Papers › BeSt-LeS: Benchmarking Stroke Lesion Segmentation using Deep Supervision

BeSt-LeS: Benchmarking Stroke Lesion Segmentation using Deep Supervision

10 Oct 2023arXiv:2310.07060archive 2025-07-28

Prantik Deb, Lalith Bharadwaj Baru, Kamalaker Dadi, Bapi Raju S

Brain stroke has become a significant burden on global health and thus we need remedies and prevention strategies to overcome this challenge. For this, the immediate identification of stroke and risk stratification is the primary task for clinicians. To aid expert clinicians, automated segmentation models are crucial. In this work, we consider the publicly available dataset ATLAS v2.0 to benchmark various end-to-end supervised U-Net style models. Specifically, we have benchmarked models on both 2D and 3D brain images and evaluated them using standard metrics. We have achieved the highest Dice score of 0.583 on the 2D transformer-based model and 0.504 on the 3D residual U-Net respectively. We have conducted the Wilcoxon test for 3D models to correlate the relationship between predicted and actual stroke volume. For reproducibility, the code and model weights are made publicly available: https://github.com/prantik-pdeb/BeSt-LeS.

PaperPDFCode

Code

prantik-pdeb/best-les officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Acute Stroke Lesion SegmentationBenchmarkingLesion Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Acute Stroke Lesion Segmentation ATLAS v2.0 2D U-Net Transformer Dice Score 0.583 #1 of 2 Archive leaderboard report
Acute Stroke Lesion Segmentation ATLAS v2.0 3D Residual U-Net Dice Score 0.504 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections