Furen Xiao 8c083abe92 feat(benchmark): switch to per-toolkit native init and full-volume registration ... Replace the shared CT head-box resampling and manual centroid pre-shift with each toolkit's native automatic transform initialization (elastix/impact use CenterOfGravity, antspyx uses center-of-mass, simpleitk uses identity). All pipelines now register on the full volumes instead of a cropped head box. Drop the _ct_head_box_mm helper and update the benchmark table to document per-toolkit init methods in a dedicated "init" column.		2026-09-29 07:43:27 +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	feat(benchmark): switch to per-toolkit native init and full-volume registration	2026-09-29 07:43:27 +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