Furen Xiao 73234db39e fix(benchmark): lower IMPACT sample-validity gate to unblock M6 runs ... The no-mask CT→T1c FOV mismatch left only ~14% of spatial samples inside the moving buffer at auto-init, below Elastix's default RequiredRatioOfValidSamples of 0.25, so the IMPACT pipeline aborted on every M6 case. Set the gate to 0.1 so the metric's native in-buffer evaluation proceeds while still catching diverging transforms. Switch the default semantic model from TotalSegmentator (TS/M730.pt) to MRSegmentator (MRSeg/MRSeg.pt), a multi-modality MRI+CT model better suited to this cross-modality task. Update docstrings and REGISTRATION_BENCHMARK.md with the new per-case MI results.		2026-09-30 05:57:46 +08:00
..
common.py	feat(registration): align CT to T1c and add benchmarking	2026-09-28 16:20:30 +08:00
dataset.py	feat(train): implement checkpointing and robust data loading	2026-09-26 03:44:12 +08:00
losses.py	feat: initial project structure	2026-09-25 16:00:37 +08:00
registration_pipelines.py	fix(benchmark): lower IMPACT sample-validity gate to unblock M6 runs	2026-09-30 05:57:46 +08:00
training.py	feat(train): implement checkpointing and robust data loading	2026-09-26 03:44:12 +08:00
unet3d.py	feat: initial project structure	2026-09-25 16:00:37 +08:00