CellaVision DC-1, CellaVision DC-1 PPA

K200595

CellaVision AB · cleared 2020-10-16 · product code JOY · Hematology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.5)
“The CellaVision® DC-1 consists of a built-in PC with a Solid-State Disc (SSD) containing CellaVision DM Software (CDMS), a high-power magnification microscope with a LED illumination, an XY stage, a proprietary camera with firmware, built-in motor- and illumination LED controller, a casing and an external power supply. It is capable of handling one slide at a time. The CellaVision® DC-1 can preclassify WBCs and precharacterize RBCs by use of artificial intelligence. For the CellaVision® DC-1 Convolutional Neural Networks (CNN) are used instead of ANN.”
AlgorithmConvolutional Neural Networks (CNN) and artificial intelligence
source quote (p.5)
“The CellaVision® DC-1 can preclassify WBCs and precharacterize RBCs by use of artificial intelligence. For the CellaVision® DC-1 Convolutional Neural Networks (CNN) are used instead of ANN. Cell images are analyzed using artificial intelligence trained to distinguish between classes of white blood cells. Neural network of convolutional type.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedNo

Validation studies (9)

Retrospective clinical

n=5 patients · 3 site(s)

standards: CLSI EP05-A3 (Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline – Third Edition)

Retrospective clinical

n=5 patients · 3 site(s)

Retrospective clinical

n=4 patients · 3 site(s)

Retrospective clinical

n=5 patients · 3 site(s)

standards: CLSI EP05-A3 (Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline - Third Edition)

Retrospective clinical

n=4 patients · 3 site(s)

Retrospective clinical

n=4 patients · 3 site(s)

Retrospective clinical

n=598 patients · 3 site(s)

endpoints: Accuracy; Positive (PPA); Negative (NPA); Overall Agreement (OA)

standards: CLSI H20-A2 (RBC, only applicable parts)

Retrospective clinical

n=586 patients · 3 site(s)

endpoints: Positive (PPA); Negative (NPA); Overall Agreement (OA)

standards: CLSI H20-A2 (RBC, only applicable parts)

Retrospective clinical

n=598 patients · 3 site(s)

endpoints: Cohen's Kappa coefficient

Reported performance (11 observations)

agreement_kappaas written: “Positive Percent Agreement (Distribution)”89.2
source quote (p.15)
“PPA 89,2%”
agreement_kappaas written: “Negative Percent Agreement (Distribution)”90.4
source quote (p.15)
“NPA 90,4%”
agreement_kappaas written: “Positive Percent Agreement (Morphology)”88.6
source quote (p.15)
“PPA 88,6%”
agreement_kappaas written: “Negative Percent Agreement (Morphology)”92.5
source quote (p.15)
“NPA 92,5%”
agreement_kappaas written: “Positive Percent Agreement (RBC Color)”87.8CI 82.3%-91.8%
source quote (p.15)
“87,8% (82,3%-91,8%)”
agreement_kappaas written: “Negative Percent Agreement (RBC Color)”76.3CI 71.9%-80.2%
source quote (p.15)
“76,3% (71,9%-80,2%)”
agreement_kappaas written: “Positive Percent Agreement (RBC Size)”89.8CI 86.3%-92.2%
source quote (p.15)
“89,8% (86,3%-92,2%)”
agreement_kappaas written: “Negative Percent Agreement (RBC Size)”84.8CI 79.0%-89.2%
source quote (p.15)
“84,8% (79,0%-89,2%)”
agreement_kappaas written: “Positive Percent Agreement (RBC Shape)”87.3CI 82.3%-91.0%
source quote (p.16)
“87,3% (82,3%-91,0%)”
agreement_kappaas written: “Negative Percent Agreement (RBC Shape)”83.8CI 79.6%-87.3%
source quote (p.16)
“83,8% (79,6%-87,3%)”
agreement_kappaas written: “Weighted Kappa (PLT)”0.89405CI 0.87062 to 0.91748
source quote (p.16)
“Weighted Kappa* 0,89405 Standard error 0,01196 95% CI 0,87062 to 0,91748”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

1
recalls in product code, 24mo
1
MAUDE reports in code, 12mo
-40%
vs code's own 3-yr baseline
1
drift signals on this device
  • recall_reason_pattern

    Software/algorithm-related recall in product code JOY (Cellavision AB Forskningsbyn Ideon Scheelevagen 19a Lund Sweden, initiated 2025-10-08): "Automated cell-locating device barcode reader may read the barcode of the previously processed slide resulting in a misattribution of diagnostic results." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97835

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Hematology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K200595