of brain metastases subtype and primary central nervous system lymphoma (PCNSL) is necessary for treatment decisions. The application machine learning facilitates the classification tumors, but prior investigations into have been limited. Purpose To develop a machine‐learning model to classify PCNSL, with lung non‐lung origin. Study Type Retrospective. Population A total 211 subjects pathologically confirmed PCNSL or (training cohort 168 testing 43). Field...
Abstract Objective . Radiation therapy for head and neck (H&N) cancer relies on accurate segmentation of the primary tumor. A robust, accurate, automated gross tumor volume method is warranted H&N therapeutic management. The purpose this study to develop a novel deep learning model based independent combined CT FDG-PET modalities. Approach In study, we developed robust learning-based leveraging information from both PET. We implemented 3D U-Net architecture with 5 levels encoding...
The purpose of this study is to identify clinical and imaging characteristics associated with post-COVID pulmonary function decline.
<h3>ABSTRACT</h3> <h3>BACKGROUND AND PURPOSE:</h3> Symptoms of normal pressure hydrocephalus (NPH) are sometimes refractory to shunt placement, with limited ability predict improvement for individual patients. We evaluated an MRI-based artificial intelligence method post-shunt NPH symptom improvement. <h3>MATERIALS METHODS:</h3> patients who underwent magnetic resonance imaging (MRI) prior placement at a single center (2014–2021) were identified. Twelve-month in modified Rankin Scale (mRS),...
The diagnostic efficiency of radiation encephalopathy (RE) remains heterogeneous, and prediction RE is difficult at the pre-symptomatic stage. We aimed to analyze whole-brain resting-state functional connectivity density (FCD) individuals with using multivariate pattern analysis (MVPA) explore its efficiency. Resting data from NPC patients nasopharyngeal carcinoma (NPC; consisting 20 subjects 26 non-RE controls) were collected in this study. used MVPA classify controls based on FCD maps....
Diabetic peripheral neuropathy (DPN) is one of the most common forms neuropathy, and its incidence has been increasing. Mounting evidence shown that patients with DPN have associated widespread alterations in structure, function connectivity brain, suggesting possible large-scale brain networks. Using structural covariance networks as well advanced graph-theory-based computational approaches, we investigated topological abnormalities for a relatively large sample ( N = 67) compared to...
Radiotherapy is the primary treatment for nasopharyngeal carcinoma, but it frequently leads to radiotherapy-induced temporal lobe injury (RTLI). Magnetic resonance imaging (MRI) main diagnostic method RTLI after radiotherapy prone missed diagnoses. This study aims investigate causes of diagnoses in carcinoma patients undergoing MRI radiotherapy.
<title>Abstract</title> Background This study aimed to develop deep learning (DL) models for lesion characterization and outcome prediction in prostate cancer (PCa) patients using Prostate-Specific Membrane Antigen (PSMA) PET/CT imaging. Methods The included 358 confirmed PCa who underwent [<sup>18</sup>F]DCFPyL Patients were divided into training internal test sets (n = 275), prospective set 64), external 19). Lesions evaluated PSMA-Reporting Data System (RADS) scores, malignancy...
Previous studies have revealed structural, functional, and metabolic changes in brain regions inside the cortico-striatal-thalamo-cortical (CSTC) loop patients with paroxysmal kinesigenic dyskinesia (PKD), whereas no quantitative susceptibility mapping (QSM)-related explored iron deposition these areas.A total of eight familial PKD 10 their healthy family members (normal controls) were recruited underwent QSM on a 3T magnetic resonance imaging system. Magnetic maps reconstructed using...
Central and peripheral nervous systems are all involved in type 2 diabetic polyneuropathy mechanisms, but such subclinical changes associations remain unknown. This study aims to explore of the central unveil their association. A total 55 type-2 diabetes patients consisting symptomatic (n = 23), 12), no 20) were enrolled this study. Cerebral morphology, function, electrophysiology, clinical information collected assessed using ANOVA post-hoc analysis. Gaussian random field correction was...
Abstract Gray matter volume and thickness reductions have been reported in patients with spinocerebellar ataxia type 3 (SCA3), whereas cortical gyrification alterations of this disease remain largely unexplored. Using local index (LGI) fractional anisotropy (FA) from structural diffusion MRI data, study investigated the as well their relationship white microstructural abnormalities SCA3 (n = 61) compared healthy controls 69). We found widespread LGI FA that changes these 2 features were also...