Motivation: With the advancement of medical imaging technology, MRI is increasingly used in clinical diagnosis. However, certain modalities are often missed in MRI images, which can lead to difficulties in accurate diagnosis. Goal(s): The paper introduces a Transformer-driven approach for synthesizing MRI images, aimed at generating missing modalities from available scans to enhance overall image quality. Approach: A generative network with anti-interference capabilities has been designed to effectively utilize structural information from existing images to generate the missing modalities. Results: The experimental results demonstrate that the proposed method exhibits robustness against motion artifacts and delivers more accurate, high-quality outcomes. Impact: This study introduces a novel technique for generating missing modality high quality images in MRI, which is robust to motion artifacts. The provision of structurally intact images enables clinicians to identify lesions more efficiently, augment diagnostic precision.
Zhang et al. (Tue,) studied this question.