SADL: A Size-Adaptive Decision Layer for Chronic Stroke Lesion Segmentation in ISLES 2026

Key points

• Their appearance overlaps with healthy tissue, and their volumes span four orders of magnitude, so voxel-level and lesion level metrics often disagree.1
• We build an eleven-member nnU-Net ensemble that covers five design axes: a baseline dice + top-K loss, heavy augmentation, per-lesion volume loss re-weighting, stochastic weight averaging, and a sampling-and-architecture block that pairs cohort-balanced sampling with a residual-encoder backbone.1
• Weighted soft-map fusion of the members feeds a tuned decision layer, SADL, that estimates lesion volume, applies an adaptive per-lesion-size threshold, prunes components by voxel count and peak probability, and adds a never-empty rescue.1
• A paired non-parametric bootstrap against a reference single ensemble member confirms the lesion-F1 gain at p=0.024, and the gain is largest in the small-lesion regime, where the rescue step recovers cases that a fixed threshold would silently discard.1

Sources (1)

• [1]SADL: A Size-Adaptive Decision Layer for Chronic Stroke Lesion Segmentation in ISLES 2026
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 11:28 AM

  Chronic ischemic stroke lesions are difficult to segment on T1-weighted MRI.

  Their appearance overlaps with healthy tissue, and their volumes span four orders of magnitude, so voxel-level and lesion level metrics often disagree.

Extractive summary: sentences quoted from the sources.