Publications by authors named "Wen-Xiao Li"
Article Synopsis
- The study aims to create a machine learning model that combines clinical data and ultrasound radiomic analysis to predict whether axillary lymph nodes are affected in early-stage breast cancer patients.
- Using retrospective data from 321 patients, the researchers identified significant risk factors and developed both clinical and ultrasound radiomics models, comparing multiple machine learning algorithms to find the most effective for diagnosis.
- The results showed that the joint prediction model based on the Extreme Gradient Boosting (XGBoost) algorithm performed best, achieving high AUC scores, indicating strong accuracy in predicting lymph node status.
Background: Explore the feasibility of using the multimodal ultrasound (US) radiomics technology to diagnose American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) 4-5 thyroid nodules.
Method: This study prospectively collected the clinical characteristics, conventional, and US elastography images of 100 patients diagnosed with ACR TI-RADS 4-5 nodules from May 2022 to 2023. Independent risk factors for malignant thyroid nodules were extracted and screened using methods such as the least absolute shrinkage and selection operator (LASSO) logistic regression (LR) model, and a multimodal US radiomics combined diagnostic model was established.
Artificial intelligence (AI), particularly deep learning (DL) algorithms, has demonstrated remarkable progress in image-recognition tasks, enabling the automatic quantitative assessment of complex medical images with increased accuracy and efficiency. AI is widely used and is becoming increasingly popular in the field of ultrasound. The rising incidence of thyroid cancer and the workload of physicians have driven the need to utilize AI to efficiently process thyroid ultrasound images.
View Article and Find Full Text PDFObjective: This study compared the diagnostic value of various diagnostic methods for lymph node metastasis (LNM) of papillary thyroid carcinoma (PTC) through network meta-analysis.
Methods: In this experiment, databases such as CNKI, Wanfang, PubMed, and Web of Science were retrieved according to the Cochrane database, Prisma, and NMAP command manual. A meta-analysis was performed using STATA 15.
Article Synopsis
- The study evaluates how accurately the VGGNet deep learning model can differentiate between benign and malignant thyroid nodules using ultrasound images.
- A total of 11 research studies were analyzed, revealing high sensitivity (0.87) and specificity (0.85) for the model, indicating it performed well in diagnosis.
- Overall, the VGGNet model showed strong diagnostic efficacy with an area under the curve of 0.93, confirming its effectiveness in this medical application.
Background: Interleukin-9 (IL9) plays a critical role in immunity and the pathogenesis of endometrial cancer (EC), especially endometrioid EC (EEC). This study aimed to identify the IL9+ immune cell subsets and their pleiotropic functions and establish an optimized prognostic nomogram towards the promotion of personalized treatment of EEC.
Methods: 1,417 EC patients were involved in the present study.
The popularity of capillary electrochromatography (CEC) has led to an increasing number of studies on the development and evaluation of enantioselective CEC systems. Herein, a novel, simple, and economical method for the preparation of chiral stationary phases for enantioselective open tubular capillary electrochromatography (OTCEC) was reported for the first time. This novel capillary column was fabricated through layer-by-layer self-assembly of GNPs on a 3-mercaptopropyl-trimethoxysilane (MPTMS)-modified fused-silica capillary and subsequent surface functionalization of the GNPs through self-assembly of thiols β-cyclodextrin (SH-β-CD).
View Article and Find Full Text PDF