A5089461674- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Surgical Treatments
- Gastric Cancer Management and Outcomes
- Organ Transplantation Techniques and Outcomes
- Liver Disease and Transplantation
- Liver Disease Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Colorectal and Anal Carcinomas
- Colorectal Cancer Screening and Detection
- Hepatocellular Carcinoma Treatment and Prognosis
- Transplantation: Methods and Outcomes
- MRI in cancer diagnosis
- Financial Risk and Volatility Modeling
- Medical Imaging Techniques and Applications
- Gastrointestinal Tumor Research and Treatment
- Colorectal Cancer Treatments and Studies
- Forecasting Techniques and Applications
- Cancer Research and Treatments
- Medical Imaging and Analysis
- Cancer Immunotherapy and Biomarkers
- Nanoplatforms for cancer theranostics
- Immune cells in cancer
- Monetary Policy and Economic Impact
- Esophageal Cancer Research and Treatment
- Inflammatory Bowel Disease
Sun Yat-sen University
2015-2025
Sixth Affiliated Hospital of Sun Yat-sen University
2017-2025
Air Force Medical University
2024
Southern Medical University
2024
RWTH Aachen University
2023
University of Sussex
2020-2022
Key Laboratory of Guangdong Province
2020
Second Affiliated Hospital of Guangzhou Medical University
2018
Guangzhou Medical University
2018
Fifth Affiliated Hospital of Sun Yat-sen University
2018
BackgroundAccurate prediction of tumour response to neoadjuvant chemoradiotherapy enables personalised perioperative therapy for locally advanced rectal cancer. We aimed develop and validate an artificial intelligence radiopathomics integrated model predict pathological complete in patients with cancer using pretreatment MRI haematoxylin eosin (H&E)-stained biopsy slides.MethodsIn this multicentre observational study, eligible participants who had undergone followed by radical surgery were...
Accurate prediction of treatment response to neoadjuvant chemotherapy (NACT) in individual patients with locally advanced gastric cancer (LAGC) is essential for personalized medicine. We aimed develop and validate a deep learning radiomics nomogram (DLRN) based on pretreatment contrast-enhanced computed tomography (CT) images clinical features predict the NACT LAGC.719 LAGC were retrospectively recruited from four Chinese hospitals between Dec 1st, 2014 Nov 30th, 2020. The training cohort...
Background Deep learning (DL) models can potentially improve prognostication of rectal cancer but have not been systematically assessed. Purpose To develop and validate an MRI DL model for predicting survival in patients with based on segmented tumor volumes from pretreatment T2-weighted scans. Materials Methods were trained validated retrospectively collected scans diagnosed between August 2003 April 2021 at two centers. Patients excluded the study if there concurrent malignant neoplasms,...
To determine the safety and efficacy of transarterial chemoembolization (TACE) combined with sorafenib (hereafter, TACE-sorafenib) in patients hepatocellular carcinoma (HCC) portal vein tumor thrombus (PVTT).This study was approved by institutional review board, requirement for informed consent waived. The medical records consecutive HCC PVTT who underwent TACE-sorafenib or TACE alone from January 2010 to December 2012 were retrospectively evaluated. Sorafenib (400 mg) administered twice...
Abstract Distant metastasis (DM) is the main cause of treatment failure in locally advanced rectal cancer. Adjuvant chemotherapy usually used for distant control. However, not all patients can benefit from adjuvant chemotherapy, and particularly, some may even get worse outcomes after treatment. We develop validate an MRI-based radiomic signature (RS) prediction DM within a multicenter dataset. The RS proved to be independent prognostic factor as it only demonstrates good accuracy...
Accurate predictions of distant metastasis (DM) in locally advanced rectal cancer (LARC) patients receiving neoadjuvant chemoradiotherapy (nCRT) are helpful developing appropriate treatment plans. This study aimed to perform DM prediction through deep learning radiomics.We retrospectively sampled 235 nCRT with the minimum 36 months' postoperative follow-up from three hospitals. Through transfer learning, a radiomic signature (DLRS) based on multiparametric magnetic resonance imaging (MRI)...
BackgroundAccurate lymph nodes (LNs) assessment is important for rectal cancer (RC) staging in multiparametric magnetic resonance imaging (mpMRI). However, it incredibly time-consumming to identify all the LNs scan region. This study aims develop and validate a deep-learning-based, fully-automated node detection segmentation (auto-LNDS) model based on mpMRI.MethodsIn total, 5789 annotated (diameter ≥ 3 mm) mpMRI from 293 patients with RC single center were enrolled. Fused T2-weighted images...
Abstract Immunotherapy brings great benefits for tumor therapy in clinical treatments but encounters the severe challenge of low response rate mainly because immunosuppressive microenvironment. Multifunctional nanoplatforms integrating effective drug delivery and medical imaging offer tremendous potential cancer treatment, which may play a critical role combinational immunotherapy to overcome microenvironment efficient therapy. Here, nanodrug (BMS‐SNAP‐MOF) is prepared using glutathione...
Background: Immune checkpoint inhibitor (ICI) treatment in patients with microsatellite instability-high/mismatch repair deficient (MSI-H/dMMR) tumors holds promise reshaping organ preservation rectal cancer. However, the benefits are accompanied by distinctive patterns of response, introducing a dilemma response evaluation for clinical decision-making. Patients and Methods: locally advanced cancer MSI-H/dMMR receiving neoadjuvant ICI (nICI) (n=13) matched chemoradiotherapy (nCRT; n=13) were...
To develop and validate a model for predicting major pathological response to neoadjuvant chemotherapy (NAC) in advanced gastric cancer (AGC) based on machine learning algorithm. A total of 221 patients who underwent NAC radical gastrectomy between February 2013 September 2020 were enrolled this study. 144 assigned the training cohort building, 77 validation cohort. was defined as primary tumor regressing ypT0 or T1. Radiomic features extracted from venous-phase computed tomography (CT)...
Pancreatic cancer therapies such as chemotherapy and immunotherapy are hindered by the dense extracellular matrix known physical barriers, leading to heterogeneity impeding effective penetration of chemotherapeutic agents activation antitumor immune responses. To address this challenge, we developed a hybrid nanoassembly with distinct core-satellite-like heterostructure, PLAF@P/T-PD, which is responsive both internal pH/redox external ultrasound stimulations. This heterostructural features...
BACKGROUND: Accurate prediction of response to neoadjuvant chemoradiotherapy is critical for subsequent treatment decisions patients with locally advanced rectal cancer. OBJECTIVE: To develop and validate a deep learning model that based on the comparison paired magnetic resonance imaging before after predict pathological complete response. DESIGN: By capturing changes from images in 638 patients, we trained multitask (DeepRP-RC) also allowed simultaneous segmentation. Its performance was...
Background: Tumor-stroma interactions, as indicated by tumor-stroma ratio (TSR), offer valuable prognostic stratification information. Current histological assessment of TSR is limited tissue accessibility and spatial heterogeneity. We aimed to develop a multitask deep learning (MDL) model noninvasively predict prognosis in colorectal cancer (CRC). Materials Methods: In this retrospective study including 2268 patients with resected CRC recruited from four centers, we developed an MDL using...
This study explored the association between cerebral metabolic rates of glucose (CMRGlc) and severity Vascular Parkinsonism (VP) Parkinson’s disease (PD). A cross-sectional was performed to compare CMRGlc in normal subjects vs. VP PD patients. Twelve subjects, 22 VP, 11 patients were evaluated with H&Y MMSE, underwent 18F-FDG measurements. Pearson’s correlations used identify potential associations VP/PD CMRGlc. pronounced reduction frontal lobe caudate putamen detected when compared...
One of the main challenges in applying immune checkpoint blockade to treat colorectal cancer (CRC) is immunosuppressive tumor microenvironment. Owing its excellent cell killing ability and activation, mild photothermal therapy (PTT) has shown bright promise sensitize tumors inhibition through turning immunologically "cold" into "hot" ones. Herein, a effect-assisted theragnostic nanodrug (MnO2@MPDA-PEG NPs) developed by incorporating MnO2 PEGylated-mesoporous polydopamine nanoparticles...