DeepCatch

K223556

MEDICALIP Co., Ltd · cleared 2023-06-16 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.3)

“DeepCatch analyzes CT images and auto-segments anatomical structures (skin, bone, muscle, visceral fat, subcutaneous fat, internal organs and central nervous system). Then, its volume and proportions are calculated and provided with the relevant 3D model.”

Algorithmanalyzes CT images and auto-segments anatomical structures (skin, bone, muscle, visceral fat, subcutaneous fat, internal organs and central nervous system). Then, its volume and proportions are calculated and provided with the relevant 3D model.

source quote (p.3)

“DeepCatch analyzes CT images and auto-segments anatomical structures (skin, bone, muscle, visceral fat, subcutaneous fat, internal organs and central nervous system). Then, its volume and proportions are calculated and provided with the relevant 3D model.”

Adaptive (vs locked)FDA source did not state this

PCCPNo

Cybersecurity addressedYes

source quote (p.11)

“"Content of Premarket Submission for Management of Cybersecurity in Medical Devices.", on October2, 2014”

Validation studies (5)

Retrospective clinical

n=100 cases

endpoints: DSC; Volume; Area; Ratio; Body Circumference

Retrospective clinical

n=580 cases

endpoints: DSC; Volume; Area; Ratio; Body Circumference

Retrospective clinical

n=167 images · 1 site(s)

endpoints: DSC; volume; area; ratio; abdominal circumference

Reader study (MRMC)

n=100 images

endpoints: automatic segmentation accuracy; DSC values

Reader study (MRMC)

n=100 images

endpoints: accuracy of the volume and proportion calculations of the body circumference, SF and AVF; volume; ratio; area; body circumference

Reported performance (3 observations)

diceas written: “DSC mean (Internal Datasets)”0.9

source quote (p.10)

“In the internal datasets test, DSC means of GT and segmentation results of DeepCatch shows greater than or equal to 90%.”

diceas written: “DSC mean (External Datasets)”0.9

source quote (p.10)

“In the external data sets test, the DSC mean of GT and segmentation results of DeepCatch in all areas is more than 90%”

diceas written: “DSC mean (US-based)”0.9

source quote (p.10)

“for all anatomical structures, DSC mean was more than 90%”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). 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).