Image quality evaluation of multi-sensitivity diffusion-weighted imaging for rectal cancer with small field of view based on deep learning

Motivation: Diffusion-weighted magnetic resonance imaging (DW-MRI) is essential for rectal cancer imaging. Goal(s): This study evaluated the image quality, rectal contours, lesion visibility of low-field multiple sensitivity diffusion-weighted imaging enhanced with deep learning reconstruction , assessing their signal-to-noise ratio and contrast-to-noise ratio . Approach: 60 patients who underwent rectal MR examination at our hospital since January 2024 and were confirmed to have rectal adenocarcinoma by pathology were included. Results: The SNR , CNR , image quality, rectal contour, and lesion visibility of FOCUS-MUSE images with DL were superior to those without DL (p < 0.01 for SNR, CNR, image quality, rectal contour, p = 0.02 for lesion visibility). Impact: This study shows that DLR-based FOCUS-MUSE DWI enhances image quality, rectal contour, lesion visibility, SNR, and CNR, suggesting its potential to improve colorectal cancer staging accuracy.