Abstract:
MRI can delineate craniomaxillofacial (CMF) bony structures without radiation, unlike CT. MRI blurs bony boundaries, so structural information must be borrowed from CT during training. Paired MRI-CT data are scarce, making this difficult.
We propose a one-shot generative adversarial model for automated MRI segmentation of CMF bony structures using abundant unpaired data and a single paired MRI-CT data. Our model has an MRI segmentation sub-network and a cross-modality image synthesis sub-network that learns CT-MRI mapping.
Both sub-networks are trained end-to-end. In the training phase, a neighbor-based anchoring method reduces the ambiguity of cross-modality synthesis, and a feature-matching-based semantic consistency constraint encourages segmentation-oriented MRI synthesis. Our method outperforms state-of-the-art MRI segmentation methods qualitatively and quantitatively in 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
