xfr/longitudinal
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
longitudinal/scripts
History
Furen Xiao a65189cd33 feat(pipelines): integrate niftyreg and adopt Mattes MI as the benchmark headline score 
Add `register_niftyreg` as the sixth rigid CT→T1c pipeline using
`reg_aladin` (symmetric block matching + trimmed least squares, NCC
similarity). Runs natively via `conda install -c conda-forge niftyreg`;
no Docker required.

Change the benchmark's primary reported metric from geometric skull-ring
QA to the achieved Mattes MI (`mi_ct_mr`, nats) between the warped CT
and the original MR over the MR head. Geometric QA fields are still
recorded per case in the JSON output.

Raise the SimpleITK benchmark-mode optimizer budget from 150 to 2000
iterations per pyramid level so all toolkits are compared on an equal
iteration footing.

Update `REGISTRATION_BENCHMARK.md` (five→six pipelines, niftyreg row,
elastix bin count 10→32), `AGENTS.md` (toolkit list), and
`bench_registration.py` docstrings/usage accordingly.
2026-09-29 09:47:28 +08:00
..
01_build_ntuh_manifest.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00
02_build_m6_dataset.py feat(registration): align CT to T1c and add benchmarking 2026-09-28 16:20:30 +08:00
03_scan_lee_t1c.py fix(t1c): exclude TOF MRA and subtraction series 2026-09-27 18:45:09 +08:00
04_reconstruct_lee.py fix(lee): exclude SSFP sequences and enhance T1c exclusion notes 2026-09-27 15:29:02 +08:00
05_build_splits.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00
06_pseudo_label.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00
07_train.py feat: initial project structure 2026-09-25 16:00:37 +08:00
08_eval.py feat: initial project structure 2026-09-25 16:00:37 +08:00
09_run_iterative.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00
bench_registration.py feat(pipelines): integrate niftyreg and adopt Mattes MI as the benchmark headline score 2026-09-29 09:47:28 +08:00
benchmark_pipelines.py fix(docs): update conda environment name to longitudinal-313 and Python version to 3.13 2026-09-28 21:01:45 +08:00
make_screenshots.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00
preprocess.py feat(registration): align CT to T1c and add benchmarking 2026-09-28 16:20:30 +08:00
scan_procs.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00
test_dataloader.py feat: refactor path handling and add configuration for external data directories 2026-09-27 10:17:33 +08:00