Publications by authors named "Tiejun Gan"
Article Synopsis
- The study investigates the effectiveness of Deep Learning Radiomics Nomograms (DLRN) for predicting IDH genotype in glioma patients.
- A total of 402 patients were divided into training and validation groups to develop a model that combines deep learning, radiomics, and clinical data for accurate classification.
- The DLRN showed high performance with an AUC of 0.98, indicating its potential to improve patient management and targeted therapy based on IDH mutation status.
Purpose: The aim of this study was to evaluate the diagnostic accuracy of the B1 inhomogeneity-corrected variable flip angle (VFA) method using native T1 values in the staging of liver fibrosis.
Methods: Eighty-three patients who presented for liver biopsy due to varying degrees of liver damage, underwent MR examinations and had T1-mapping images of the liver acquired using the B1 inhomogeneity-corrected VFA VIBE method. Among them, 65 patients underwent Fibroscan, and their results were used to evaluate the elasticity of liver tissue.
Combination of IVIM with DCE-MRI for diagnostic and prognostic evaluation of breast cancer.
Magn Reson Imaging
November 2024
Purpose: To identify the most effective combination of DCE-MRI (K,K) and IVIM (D,f) and analyze the correlations of these parameters with prognostic indicators (ER, PR, and HER2, Ki-67 index, axillary lymph node (ALN) and tumor size) to improve the diagnostic and prognostic efficiency in breast cancer.
Methods: This is a prospective study. We performed T1WI, T2WI, IVIM, DCE-MRI at 3 T MRI examinations on benign and malignant breast lesions that met the inclusion criteria.
Article Synopsis
- Accurate assessment of IDH mutation status in glioma patients is critical for treatment planning and predicting outcomes; this study focuses on using MRI to differentiate between astrocytoma and glioblastoma based on IDH status.
- The study involved 80 glioma patients and utilized synthetic MRI scans alongside immunohistochemistry or gene sequencing to determine IDH mutation status; histogram metrics from the MRI were compared with radiological features.
- Results showed that IDH-mutant astrocytoma patients had different MRI metrics (e.g., lower T1 values and higher post-contrast T1 values) compared to IDH-wildtype glioblastoma patients, leading to a combined model that could improve diagnostic accuracy.
This study associated the liver proton density fat fraction (PDFF), measured by multi-echo Dixon (ME-Dixon) and breath-hold single-voxel high-speed T2-corrected multi-echo H magnetic resonance spectroscopy (HISTO) at 1.5 T, with serum biomarkers and liver fibrosis stages. This prospective study enrolled 75 patients suspected of liver fibrosis and scheduled for liver biopsy and 23 healthy participants with normal liver function.
View Article and Find Full Text PDFStroke is a massive public health problem. The rupture of vulnerable carotid atherosclerotic plaques is the most common cause of acute ischemic stroke (AIS) across the world. Currently, vessel wall high-resolution magnetic resonance imaging (VW-HRMRI) is the most appropriate and cost-effective imaging technique to characterize carotid plaque vulnerability and plays an important role in promoting early diagnosis and guiding aggressive clinical therapy to reduce the risk of plaque rupture and AIS.
View Article and Find Full Text PDFArticle Synopsis
- * This study compared various deep learning frameworks (like ResNet and ConvNext) and image preprocessing techniques using MRI data from 211 glioma patients to enhance model accuracy before surgery.
- * Results indicated that specific preprocessing methods and adding numerical data improved accuracy significantly, with ResNet34 outperforming other models, especially in small to medium datasets.
Fatigue is a debilitating and prevalent symptom of multiple sclerosis (MS). The thalamus is atrophied at an earlier stage of MS and although the role of the thalamus in the pathophysiology of MS-related fatigue has been reported, there have been few studies on intra-thalamic changes. We investigated the alterations of thalamic nuclei volumes and the intrinsic thalamic network in people with MS presenting fatigue (F-MS).
View Article and Find Full Text PDFBackground: Hepatocellular carcinoma (HCC) is ranked fifth among the most common cancer worldwide. Hypoxia can induce tumor growth, but the relationship with HCC prognosis remains unclear. Our study aims to construct a hypoxia-related multigene model to predict the prognosis of HCC.
View Article and Find Full Text PDF