FOCUS DWI and Deep Learning Reconstruction in breast MRI: A comparison with conventional DWI

Abstract

Purpose

To employ deep-learning based reconstruction (DLR) to improve the SNR of FOCUS DWI for breast imaging in Asian patients and investigate the feasibility and performance of reduced-FOV FOCUS DWI and FOCUS DWI with deep learning-based reconstruction (DLR) for breast MRI in Asian patients with small breast volumes.

Materials and Methods

Forty-nine female patients suspected of having breast cancer from July 2023 to December 2023. They underwent breast MRI examinations using three sequences: Conventional DWI, Focus DWI, Focus-DLR DWI. Two radiologists independently assessed image quality using a 5-point Likert scale. They also outlined the lesions, calculating the signal-to-noise ratio (SNR) of the lesion, the Contrast-to-Noise Ratio (CNR) between the lesion and surrounding tissue, and the Apparent Diffusion Coefficient (ADC) of the lesion. Image scores, SNR, CNR and ADC were compared using the Friedman test.

Results

FOCUS-DLR DWI had higher scores in terms of the overall image quality, the anatomical details, lesion conspicuity, artifacts and distortion than conventional DWI (P<0.001, P<0.001, P<0.001, P<0.001, P<0.001). The SNR of FOCUS-DLR DWI was higher than that of conventional DWI and FOCUS DWI (P<0.001, P<0.001), while there were no statistically significant differences between FOCUS-DWI and conventional DWI(P>0.05). What's more, in terms of CNR values and ADC values, there were no significant difference among three sequences.

Conclusion

Our findings indicate that FOCUS DWI with deep learning-based reconstruction produces superior images than conventional DWI, enhancing the applicability of this technique in clinical practice. Deep learning-based reconstruction provides a new direction for optimizing DWI imaging techniques in Asian breast MRI.