A5076001800- Genetic Associations and Epidemiology
- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Medical Imaging and Analysis
- Brain Tumor Detection and Classification
- Prostate Cancer Diagnosis and Treatment
- Colorectal Cancer Surgical Treatments
- Epigenetics and DNA Methylation
- Bioinformatics and Genomic Networks
- Tryptophan and brain disorders
- Advanced Radiotherapy Techniques
- Neurological diseases and metabolism
- Advanced Neural Network Applications
- Amyotrophic Lateral Sclerosis Research
- Ferroptosis and cancer prognosis
- 14-3-3 protein interactions
- 3D Shape Modeling and Analysis
- Obesity, Physical Activity, Diet
- Colorectal Cancer Screening and Detection
- Cancer-related gene regulation
- Genetic Neurodegenerative Diseases
- Autonomous Vehicle Technology and Safety
- Advanced X-ray and CT Imaging
- Liver Disease Diagnosis and Treatment
- Radiation Therapy and Dosimetry
University of Chinese Academy of Sciences
2022-2025
Chinese Academy of Sciences
2022-2025
Shanghai Dianji University
2024
Alzheimer's disease (AD) is the leading cause of dementia. Currently, there are no effective disease-modifying treatments for AD. Mendelian randomisation (MR) has been widely used to repurpose licensed drugs and discover novel therapeutic targets. Thus, we aimed identify targets AD analyse their pathophysiological mechanisms potential side effects.A two-sample MR integrating identified druggable genes was performed estimate causal effects blood brain expression quantitative trait loci...
Abstract Increased expression of CD33 in the brain has been suggested to be associated with increased amyloid plaque burden, while peripheral level Alzheimer’s disease (AD) patients and its role AD remain unclear. The current study aimed systematically explore bidirectional relationship between AD. Genome-wide association (GWAS) datasets (N cases : 21982; N controls 41944), blood mRNA level, plasma protein on immune-cell subtypes were obtained from GWASs conducted European population....
Genome‑wide association studies (GWASs) have revealed numerous loci associated with Parkinson's disease (PD). However, some potential causal/risk genes were still not and no etiological therapies are available. To find causal explore genetically supported drug targets for PD is urgent. By integrating the expression quantitative trait (eQTL) protein (pQTL) datasets from multiple tissues (blood, cerebrospinal fluid (CSF) brain) GWAS summary statistics, a pipeline combing Mendelian...
Large case-control genome-wide association studies (GWASs) have detected loci associated with insomnia, but how these risk confer disease remains largely unknown. By integrating brain protein quantitative trait (pQTL) (NpQTL1 = 376, NpQTL2 152) and expression QTL (eQTL) (N 452) datasets, the latest insomnia GWAS summary statistics (Ncase 109,548, NControls 277440), we conducted proteome/transcriptome-wide study (PWAS/TWAS) Mendelian randomization (MR) analysis, aiming to identify causal...
Automatic liver and tumor segmentation in contrast-enhanced magnetic resonance imaging (CE-MRI) images are of great value clinical practice as they can reduce surgeons’ workload increase the probability success surgery. However, this is still a challenging task due to complex background, irregular shape, low contrast between organ lesion. In addition, size, number, spatial location tumors vary from person person, existing automatic models unable achieve satisfactory results. work, drawing...
Schizophrenia (SCZ) is a chronic and severe mental illness with no cure so far. Mendelian randomization (MR) genetic method widely used to explore etiologies of complex traits. In the current study, we aimed identify novel proteins underlying SCZ systematic analytical approach.We integrated protein quantitative trait loci (pQTLs) brain, cerebrospinal fluid (CSF), plasma latest largest genome-wide association study (GWAS) via framework, including two-sample MR analysis, Steiger filtering...
To develop a model for predicting response to total neoadjuvant treatment (TNT) patients with locally advanced rectal cancer (LARC) based on baseline magnetic resonance imaging (MRI) and clinical data using artificial intelligence methods.
Radical prostatectomy (prostate removal) is a standard treatment for clinically localized prostate cancer and often followed by postoperative radiotherapy. Postoperative radiotherapy requires accurate delineation of the clinical target volume (CTV) lymph node drainage area (LNA) on computed tomography (CT) images. However, CTV contour cannot be determined simple expansion after resection in CT image. Constrained this factor, manual process more time-consuming challenging than radical In...
While there are established international consensuses on the delineation of pelvic lymph node regions (LNRs), significant inter- and intra-observer variabilities persist. Contouring these clinical target volumes for irradiation in malignancies is both time-consuming labor-intensive.
Abstract Background Radiotherapy has been crucial in prostate cancer treatment. However, manual segmentation is labor intensive and highly variable among radiation oncologists. In this study, a deep learning based automated contouring model constructed for clinical target volumes (CTVs) of intact postoperative cancer. Methods Computed tomography (CT) data sets 197 patients were collected. Two auto‐delineation models built radical radiotherapy respectively, each included CTVn pelvic lymph...
In this paper, we propose a deep learning-based liver tumor segmentation algorithm in enhanced multi-phase MRI images. The experimental results show that the proposed method can segment and images with smaller resource occupation, outperforms comparison method.
To achieve precise Couinaud liver segmentation in preoperative planning for hepatic surgery, accommodating the complex anatomy and significant variations, optimizing surgical approaches, reducing postoperative complications, preserving function.This research presents a novel approach to automating by identifying seven key anatomical landmarks using portal venous phase images from contrast-enhanced magnetic resonance imaging (CE-MRI). By employing multi-task learning framework, we...
Bacground and Objectibve: The delineation of the liver into Couinaud segments constitutes an essential aspect preoperative planning in hepatic surgery, given its complexity significantBacground significant anatomical variations present. Accurate segmentation underpins customization operative techniques, critically influencing minimization postoperative complications preservation functionality.Methods: This research introduces a novel approach to automating this by identifying seven key...
Abstract Background: Radiotherapy has been crucial in the treatment of prostate cancer. However, manual segmentation is labor intensive and highly variable among radiation oncologists, especially for lymph node volumes. Hence, this study, a deep learning based automated contouring model constructed with style adaptation algorithm clinical target volumes (CTVs) intact postoperative Methods: Computed tomography (CT) data sets 197 cancer patients, treated by one senior physician more than 15...
Abstract Purpose To develop a model for predicting response of Total Neoadjuvant Treatment (TNT) patients with locally advanced rectal cancer (LARC) based on baseline MRI and clinical data using artificial intelligence method. Methods Patients LARC who received TNT were enrolled retrospectively. We defined two groups to as pCR vs non-pCR (Group 1), high sensitivity moderate low 2). extracted selected radiomic features T2WI. Then we built logistic regression (LR) models deep learning (DL)...
Background: Genome-wide association studies (GWAS) have discovered numerous risk genes for amyotrophic lateral sclerosis (ALS), but how these loci confer ALS is unclear. The current study aims to identify novel causal proteins in the brain by employing an integrative analytical pipeline.Methods: Using datasets of protein quantitative trait (pQTL) (NpQTL1=376, NpQTL1=152), expression QTL (eQTL) (N=452) and largest GWAS (NALS=27205, NControls=110881), we performed a systematic pipeline...