Meeting Banner
Abstract #1974

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

Debosmita Biswas1, Vivian Y Park2, Daniel S Hippe3, Dallas Turley4, Kevin Widner5, Tao Yangchen5, Isabella Li1, Mary Lynn Bryant1, Johannes Peeters6, Habib Rahbar1, and Savannah C Partridge1
1University of Washington, Seattle, WA, United States, 2Radiology, Yonsei University College of Medicine, Seattle, WA, United States, 3Clinical research Division, Fred Hutchison Cancer Center, Seattle, WA, United States, 4Philips Healthcare, Seattle, WA, United States, 5Fred Hutchison Cancer Center, Seattle, WA, United States, 6Philips Healthcare, Eindhoven, Netherlands

Synopsis

Keywords: Breast, Breast, DWI Breast AI/ML reconstructions on scanner

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords