Competition performance metric
Biomarker1 paper2 findings
- In silico1
Upstream
2Thin-slab maximum-intensity projection
downin silico1
1 study
Thin-slab maximum-intensity projection
downin silico1
thin-slab maximum-intensity projection decreases competition performance metric in silico (0.5965 CPM vs 0.6498).
“thin-slab projection (0.5965) was worse than a plain 2D slice”
In silico
Inter-Slice Representation Outweighs Bounding-Box Supervision Extent in Lightweight 2.5D Pulmonary Nodule Detection: A Whole-Volume Benchmark on LUNA16 · Diagnostics (Basel, Switzerland) · 19 Sep 2026
Adjacent-slice 2.5D input
upin silico1
1 study
Adjacent-slice 2.5D input
upin silico1
adjacent-slice 2.5D input increases competition performance metric in silico (+0.1297 CPM (0.7795 vs 0.6498)).
“Adjacent-slice input reached a competition performance metric (CPM) of 0.7795 (95% CI 0.7517-0.8005) against 0.6498 for the 2D baseline”
In silico
Inter-Slice Representation Outweighs Bounding-Box Supervision Extent in Lightweight 2.5D Pulmonary Nodule Detection: A Whole-Volume Benchmark on LUNA16 · Diagnostics (Basel, Switzerland) · 19 Sep 2026