Cover Image

Optimizing MRI sequence classification performance: insights from domain shift analysis

MRI sequence classification becomes challenging in multicenter studies due to variability in imaging protocols, leading to unreliable metadata and requiring labor-intensive manual annotation. While numerous automated MRI sequence identification models are available, they frequently encounter the iss...

Full description

Saved in:
Bibliographic Details
Main Authors: Mahmutoglu, Mustafa A. (Author) , Rastogi, Aditya (Author) , Brugnara, Gianluca (Author) , Vollmuth, Philipp (Author) , Foltyn-Dumitru, Martha (Author) , Sahm, Felix (Author) , Pfister, Stefan (Author) , Sturm, Dominik (Author) , Bendszus, Martin (Author) , Schell, Marianne (Author)
Format: Article (Journal)
Language:English
Published: 26 May 2025
In: European radiology
Year: 2025, Volume: 35, Issue: 11, Pages: 6710-6718
ISSN:1432-1084
DOI:10.1007/s00330-025-11671-5
Online Access:Resolving-System, kostenfrei, Volltext: https://doi.org/10.1007/s00330-025-11671-5
Verlag, kostenfrei, Volltext: https://link.springer.com/article/10.1007/s00330-025-11671-5
Get full text
Author Notes:Mustafa Ahmed Mahmutoglu, Aditya Rastogi, Gianluca Brugnara, Philipp Vollmuth, Martha Foltyn-Dumitru, Felix Sahm, Stefan Pfister, Dominik Sturm, Martin Bendszus and Marianne Schell
Description
Summary:MRI sequence classification becomes challenging in multicenter studies due to variability in imaging protocols, leading to unreliable metadata and requiring labor-intensive manual annotation. While numerous automated MRI sequence identification models are available, they frequently encounter the issue of domain shift, which detrimentally impacts their accuracy. This study addresses domain shift, particularly from adult to pediatric MRI data, by evaluating the effectiveness of pre-trained models under these conditions.
Item Description:Gesehen am 31.03.2026
Physical Description:Online Resource
ISSN:1432-1084
DOI:10.1007/s00330-025-11671-5

Similar Items