No description
Find a file
Xiao Furen 0a928d8f8e refactor(imaging): update coordinate transformation logic to use transform.json
Update the coordinate transformation pipeline to prioritize the affine
transformation chain recorded in `transform.json` (original_to_source)
instead of relying on re-calculated geometric parameters.

The previous method relied on re-estimating rotation, center, and
bounding boxes from the bone mask, which led to inaccuracies in screw
pillar mapping (e.g., dropping from 99% to 30-94% in-label accuracy).
The new approach uses the precise inverse affine mapping `o = M^-1 (s - t)`
from the transformation metadata.

A fallback mechanism is maintained for legacy volumes lacking
`transform.json`, which continues to use the re-calculation method.

- Implement `load_transform` and `original_to_source` integration
- Update documentation to reflect the new primary/fallback coordinate chains
- Improve precision of screw parameter mapping to native index space
2026-09-09 19:08:52 +08:00
.kilo/agents refactor(core): improve cylinder parameter snapping and optimization logic 2026-08-26 22:36:07 +08:00
.vscode refactor(core): improve cylinder parameter snapping and optimization logic 2026-08-26 22:36:07 +08:00
config refactor(imaging): improve orientation detection and segmentation robustness 2026-09-07 18:46:06 +08:00
core refactor(imaging): improve orientation detection and segmentation robustness 2026-09-07 18:46:06 +08:00
imaging feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
references refactor(core): remove global state and implement OptimizationContext 2026-08-30 00:54:55 +08:00
results first commit 2026-04-10 13:25:27 +08:00
utils refactor(imaging): improve orientation detection and segmentation robustness 2026-09-07 18:46:06 +08:00
visualization feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
.gitignore feat(core): implement vertebral body rewards and enhanced segmentation logic 2026-09-05 04:30:10 +08:00
__init__.py first commit 2026-04-10 13:25:27 +08:00
experiment.ipynb first commit 2026-04-10 13:25:27 +08:00
optimization_benchmark_results_DE.csv first commit 2026-04-10 13:25:27 +08:00
optimization_benchmark_results_NM.csv first commit 2026-04-10 13:25:27 +08:00
optimization_benchmark_results_PSO.csv first commit 2026-04-10 13:25:27 +08:00
progress.json refactor(core): improve cylinder parameter snapping and optimization logic 2026-08-26 22:36:07 +08:00
run_all_cases.py first commit 2026-04-10 13:25:27 +08:00
run_benchmark.py first commit 2026-04-10 13:25:27 +08:00
run_de.py first commit 2026-04-10 13:25:27 +08:00
run_pso.py first commit 2026-04-10 13:25:27 +08:00
structure.txt first commit 2026-04-10 13:25:27 +08:00
xfr_cbt_native.py refactor(imaging): update coordinate transformation logic to use transform.json 2026-09-09 19:08:52 +08:00
xfr_check_spinous.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_debug.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_inverse_transform.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_migrate_crop.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_orig_labels.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_plot_level.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_preprocess.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00
xfr_reprocess_ap.py feat(imaging): implement coordinate transformation pipeline and directory restructuring 2026-09-09 13:39:47 +08:00