# Site configuration for auto_detect_breast_mri.
#
#   cp config.example.yaml config.yaml      # config*.yaml is gitignored, this example is not
#   export AIMRI_CONFIG=/absolute/path/to/config.yaml
#
# Every value is optional: command line arguments always take precedence, so a fully specified
# command line needs no config file at all. Keep the real file out of the repository -- it is the
# one place where paths of your own machine or cluster are allowed to appear.

# --- paths -------------------------------------------------------------------------------------
# Root folder of the NIfTI data, i.e. the folder holding one subfolder per examination.
# See README.md ("Data contract") for the two supported folder layouts.
data_root: /path/to/nifti_root

# Metadata export (.csv or .xlsx) with one row per examination and the label columns configured
# under `columns:` below.
metadata_file: /path/to/metadata.csv

# Folder holding the cross validation split files, i.e. the parent of fold0/, fold1/, ...
# Expected file names are documented in README.md ("Split files").
split_root: /path/to/split_files

# Where runs write checkpoints, ROC plots, heatmaps, prediction tables and pickled results.
output_root: /path/to/outputs

# Where already trained checkpoints are read from. Defaults to output_root when unset.
model_root: /path/to/checkpoints

# --- weights & biases --------------------------------------------------------------------------
# Project and (optional) team the runs are logged to. Set wandb_mode to 'offline' to keep runs
# local, or 'disabled' to turn logging off entirely -- useful when running on data that must not
# leave the machine, since run names and captions can contain case identifiers.
wandb_project: my-breast-mri-project
wandb_entity: my-team
wandb_mode: online

# --- CSV column names --------------------------------------------------------------------------
# Names of the columns in your metadata export and split files. Override what differs in your data. Values in the side
# column are matched case insensitively. Unset keys fall back to the defaults in
# auto_detect_breast_mri/config.py (DEFAULT_COLUMNS), which are the original UKA export's names.
#
# tools/make_synthetic_dataset.py reads this block to name the columns of the CSVs it writes and
# copies it into the config it generates, so a renamed column only has to be changed here.
columns:
  examination_id: exam_id           # one MRI examination, in the split CSVs
  metadata_examination_id: exam_id  # the same ID in the metadata export
  patient_id: pat_id                          # patient; splits are grouped by this so that no
                                           # patient appears in two folds
  side: side                               # breast side in the split CSVs
  metadata_side: side                     # breast side in the metadata export
  criterion: Malign                        # training label, one row per breast
  criterion_left: Malign_Left              # per-side label in the wide metadata export
  criterion_right: Malign_Right
  side_left: left                          # the two values found in the side column
  side_right: right
  indication_left: Indication_Left         # per-side indication code in the metadata export
  indication_right: Indication_Right
  birads_left: BIRADS_Left                 # per-side BI-RADS category
  birads_right: BIRADS_Right
  biopsy_left: ""                          # per-side prior biopsy status; leave empty if absent
  biopsy_right: ""                         # (the error analysis then skips its biopsy tables)