What type of study is this?

This is a Quantitative Study study.

September 17, 2025

Multi-shot EPI and deep learning reconstruction: Clinical utility in breast DWI

Key Points

MsDWI and msDWI-DL exhibited less distortion compared to conventional ssDWI, enhancing diagnostic precision.
The qualitative comparison revealed msDWI-DL's potential for greater lesion conspicuity, although it introduced more noise in images.
Improvements noted in imaging metrics suggest multi-shot EPI techniques may enable better evaluation of breast lesions.
These findings highlight the clinical relevance of integrating deep learning techniques in breast MRI to optimize imaging outcomes.

Abstract

Motivation: - DWI can detect and characterize breast lesions with encouraging performance but suffers from geometric distortions especially at higher resolutions, limiting clinical uptake. Multi-shot EPI DWI (msDWI) decreases distortions but is sensitive to motion and requires longer acquisition times. Deep learning-enhanced (msDWI-DL) approaches may further improve image quality. Goal(s): Evaluate msDWI and msDWI-DL versus conventional single-shot DWI (ssDWI) in clinical breast MRI. Approach: Conducted qualitative and quantitative comparison of image quality and lesion conspicuity for ssDWI, msDWI, and high resolution msDWI-DL. Results: msDWI and msDWI-DL demonstrated less distortion versus ssDWI. msDWI-DL had higher noise but may also provide greater lesion conspicuity. Impact: This study demonstrated that multishot EPI breast DWI can significantly reduce geometric distortions and potentially improve lesion conspicuity over single-shot EPI DWI, especially using an AI based reconstruction technique to increase spatial resolution without adding to scan time.

Multi-shot EPI and deep learning reconstruction: Clinical utility in breast DWI

Key Points

Abstract

Cite This Study

Also Consider

Also Consider