Clinical feasibility of a deep learning approach for conventional and synthetic diffusion-weighted imaging in breast cancer: Qualitative and quantitative analyses

Purpose: In this study, we aimed to investigate the clinical feasibility of deep learning (DL)-based reconstruction applied to conventional diffusion-weighted imaging (cDWI) and synthetic diffusion-weighted imaging (sDWI) by comparing the DL reconstructions to cDWIs and sDWIs in patients with various breast malignancies. Methods: We retrospectively analyzed 115 patients with biopsy-proven breast malignancies who underwent breast magnetic resonance imaging from July 2022 to June 2023, including cDWI with b-value of 800 s/mm(2) (cDWI(800)), sDWI with b-value of 1500 s/mm(2) (sDWI(1500)), DWI using DL-based reconstruction (DL-DWI) with bvalue of 800 s/mm(2) , and synthetic DL-DWI with b-value of 1500 s/mm(2) (DL-DWI800 and sDL-DWI1500). Two radiologists independently performed the qualitative analyses using a 5-point Likert scale for all DWI sets. The quantitative analyses were also conducted for signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and cancer-to-parenchyma contrast ratio (CPR). Results: DL-DWI800 and sDL-DWI(1500)provided better lesion conspicuity and thoracic muscle and rib delineation than cDWI(800 )and sDWI(1500) (all P < 0.05). DL-DWI800 and sDL-DWI(1500)showed comparable normal parenchymal signals to those of cDWI(800 )and sDWI(1500 )all P > 0.05). sDL-DWI(1500)and sDWI(1500 )showed no significant differences in SNR and CNR (P = 0.908, and P = 0.081, respectively). DL-DWI800 and cDWI(800 )were not significantly different between SNR, CNR, and CPR (all P > 0.05). Conclusions: DL-DWI outperformed cDWI and sDWI in both qualitative and quantitative analyses at the high b- values, while also achieving a shorter acquisition time.