Motivation: 7T SWI provides a higher signal-to-noise ratio, greater venous detail, and better diagnostic capability but its application is limited by physiologic considerations and high costs. Goal(s): Our goal was to generate realistic 7T-like SWI from routine 3T SWI to improve the image quality and diagnostic capability. Approach: We employed an attention-based generative adversarial network guided by inverted minimum intensity projection information. Results: The proposed method achieved the best qualitative and quantitative results compared to existing competitive methods. Impact: This study was an early exploration of artificial intelligence methods in the field of cross-field-strength SWI image generation. It provided insights for related research on enhancing the image quality and diagnostic capability of low-field MR images.
Tang et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: