Skip to main content

task

Prefect task for the CST/CRT calculation step (v2).

Consumes two RAW inference caches — retinal-layers segmentation predictions and fovea v7 landmark predictions — plus the scan filter's filenames, and computes per-file Central Subfield Thickness / Central Retinal Thickness, plus the EZ-integrity measurement on the fovea-reference B-scan.

Identical to v1 but for the EZ block: it takes exactly the two inputs the EZ measurement needs, already parses the fovea centre, and already builds the boundary grid the measurement reads. Hosting it here rather than in a new step saves the cache table, the step package, and every line of tabulation plumbing — cst_metrics is already an input to biomarker_tabulation and the built frame is driven by CSTMetrics.expected_cols(), so the new columns flow with no wiring change.

The table is unchanged (cst_calculation, version 1). What moves is the task_hash: it is a Merkle hash over the step's version and semantic config, so v2 lands in a fresh partition and every existing CST/CRT value is recomputed. That recompute is thickness maths over already-cached layer inferences, not GPU re-inference — the model_inferences cache is upstream and keyed by (model_ref, model_version). Rollback is pinning a template back to v1, whose partition survives untouched.

Delegates the per-file orchestration to the shared run_thickness_calculation runner (which GCC reuses unchanged) and the metric maths to compute_cst_metrics_for_scan.

Runs in background mode: an in-memory result does not cross the phase boundary, so the per-file metrics are persisted to the cst_calculation cache table (keyed by (task_hash, file_id), project_id provenance-only) and a downstream step reads them via the cst_calculation.cache accessor.

Module​

Functions​

cst_calculation_task_v2​

def cst_calculation_task_v2(    datasource: BaseSource,    config: CSTCalculationConfigV2,    layer_predictions: CacheAccessor,    center_predictions: CacheAccessor,    filenames: list[str],    cache: CacheProtocol,    task_hash: str,    project_id: str | None = None,    run_id: str | None = None,) ‑> CSTCalculationResult:

Compute CST/CRT metrics for each file and persist them to cache.

Arguments

  • datasource: The datasource providing DICOM metadata (slice thickness, pixel spacing row/column) for each file.
  • config: CST calculation configuration, including the EZ-integrity layer pair and threshold.
  • layer_predictions: Cache accessor for retinal-layers model inference results (background step retinal_layers_inference.cache).
  • center_predictions: Cache accessor for fovea model inference results (background step fovea_inference.cache).
  • filenames: List of file IDs to process.
  • cache: Cache instance to persist the CST metrics into.
  • task_hash: Partition key for the cst_calculation table; a config change lands in a fresh partition.
  • project_id: Provenance only — the project that triggered this run. NOT part of the cache key: rows are keyed by (task_hash, file_id) so two projects on the same datasource share them.
  • run_id: Optional provenance run ID.

Returns CSTCalculationResult carrying the number of rows persisted and a CacheAccessor scoped to this task_hash (cst_calculation.cache).