Scanner agnostic large-scale evaluation of MS lesion delineation tool for clinical MRI.

Amalie Monberg Hindsholm,Flemming Littrup Andersen,Stig Præstekjær Cramer,Helle Juhl Simonsen, Mathias Gæde Askløf,Melinda Magyari, Poul Nørgaard Madsen,Adam Espe Hansen,Finn Sellebjerg,Henrik Bo Wiberg Larsson,Annika Reynberg Langkilde,Jette Lautrup Frederiksen,Liselotte Højgaard,Claes Nøhr Ladefoged,Ulrich Lindberg

Frontiers in neuroscience（2023）

引用 1|浏览1

暂无评分

摘要

In conclusion we have seen, that by including a large, heterogeneous dataset emulating clinical reality, we have trained a segmentation model which maintains a high segmentation performance while being robust to data from unseen scanners. This broadens the applicability of the model in clinic and paves the way for clinical implementation.

查看译文

关键词

multiple sclerosis,white matter lesions (WML),automatic segmentation algorithm,clinical applicability,clinical dataset,heterogeneous dataset,multi-scanner

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要