A5053996727- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- Head and Neck Cancer Studies
- Gastric Cancer Management and Outcomes
- Lung Cancer Treatments and Mutations
- Colorectal Cancer Surgical Treatments
- Glioma Diagnosis and Treatment
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- Lung Cancer Research Studies
- Thyroid Cancer Diagnosis and Treatment
- Helicobacter pylori-related gastroenterology studies
- Salivary Gland Tumors Diagnosis and Treatment
- Cancer Immunotherapy and Biomarkers
- Colorectal Cancer Treatments and Studies
- Cell Image Analysis Techniques
- Hepatocellular Carcinoma Treatment and Prognosis
- EEG and Brain-Computer Interfaces
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Advanced Memory and Neural Computing
- Breast Cancer Treatment Studies
- Advanced Neuroimaging Techniques and Applications
- Colorectal and Anal Carcinomas
- Neuroscience and Neural Engineering
- Gynecological conditions and treatments
Fudan University
2025
First Affiliated Hospital of Jinan University
2020-2024
Nantong University
2024
Jinan University
2021-2024
Donghua University
2024
Sichuan Cancer Hospital
2024
University of Electronic Science and Technology of China
2024
China Medical University
2024
First Hospital of China Medical University
2024
Hebei Medical University
2023
Artificial intelligence (AI) has unparalleled potential to unlock useful information from real-world data innovate trial design. Here, we discuss how AI can be used optimize clinical design and potentially boost the success rate of trials. Zhang et al. artificial leverage valuable insights for innovative
Abstract Tumour recurrence and drug resistance in hepatocellular carcinoma remain challenging. Cancer stem cells (CSCs) are responsible for tumour initiation because of their stemness characteristics. CSCs accounting relapse promising therapeutic targets. We report that Abelson interactor 2 (ABI2) is a novel target HCC CSCs. First, ABI2 was upregulated tissues compared with liver associated size, pathological grade, cirrhosis, worse prognosis high rate. Functional studies illustrate...
Annexin A3 has been demonstrated to be a key pathogenic protein in the occurrence and development of triple-negative breast cancer (TNBC); its overexpression TNBC cells can promote proliferation, migration, drug resistance TNBC. Previously, we reported first ANXA3 degrader, (R)-SL18, with potent anti-TNBC effects, albeit moderate binding affinity leading off-target effects relatively poor degradation selectivity family proteins. To obtain molecules stronger lower toxicity, performed further...
Background Distant metastasis is the primary cause of treatment failure in locoregionally advanced nasopharyngeal carcinoma (LANPC). Purpose To develop a model to evaluate distant metastasis‐free survival (DMFS) LANPC and explore value additional chemotherapy concurrent chemoradiotherapy (CCRT) for different risk groups. Study Type Retrospective. Population In all, 233 patients with biopsy‐confirmed (NPC) from two hospitals. Field Strength 1.5T 3T. Sequence Axial T 2 ‐weighted (T ‐w)...
Transcatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with same tumor stage. Accurate prediction TACE response remains a major concern to avoid overtreatment. Thus, we aimed develop and validate an artificial intelligence system real-time automatic in HCC based on digital subtraction angiography (DSA) videos via deep learning approach.This retrospective cohort study included...
Hyperprogressive disease (HPD) is a new progressive pattern in patients with advanced hepatocellular carcinoma (HCC) treated programmed cell death 1 (PD-1) inhibitors. We aimed to investigate risk factors associated HPD HCC undergoing anti-PD-1 therapy.A total of 69 therapy between March 2017 and January 2020 were included. was determined according the time treatment failure, tumour growth rate, rate ratio. Univariate multivariate analyses performed identify clinical variables significantly...
Ivo is a bispecific antibody with cooperative binding to enhance affinity PD-1 and VEGF, as yet undefined in IC activity. This analysis assesses activity of ivo pts BMs at baseline (BL) who received +/- PC first line systemic therapy for aNSCLC. Pts aNSCLC any histology, no prior cancer, performance status 0-1 were eligible combined or alone on the AK112-201 AK112-202 trials, respectively, enrolled from 2 centers China. was continued up 4 cycles AK112-201, while until progressing disease...
To assess whether apparent diffusion coefficient (ADC) metrics can be used to tumor-infiltrating lymphocyte (TIL) levels in breast cancer, particularly the molecular subtypes of cancer.In total, 114 patients with cancer met inclusion criteria (mean age: 52 years; range: 29-85 years) and underwent multi-parametric magnetic resonance imaging (MRI). The were imaged by diffusion-weighted (DW)-MRI (1.5 T) using a single-shot spin-echo echo-planar sequence. Two readers independently drew region...
Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well prognosis (primary task) gliomas. Further, provide the mechanisms underlying model's predictions. We collected multiscale data...
This study investigated the mechanism of extracellular matrix-mimicking hydrogel-mediated TGFB1/Nrf2 signaling pathway in osteoarthritis using bone marrow mesenchymal stem cell-derived exosomes (BMSCs-Exos). A GMOCS-Exos hydrogel was synthesized and evaluated for its impact on chondrocyte viability neutrophil traps (NETs) formation. In an OA rat model, promoted cartilage regeneration inhibited NETs Transcriptome sequencing identified TGFB1 as a key gene, with activating Nrf2 through TGFB1....
Current risk stratification systems for thyroid nodules suffer from low specificity and high biopsy rates. Recently, machine learning (ML) is introduced to assist nodule diagnosis but lacks interpretability. Here, we developed validated ML models on 3965 nodules, as compared the American College of Radiology Thyroid Imaging, Reporting Data System (ACR TI-RADS). Subsequently, a SHapley Additive exPlanation (SHAP) algorithm was leveraged interpret results best-performing model. Clinical...
Abstract Background To develop and validate an MRI texture-based machine learning model for the noninvasive assessment of renal function. Methods A retrospective study 174 diabetic patients (training cohort, n = 123; validation 51) who underwent scans was included. They were assigned to normal function ( 71), mild or moderate impairment 69), severe groups 34) according Four methods kidney segmentation on T2-weighted images (T2WI) compared, including regions interest covering all coronal...
<title>Abstract</title> Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well prognosis (primary task) gliomas. Further, provide the mechanisms underlying model's predictions. We...
Objective To investigate the efficacy of all- trans retinoic acid (ATRA) in human gastric dysplasia. Methods In this double-blind study, patients with precancerous dysplasia or without intestinal metaplasia (IM) received either conventional treatment consisting omeprazole and sucralfate (control group) plus ATRA. Gastric mucosal biopsies were performed before after drug analysed histologically; expression retinoblastoma (Rb) protein HER2 mucosa measured using immunohistochemistry. Results A...