Abstract #2642

Validation of Deep Learning Volume Interpolated Breath-hold Exam (VIBE) versus Standard VIBE for Detecting Internal Auditory Canal Lesions.

Chen Hua Chiang^1,2,3, Sittaya Buathong^1,3, Azadeh Hajati^1,4, Azadeh Tabari^1,4, Wei-Ching Lo⁵, Dominik Nickel⁶, Bryan Clifford⁵, Robert Sellers⁷, Stephen F. Cauley⁵, John Conklin^1,4, and Susie Y Huang^1,4,8

¹Department of Radiology, Massachusetts General Hospital, Boston, MA, United States, ²2. Department of Medical Image, Shuang Ho Hospital, Taipei Medical University, Taipei, Taiwan, ³Department of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, United States, ⁴Harvard Medical School, Boston, MA, United States, ⁵Siemens Medical Solutions USA, Boston, MA, United States, ⁶Siemens Healthineers AG, , Germany, Forchheim, Germany, ⁷Siemens Medical Solutions USA, Philadelphia, PA, United States, ⁸Harvard-MIT Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States

Synopsis

Keywords: AI/ML Image Reconstruction, AI/ML Image Reconstruction, MRI, IAC

Motivation: MRI is vital for evaluating intracranial pathologies, but standard VIBE can be limited by artifacts and lower soft tissue contrast. Recent DL-based reconstructions offer potential for improved imaging quality and reduced scan times.

Goal(s): To determine if DL-VIBE is non-inferior to standard VIBE in diagnostic quality.

Approach: A prospective study with 62 patients undergoing IAC MRI. Radiologists assessed DL-VIBE and ST-VIBE sequences using a 5-point scale across multiple diagnostic categories for qualitative comparison and quantitative comparison.

Results: DL-VIBE was non-inferior in key image quality, with high interrater agreement for enhancing lesions and comparable SNR, CNR while providing a 15% reduction in scanned time.

Impact: DL-VIBE supports efficient clinical workflows and reliable diagnostics compared with standard VIBE, encouraging wider adoption of DL-based MRI protocols.

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.