A5013607405- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced Radiotherapy Techniques
- Advanced X-ray and CT Imaging
- Medical Image Segmentation Techniques
- AI in cancer detection
- MRI in cancer diagnosis
- Medical Imaging and Analysis
- Radiation Dose and Imaging
- Renal cell carcinoma treatment
- Digital Radiography and Breast Imaging
- Gene expression and cancer classification
- Brain Tumor Detection and Classification
- Lung Cancer Diagnosis and Treatment
- Glioma Diagnosis and Treatment
- Machine Learning and Data Classification
- Reproductive Biology and Fertility
- Hepatocellular Carcinoma Treatment and Prognosis
- Blood disorders and treatments
- Evolutionary Algorithms and Applications
- Seed Germination and Physiology
- Plant-based Medicinal Research
- Imbalanced Data Classification Techniques
- Iron Metabolism and Disorders
- Radiation Therapy and Dosimetry
Southern Medical University
2016-2025
United Imaging Healthcare (China)
2025
Dali University
2025
Vanderbilt University Medical Center
2024
Fuzhou University
2024
Third Affiliated Hospital of Sun Yat-sen University
2022-2024
Sun Yat-sen University
2022-2024
Guangdong Academy of Medical Sciences
2024
Guangdong Provincial People's Hospital
2024
Changchun University of Technology
2023-2024
Chronic kidney disease (CKD) patients have an increased risk of cardiovascular diseases (CVDs). The present study aimed to investigate the gut microbiota and blood trimethylamine-N-oxide concentration (TMAO) in Chinese CKD explore underlying explanations through animal experiment. median plasma TMAO level was 30.33 μmol/L patients, which significantly higher than 2.08 measured healthy controls. Next-generation sequence revealed obvious dysbiosis microbiome with reduced bacterial diversity...
Better understanding of the dose-toxicity relationship is critical for safe dose escalation to improve local control in late-stage cervical cancer radiotherapy. In this study, we introduced a convolutional neural network (CNN) model analyze rectum distribution and predict toxicity. Forty-two patients treated with combined external beam radiotherapy (EBRT) brachytherapy (BT) were retrospectively collected, including twelve toxicity thirty non-toxicity patients. We adopted transfer learning...
Ovarian cancer is the most lethal gynecological malignancy. Timely diagnosis of ovarian difficult due to lack effective biomarkers. Laboratory tests are widely applied in clinical practice, and some have shown diagnostic prognostic relevance cancer. We aimed systematically evaluate value routine laboratory on prediction cancer, develop a robust generalisable ensemble artificial intelligence (AI) model assist identifying patients with
Accurate and automatic brain metastases target delineation is a key step for efficient effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed deep learning convolutional neural network (CNN) algorithm segmenting on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based into an segmentation workflow validated both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data clinical patients' data. Validation...
Breast cancer is one of the most common malignant tumors in women and a serious threat to women's health. The pentose phosphate pathway (PPP) mode oxidative breakdown glucose that can be divided into (oxPPP) non-oxidative (non-oxPPP) stages necessary for cell body survival. However, abnormal activation PPP often leads proliferation, migration, invasion, chemotherapy resistance breast cancer. Glucose-6-phosphate dehydrogenase (G6PD) rate-limiting enzyme oxidation. Nicotinamide adenine...
Computed tomography (CT) to cone-beam CT (CBCT) deformable image registration (DIR) is a crucial step in adaptive radiation therapy. Current intensity-based algorithms, such as demons, may fail the context of CT–CBCT DIR because inconsistent intensities between two modalities. In this paper, we propose variant called deformation with intensity simultaneously corrected (DISC), deal DIR. DISC distinguishes itself from original demons algorithm by performing an correction on CBCT at every...
The non-perturbative ab initio calculations of infinite nuclear matter using In-Medium Similarity Renormalization Group (IMSRG) method is developed in this work, which enables with chiral two and three-nucleon forces at N$^2$LO N$^3$LO. Results from the many-body perturbation theory different orders coupled-cluster are also presented for comparison. It shown that approaches lead to divergences a harder interaction pure neutron matter. For symmetric matter, such would appear even soft...
To evaluate the performance of a multi-constraint representation learning classification model for identifying ovarian cancer with missing laboratory indicators. Tabular data indicators were collected from 393 patients and 1951 control patients. The indicator features projected to latent space obtain using representational based on discriminative mutual information coupled feature projection significance score consistency location estimation. proposed constraint term was ablated...
Objective: For patients with AIDS-related lymphoma (ARL), optimizing risk stratification is crucial to creating customized therapy regimens and enhancing their prognosis. This study aims develop a more precisely predicted prognostic model for ARL patients. Design: A 7-year retrospective cohort (2016–2023) of 136 at single institution randomly allocated training (n = 109) validation 27) cohorts. Methods: We assessed the relationship between HIV, lymphoma, patient-specific factors overall...
Deformable image registration (DIR) is a critical technic in adaptive radiotherapy (ART) for propagating contours between planning computerized tomography (CT) images and treatment CT/cone-beam CT (CBCT) to account organ deformation re-planning. To validate the ability accuracy of DIR algorithms at risk (OAR) contour mapping, ten intensity-based strategies, which were classified into four categories-optical flow-based, demons-based, level-set-based spline-based-were tested on fractional CBCT...
Deep learning has recently been extensively investigated to remove artifacts in low-dose computed tomography (LDCT). However, the power of transfer for medical image denoising tasks not fully explored. In this work, we proposed a residual convolutional neural network (TLR-CNN) restore LDCT images at single and blind noise levels. A was implemented effectively estimate difference between denoised its original map, noise-free obtained by subtracting map from image. The results were compared...
Adaptive radiation therapy (ART) can reduce normal tissue toxicity and/or improve tumor control through treatment adaptations based on the current patient anatomy. Developing an efficient and effective re-planning algorithm is important step toward clinical realization of ART. For process, manual trial-and-error approach to fine-tune planning parameters time-consuming usually considered unpractical, especially for online It desirable automate this yield a plan acceptable quality with minimal...
Purpose: 4D cone beam CT (4D-CBCT) has been utilized in radiation therapy to provide image guidance lung and upper abdomen area. However, clinical application of 4D-CBCT is currently limited due the long scan time low quality. The purpose this paper develop a new reconstruction method that restores volumetric images based on 1-min data acquired with standard 3D-CBCT protocol. Methods: model optimizes deformation vector field deforms patient-specific planning (p-CT), so calculated projections...