Cleared Special

K203822 - ProFound AI Software V3.0 (FDA 510(k) Clearance)

Class II Radiology device cleared through the Special 510(k) pathway - typically does not require clinical trials.

K203822 · Icad, Inc. · Radiology device
Download Printable Device Report (PDF)
Optimized for regulatory review, auditing and printing
Mar 2021
Decision
73d
Days
Class 2
Risk

K203822 is an FDA 510(k) clearance for the ProFound AI Software V3.0. Classified as Radiological Computer Assisted Detection/diagnosis Software For Lesions Suspicious For Cancer (product code QDQ), Class II - Special Controls.

Submitted by Icad, Inc. (Nashua, US). The FDA issued a Cleared decision on March 12, 2021 after a review of 73 days - a notably fast clearance cycle.

This device falls under the Radiology FDA review panel, regulated under 21 CFR 892.2090 - the FDA radiology and imaging software oversight framework. As a Special 510(k), this submission covers a manufacturer modification to an existing cleared device rather than a new device introduction.

Device pattern: Incremental AI imaging tool. Low regulatory complexity profile. Overall, this clearance reflects a predicate-aligned approval typical of modern AI radiology extensions - not a novel clinical breakthrough, but a validated iteration within an established regulatory category.

View all Icad, Inc. devices

Submission Details

510(k) Number K203822 FDA.gov
FDA Decision Cleared Substantially Equivalent - Traditional 510(k) (SESE)
Date Received December 29, 2020
Decision Date March 12, 2021
Days to Decision 73 days
Submission Type Special
Review Panel Radiology (RA)
Summary Summary PDF
Third-party Review No - reviewed directly by FDA
Combination Product No
PCCP Authorized No
Regulatory Context
Review time vs. panel average
34d faster than avg
Panel avg: 107d · This submission: 73d
Pathway characteristics
Modification to existing cleared device.

Device Classification

Product Code QDQ Radiological Computer Assisted Detection/diagnosis Software For Lesions Suspicious For Cancer
Device Class Class 2 - Special Controls
CFR Regulation 21 CFR 892.2090
Definition A Radiological Computer Assisted Detection And Diagnostic Software For Suspected Lesions Is An Image Processing Device Intended To Aid In The Detection, Localization, And Characterization Of Lesions Suspicious For Cancer On Acquired Medical Images (e.g., Mammography , Mr, Ct, Ultrasound, Radiography). The Device Detects, Identifies And Characterizes Lesions Suspicious For Cancer Based On Features Or Information Extracted From The Images, And May Provide Information About The Presence, Location, And Characteristics Of The Lesion To The User. Primary Diagnostic And Patient Management Decisions Are Made By The Clinical User.
What this classification means

Class II devices require demonstration of substantial equivalence to a legally marketed predicate device. This pathway does not require clinical trials - it relies on engineering equivalence and performance data. Most Radiology devices follow this clearance model.

Regulatory Peers - QDQ Radiological Computer Assisted Detection/diagnosis Software For Lesions Suspicious For Cancer

All 33
Devices cleared under the same product code (QDQ) and FDA review panel - the closest regulatory comparables to K203822.
DeepHealth ProstateAI
K253682 · Quantib B.V. · Apr 2026
Lunit INSIGHT MMG (v1.1.10)
K260320 · Lunit, Inc. · Apr 2026
Lunit INSIGHT DBT (V1.2)
K253796 · Lunit, Inc. · Mar 2026
Median LCS (internal name) / eyonis LCS (trade name) (1.0)
K251474 · Median Technologies · Feb 2026
Saige-Dx
K251873 · DeepHealth, Inc. · Aug 2025
Genius AI Detection 2.0
K243341 · Hologic, Inc. · Jul 2025