LightMedSeg-ISLES: Stroke Lesion Segmentation with 81x Fewer Parameters than nnU-Net
LightMedSeg-ISLES, a 1.26-million-parameter pipeline for T1-weighted stroke lesion segmentation in ISLES, is presented, establishing a strong single-checkpoint alternative to much larger models.
Giorgi Nikvashvili, Han Gu, Jie Bao et al.
· 0 citations