Codesota · Models · SAM-Med3DUniversity Medical Center Hamburg-Eppendorf et al.1 results · 1 benchmarks
Model card

SAM-Med3D.

University Medical Center Hamburg-Eppendorf et al.open-source387M paramsSAM adapted for 3D volumes

Segment Anything Model extended to 3D volumetric medical images. Trained on 21K segmentation masks.

§ 01 · Benchmarks

Every benchmark SAM-Med3D has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01BTCVMedical · Medical Image Segmentationmean-dsc78.9%#5/62023-08-30source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area

Where SAM-Med3D actually performs.

Medical
1
benchmark
avg rank #5.0
§ 03 · Papers

1 paper with results for SAM-Med3D.

  1. 2023-08-30· Medical· 1 result

    SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images

§ 05 · Sources & freshness

Where these numbers come from.

arxiv
1
result
1 of 1 rows marked verified.