A5072504172- Radiomics and Machine Learning in Medical Imaging
- Bladder and Urothelial Cancer Treatments
- Urinary and Genital Oncology Studies
- EEG and Brain-Computer Interfaces
- Maternal and fetal healthcare
- Colorectal Cancer Screening and Detection
- Sarcoma Diagnosis and Treatment
- Pregnancy and preeclampsia studies
- Healthcare Technology and Patient Monitoring
- MRI in cancer diagnosis
- Uterine Myomas and Treatments
- Bone Tumor Diagnosis and Treatments
- Renal cell carcinoma treatment
- Musculoskeletal synovial abnormalities and treatments
- Pancreatic and Hepatic Oncology Research
- Non-Invasive Vital Sign Monitoring
- Pelvic and Acetabular Injuries
- Medical Image Segmentation Techniques
Shenzhen University
2023-2025
Shenzhen University Health Science Center
2022-2024
Macao Polytechnic University
2024
Inflammatory bowel disease (IBD) is a recurrent that usually requires magnetic resonance enterography (MRE) for diagnosis and monitoring. However, recognition of segments from MRE images by radiologist challenging time-consuming. Deep learning-based medical image segmentation has shown the potential to reduce manual effort provide automated tools assist in management; however, it large-scale fine-annotated dataset training. To address this gap, we collected data, including half-Fourier...
Aim: To construct and validate a multitask deep learning (DL) model based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) contrast-enhanced magnetic resonance imaging (MRI) for predicting microvascular invasion (MVI) plus cytokeratin 19 (CK19) positivity in patients with hepatocellular carcinoma (HCC). Methods: A total of 145 pathologically confirmed HCC undergoing preoperative enhanced MRI were assessed between January 2012 2023. predictive model, whose skeleton...
Background Different placenta accreta spectrum (PAS) subtypes pose varying surgical risks to the parturient. Machine learning model has potential diagnose PAS disorder. Purpose To develop a cascaded deep semantic‐radiomic‐clinical (DRC) for diagnosing and its based on T2‐weighted MRI. Study Type Retrospective. Population 361 pregnant women (mean age: 33.10 ± 4.37 years), suspected of PAS, divided into segment training cohort ( N = 40), internal 139), testing 60), external 122). Field...
Bladder cancer (BCa), as the most common malignant tumor of urinary system, has received significant attention in research on clinical application artificial intelligence algorithms. Nevertheless, it been observed that certain investigations use data from various medical facilities to train models for BCa, which may pose a privacy risk. Given this concern, protecting patient during machine learning algorithm training is crucial aspect requires substantial attention. One emerging paradigm...
Conventional radiomics analysis requires the manual segmentation of lesions, which is time-consuming and subjective. This study aimed to assess feasibility predicting muscle invasion in bladder cancer (BCa) with using a semi-automatic lesion method on T2-weighted images. Cases non-muscle-invasive BCa (NMIBC) muscle-invasive (MIBC) were pathologically identified training cohort internal external validation cohorts. For tumor segmentation, deep learning-based model was constructed, while...
Background: Occult peritoneal metastases (OPM) in patients with pancreatic ductal adenocarcinoma (PDAC) are frequently overlooked during imaging. We aimed to develop and validate a CT-based deep learning-based radiomics (DLR) model identify OPM PDAC before treatment. Methods: This retrospective, bicentric study included 302 (training: n=167, OPM-positive, n=22; internal test: n=72, n=9: external test, n=63, n=9) who had undergone baseline CT examinations between January 2012 October 2022....
Most primary bone tumors are often found in the around knee joint. However, detection of on radiographs can be challenging for inexperienced or junior radiologist. This study aimed to develop a deep learning (DL) model joint radiographs.