The problem — A segmentation mask that merges two touching cells creates one object where two exist; every per-cell feature for that object is a blend of two biological signals. A tracking error that breaks a lineage assigns daughter cells to the wrong mother. These are not downstream problems — they are structural errors baked into the feature table, invisible to any per-feature check.
What it is / how it works — The segment stage covers three related operations, depending on modality. Segmentation partitions an image into per-object masks: nuclei, cell bodies, cytoplasm, organoids, tissue regions. Registration aligns multi-view, multi-tile, or multi-cycle acquisitions into a common coordinate frame (BigStitcher for light-sheet multi-view fusion, ASHLAR or SimpleITK for cyclic-IF in spatial omics). Tracking links per-frame detections into trajectories over time (TrackMate, ultrack, btrack for live-cell; TrackMate for particle tracking). The Cell Tracking Challenge (Ulman et al.) established the canonical benchmark metrics for these tasks — SEG (instance segmentation overlap) and TRA (tracking accuracy weighted by curator effort) — which Fovea uses as the readout-level validation gate per Metrics Reloaded principles.
Where it breaks — Generalist deep-learning segmentation models (Cellpose, StarDist) generalize across stains and magnifications but fail on severely out-of-focus images, extremely dense cultures, and modalities outside their training distribution — which is why Cellpose vs CellProfiler for Nuclei Segmentation carries a per-object confidence requirement: confidence propagated forward lets the features and correction stages weight or exclude uncertain objects rather than treating a bad mask as equivalent to a good one. Tracking compounds the segmentation error: a single missed detection can split a lineage, and that error propagates into every lineage-derived feature.