Radiology · 510(k) · 2024
MSKai
MSKai. Cleared by FDA on 16 December 2024 under submission K240793, product code QIH (automated radiological image processing software). What FDA's record says, in FDA's words.
Device record · K240793
- Device. MSKaiDEVICE
- Company. MSKaiCOMPANY
- Decision. 16 December 2024, 510(k), substantially equivalent (traditional review); received 22 March 2024DECISION
- Panel. RadiologyPANEL
- Product code. QIH, Automated Radiological Image Processing SoftwareCODE
- Regulation. 21 CFR 892.2050, Class IIREG
- Source. FDA database entry · decision document (18 pages)SOURCE
Retrieved · the fields above are FDA's; the statement below was copied from the decision document on that day.
What FDA cleared it for
The Indications for Use statement, verbatim, from the decision document.
MSKai is an image identification, post-processing, measurement, and reporting software tool that provides qualitative viewing and quantitative spine measurements from previously-acquired T2 weighted DICOM lumbar spine Magnetic Resonance Imaging (MRI) images for users' review, evaluation and analysis. It provides the following functionality to assist users in identifying, observing, measuring and reporting measurements: - Anatomy segmentation; - Anatomy labeling; - Anatomy measurement; and - Export of measurement results to a qualitative and quantitative report for user's evaluation, amendment and authorization MSKai does not serve as a diagnostic device by providing or recommending any type of medical diagnosis or treatment. MSKai simply provides users the ability to access objective and repeatable identification, segmentation, measurement and reported measurements of the Lumbar spine. The user is responsible for the indications of preferences and settings, confirming the software generated measurements, and reviewing, confirming and approving draft reports based on their medical training. The device is intended to be used only by physicians, radiologist, hospitals and other medical institutions. Only T2 weighted DICOM images of MRI acquired from lumbar spine exams of patients aged 18 and above are acceptable input. MS Kai does not support DICOM images of patients that are pregnant, have post-operational complications, tumors, infections, or complex hardware.
The product code's definition, from FDA's classification record. To provide automated radiological image processing and analysis tools. Software implementing artificial intelligence including nonadaptive machine learning algorithms trained with clinical and/or artificial data. In these devices, the algorithm training data typically impacts device performance. Adaptive AI algorithms are not within scope of this product code.
What the statement says
Pattern matches on the Indications for Use text. Each line is a fact that the text contains the words, not a finding about the device.
- Modalities namedMRI
- Mentionsdetection or identification of findings
- Mentionsmeasurement or quantification
- Mentionsa diagnostic claim
- Mentionsadult patients
Adverse-event reports in MAUDE, by product code
As of , MAUDE held 10 reports filed against devices carrying product code QIH. That code is shared by every device of this type, not this device alone, and MAUDE reports are submitted by manufacturers, facilities and the public without FDA verification. The latest reports, in the reporter’s words:
2 July 2026 · Malfunction · SYNAPSE PACS · FUJIFILM HEALTHCARE AMERICAS CORPORATION · report 3004972322-2026-00002
ON 06/04/2026, FUJIFILM HEALTHCARE AMERICAS CORPORATION BECAME AWARE OF A BUG IN SYNAPSE PACS V7.4.310 THAT COULD POTENTIALLY LEAD TO A MISDIAGNOSIS IN THE CARDIOLOGY BASED STUDIES. IT WAS FOUND DURING REGRESSION TESTING OF THE PRODUCT THAT THE ANNOTATION TAKEN AND SAVED IN AN EARLIER VERSION OF THE PRODUCT CAN SHOW THE INCORRECT VALUE IN BOTH ZERO VIEWER (ZV) AND VX WHEN REOPENING THE STUDY IN THE NEWER VERSION. THIS ISSUE WAS INTRODUCED INTO THE PRODUCT DURING AN ENHANCEMENT TO SUPPORT […]
9 April 2026 · Malfunction · ORIGIN DATA MANAGEMENT (VERSION 3.2, SOFTWARE COMPONENT) · BRAINLAB SE · report 8043933-2026-00021
A PATIENT RECORD REQUIRED FOR STEREOTACTIC PLANNING COULD NOT BE FOUND DURING A FRAME-BASED STEREOTACTIC BIOPSY FOR A SUSPECTED BRAIN TUMOR. AFTER BRIEF TROUBLESHOOTING, IT BECAME CLEAR THAT THE PATIENT RECORD WAS UNINTENTIONALLY MERGED WITH ANOTHER PATIENT RECORD. THE SURGEON RESOLVED THE MERGE WITH SUPPORT FROM BRAINLAB. FURTHER INVESTIGATION BY BRAINLAB UNCOVERED FOUR MORE CASES OF INCORRECT PATIENT RECORD MERGES AT THE SAME SITE THAT WERE THEREAFTER RESOLVED. ACCORDING TO THE SURGEON […]
26 February 2026 · Malfunction · ORIGIN DATA MANAGEMENT (VERSION 3.2, SOFTWARE COMPONENT) · BRAINLAB SE · report 8043933-2026-00011
WHILE SEARCHING FOR A MISSING PATIENT RECORD IN THE BRAINLAB PATIENT SELECTION 6.1 APPLICATION, A CUSTOMER DISCOVERED THAT THE MISSING PATIENT RECORD HAD BEEN MERGED WITH AN UNRELATED PATIENT RECORD. THE CUSTOMER RESTORED THE MERGED PATIENT RECORD TO ITS ORIGINAL CONSTITUENT PATIENT RECORDS ON THE SAME DAY. AFTER THIS, THE MISSING PATIENT RECORD BECAME AVAILABLE IN THE PATIENT LIST. ACCORDING TO THE HOSPITAL, NO PATIENT WAS AFFECTED DUE TO THE DESCRIBED ISSUE AS NEITHER OF THE PATIENTS HAS HAD […]
13 August 2025 · Malfunction · ORIGIN DATA MANAGEMENT (VERSION 3.2, SOFTWARE COMPONENT) · BRAINLAB AG · report 8043933-2025-00058
A CUSTOMER REPORTED THAT A PATIENT RECORD DID NOT APPEAR IN THE BRAINLAB PATIENT SELECTION APPLICATION WHEN THE PATIENT'S NAME WAS SEARCHED. THE CUSTOMER FOUND THE MISSING PATIENT DATA MERGED INTO A DIFFERENT PATIENT RECORD AND WAS ABLE TO RESTORE THE PATIENT RECORDS TO THEIR ORIGINAL STATES. NO PATIENT WAS AFFECTED DUE TO THIS ISSUE.
25 June 2025 · Malfunction · SONIO DETECT · SONIO · report MW5171987
SONIO DETECT SOFTWARE AI ALGORITHM IS FAULTY AND WRONGLY LABELS FETAL STRUCTURES AND ASSOCIATES THEM WITH THE WRONG BODY PARTS. THE SYSTEM WILL FREQUENTLY DISPLAY AS VISUALIZED EVEN THOUGH IT HASN'T LEAVING PROVIDERS TO GIVE FALSE NORMALCY AND OPENING THEM UP TO LIABILITIES.
Where this fits
This page is a record, not medical advice and not a safety rating. It copies FDA's fields and FDA's statement, and lists what the statement's text mentions. Read the labeling before relying on any of it.
More devices under product code QIH, in Radiology, or cleared in 2024. The whole record is at FDA AI-enabled medical devices.
A device's authorized use is a sentence the record can be read against. What Apodicta does on a medical record is that reading: every line of a note, a claim or a report proved to its source or held, before it renders.