Publications by authors named "Wuli Tang"
Article Synopsis
- Researchers developed a machine learning model using unenhanced CT scans to evaluate the risk of malignant cerebral edema (MCE) in patients with acute ischemic stroke (AIS).
- The study involved 179 patients assigned to training and validation groups, analyzing radiomics features related to MCE through various statistical methods and constructing predictive models.
- Logistic regression was identified as the most effective algorithm, with high accuracy rates in predicting MCE, suggesting the model can aid in clinical decision-making and patient prognosis.
Article Synopsis
- Researchers developed machine learning models using non-contrast computed tomography images and clinical data to assess the risk of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS).
- A study involving 180 AIS patients revealed that 104 experienced HT, with significant clinical differences in factors like the neutrophil-to-lymphocyte ratio and infarct volume between those who did and did not have HT.
- The optimal ML model for predicting HT was logistic regression, achieving high predictive accuracy, particularly with a combined clinical-radiomics approach, which showed an area under the curve (AUC) of 0.957 in validation.
Article Synopsis
- The study aimed to develop a machine learning model that uses dual-energy CT enterography (DECTE) to noninvasively assess Crohn's disease (CD) activity, which is typically evaluated through an invasive scoring method called SES-CD.
- A total of 202 bowel segments from 46 CD patients were analyzed, and the models showed an area under the ROC curve (AUC) between 0.81 and 0.87 for accurately assessing CD activity based on DECTE parameters.
- The results suggest that the machine learning model effectively and quantitatively evaluates CD activity, making it a promising alternative to traditional invasive methods.
Background: The disease activity status and behavior of Crohn's disease (CD) can reflect the severity of the disease, and changes in body composition are common in CD patients.
Aims: The aim of this study was to investigate the relationship between body composition parameters and disease severity in CD patients treated with infliximab (IFX).
Methods: Patients with CD assessed with the simple endoscopic score (SES-CD) and were treated with IFX were retrospectively collected, and body composition parameters at the level of the 3rd lumbar vertebrae were calculated from computed tomography (CT) scans of the patients.
Background And Aims: Body composition changes in patients with Crohn's disease (CD) have received increasing attention in recent years. This review aims to describe the changes in body composition in patients with CD on imaging and to analyze and summarize the prognostic value of body composition.
Methods: We systematically searched Web of Science, PubMed, Embase, Cochrane Library, and Medline via OVID for literature published before November 2022, and two researchers independently evaluated the quality of the retrieved literature.
Objective: To develop and validate a model based on the radiomics features of the infarct areas on non-contrast-enhanced CT to predict hemorrhagic transformation (HT) in acute ischemic stroke.
Materials And Methods: A total of 118 patients diagnosed with acute ischemic stroke in two centers from January 2019 to February 2022 were included. The radiomics features of infarcted areas on non-contrast-enhanced CT were extracted using 3D-Slicer.