The Value of Deep Learning Reconstruction In Improving the Image Quality of rectum MRI Images

Motivation: TSE sequences are crucial for rectum MRI, but have limitations. DL-TSE is expected to improve image quality and reduce acquisition time for rectum MRI. Goal(s): To assess the viability of employing TSE sequences with deep learning reconstruction for rectal MRI when compared to conventional TSE sequences. Approach: This study included 16 patients with colorectal cancer confirmed by pathology. SNR and CNR were analyzed by SPSS 22.0 software.A P-value below 0.05 was considered statistically significant. Results: The results show that the application of deep learning can shorten the scanning time while maintaining high image resolution, and improve the diagnostic efficiency of rectal diseases. Impact: Deep learning reconstruction of TSE sequence in rectal MRI has the advantages of shortening acquisition time, improving image quality, and improving diagnostic efficiency. DL-TSE may also be extended to MRI examinations of other organs, such as the prostate and pelvis.