Publications by authors named "Zifeng Lian"
Deep learning methods show great potential for the efficient and precise estimation of quantitative parameter maps from multiple magnetic resonance (MR) images. Current deep learning-based MR parameter mapping (MPM) methods are mostly trained and tested using data with specific acquisition settings. However, scan protocols usually vary with centers, scanners, and studies in practice.
View Article and Find Full Text PDFPurpose: To develop a fully automatic parenchyma extraction method for the T2* relaxometry of iron overload liver.
Methods: A retrospective multicenter collection of liver MR examinations from 177 transfusion-dependent patients was conducted. The proposed method extended a semiautomatic parenchyma extraction algorithm to a fully automatic approach by introducing a modified TransUNet on the R2* (1/T2*) map for liver segmentation.
Background: The T2* value of interventricular septum is routinely reported for grading myocardial iron load in thalassemia major, and automatic segmentation of septum could shorten analysis time and reduce interobserver variability.
Purpose: To develop a deep learning-based method for automatic septum segmentation from black-blood MR images for the myocardial T2* measurement of thalassemia patients.
Study Type: Retrospective.
Cascade of Denoising and Mapping Neural Networks for MRI R2* Relaxometry of Iron-Loaded Liver.
Bioengineering (Basel)
February 2023
Article Synopsis
- MRI can help measure iron in the liver, but noise can make it harder to get clear results.
- The study created a special computer program called CadamNet that uses advanced technology to improve the accuracy of these measurements, even with noisy data.
- CadamNet was tested and showed it could produce better quality results compared to other methods, making it a reliable way to check for iron overload in the liver.