ART-Plan+ (v.3.0.0)

K242822

Therapanacea SAS · cleared 2025-02-25 · product code MUJ · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.6)
“ART-Plan+ is a software platform allowing contour regions of interest on 3D images and to provide an automatic treatment plan.”
Algorithmdeep-learning based automatic segmentation
source quote (p.6)
“ART-Plan+ offers deep-learning based automatic segmentation of OARs and LNs for the following localizations: ... Deep learning algorithm.”
Adaptive (vs locked)FDA source did not state this
PCCPNo
Cybersecurity addressedNo

Validation studies (7)

Retrospective clinical

n=24 patients

endpoints: Mean DSC should not regress negatively between the current and last validated version of Annotate beyond a maximum tolerance margin set to -5% relative error.

Retrospective clinical

n=18 patients

endpoints: The clinicians' qualitative evaluation of the auto-segmentation is considered acceptable for clinical use without modifications (A) or with minor modifications / corrections (B) with a A+B % above or equal to 85% considering the following scale: A. the contour is acceptable for a clinical use without any modification B. the contour would be acceptable for clinical use after minor modifications/corrections C. the contour requires major modifications (e.g. it would be faster for the expert to manually delineate the structure)

Retrospective clinical

n=24 patients

endpoints: Mean DSC (annotate) ≥ 0.8

Reader study (MRMC)

n=13 patients

endpoints: Mean DSC (annotate) ≥ Mean DSC (inter-expert) with a tolerance margin of -5% of relative error

Retrospective clinical

n=51 patients

endpoints: The lesion-wise sensitivity is equal to or superior to state-of-the-art as benchmark: mean lesion-wise sensitivity ≥ 0.86; The lesion-wise precision is equal to or superior to state-of-the-art as benchmark: mean lesion-wise precision ≥ 0.70; The lesion-wise DSC similarity coefficient (DSC) is equal to or superior to state-of-the-art as benchmark: mean lesion-wise DSC ≥ 0.78; The patient-wise DSC similarity coefficient (DSC) is equal to or superior to state-of-the-art as benchmark: mean patient-wise DSC ≥ 0.83; The patient-wise false positive (FP) is equal to or superior to state-of-the-art as benchmark: mean patient-wise FP ≤ 2.1

Retrospective clinical

n=43 patients

endpoints: The sensitivity is equal to or superior to state-of-the-art as benchmark: mean sensitivity ≥ 0.80; The DSC is equal to or superior to state-of-the-art as benchmark: mean DSC ≥ 0.76

Retrospective clinical

n=20 patients

endpoints: effectiveness difference (%) in DVH achieved goals between manual plans and automatic plans ≤ 5%; % of clinical acceptable automatic plans ≥ 93% after expert review.

Reported performance (5 observations)

sensitivity0.86
source quote (p.10)
“The lesion-wise sensitivity is equal to or superior to state-of-the-art as benchmark: mean lesion-wise sensitivity ≥ 0.86”
ppvas written: “lesion-wise precision”0.7
source quote (p.10)
“The lesion-wise precision is equal to or superior to state-of-the-art as benchmark: mean lesion-wise precision ≥ 0.70”
diceas written: “lesion-wise DSC similarity coefficient”0.78
source quote (p.10)
“The lesion-wise DSC similarity coefficient (DSC) is equal to or superior to state-of-the-art as benchmark: mean lesion-wise DSC ≥ 0.78”
diceas written: “patient-wise DSC similarity coefficient”0.83
source quote (p.10)
“The patient-wise DSC similarity coefficient (DSC) is equal to or superior to state-of-the-art as benchmark: mean patient-wise DSC ≥ 0.83”
diceas written: “DSC (Glioblastoma)”0.76
source quote (p.10)
“The DSC is equal to or superior to state-of-the-art as benchmark: mean DSC ≥ 0.76”

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

35
recalls in product code, 24mo
17
MAUDE reports in code, 12mo
-50%
vs code's own 3-yr baseline
3
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K253091 (decision 2025-12-23) from Therapanacea Sas for a matching device line ("ART-Plan+ (v3.1.0)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K253091

  • recall_reason_pattern

    Software/algorithm-related recall in product code MUJ (Philips Medical Systems (Cleveland) Inc, initiated 2025-08-05): "Due to a software issue, there is a potential image error of the Region of Interest for expansion/contraction for HFP (Head First Prone), FFS (Feet First Supine) and FFP (Feet Firs" Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97049

  • recall_reason_pattern

    Software/algorithm-related recall in product code MUJ (Philips Medical Systems (Cleveland) Inc, initiated 2025-07-17): "Due to software issue, Radiation Therapy Planning system may provide incorrect dataset calculations when performing the "Stopping Power Ratio" (SPR) ," Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97309

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 Radiology 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/K242822