Abstract:
Super paramagnetic iron oxide (SPIO) particles are useful for MRI contrast agents due to their susceptibility. Relaxometry or measuring their inhomogeneities quantifies these particles. These methods use phase, which is unreliable at high concentrations. This study introduces a Deep Learning method to quantify SPIO concentration distribution. We used View Line to encode field map information in image geometry. Our novel network uses residual blocks as the bottleneck and multiple decoders to improve gradient flow. Each decoder predicts a different concentration map wavelet decomposition. This decomposition increases model convergence and concentration estimation. Our SPIO concentration reconstruction method was tested with simulated images and phantom scan data. The IXI dataset images were used to simulate plastic cylinders with agar and SPIO particles at different concentrations. The model accurately quantified distributions in both experiments.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
