LightMedSeg-ISLES: Stroke Lesion Segmentation with 81x Fewer Parameters than nnU-Net

arXiv:2609.09634v1 Announce Type: new Abstract: Large networks and ensembles often lead medical image segmentation challenges, but their storage and inference demands complicate deployment. We present LightMedSeg-ISLES, a 1.26-million-parameter pipeline for T1-weighted stroke lesion segmentation in ISLES'26. On a 146-case held-out cohort, flip test-time augmentation produces 0.618 mean Dice and 0.599 lesion-wise F1. A 102.35-million-parameter nnU-Net ResEnc-L produces 0.634 Dice and 0.544 lesion-wise F1 after size filtering. LightMedSeg therefore retains 97.5% of nnU-Net's Dice with 81.4imes fewer parameters while improving lesion-wise F1 by 0.055. Its four-pass TTA operating point requires 4.7imes fewer FLOPs per standardized patch than nnU-Net. It also slightly exceeds filtered UNETR++ and nnFormer. Longer training and stronger augmentation add 0.0358 Dice without increasing capacity, establishing a strong single-checkpoint alternative to much larger models.

Related

• GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modeling
• Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis
• MedCore: Boundary-Preserving Medical Core Pruning for MedSAM
• PBE-UNet: A light weight Progressive Boundary-Enhanced U-Net with Scale-Aware Aggregation for Ultrasound Image Segmentation

Source: arXiv cs.CV | 2026-09-10