Radiology · 510(k) · 2025

TAIMedImg DeepMets

Taiwan Medical Imaging Co., Ltd.. Cleared by FDA on 28 May 2025 under submission K250427, product code QKB (radiological image processing software for radiation therapy). What FDA's record says, in FDA's words.

Device record · K250427

  1. Device. TAIMedImg DeepMetsDEVICE
  2. Company. Taiwan Medical Imaging Co., Ltd. (TW)COMPANY
  3. Decision. 28 May 2025, 510(k), substantially equivalent (traditional review); received 14 February 2025DECISION
  4. Panel. RadiologyPANEL
  5. Product code. QKB, Radiological Image Processing Software For Radiation TherapyCODE
  6. Regulation. 21 CFR 892.2050, Class IIREG
  7. Source. FDA database entry · decision document (12 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.

TAIMedImg DeepMets is a software device intended to assist trained medical professionals by providing initial object contours on axial T1-weighted contrast- enhanced (T1WI+C) brain magnetic resonance (MR) images to accelerate workflow for radiation therapy treatment planning. TAIMedImg DeepMets is intended only for patients with known (imaging diagnosed) brain metastases (BM) when cancer cells spread from primary site to the brain. It is not intended to be used with images of other brain tumors or other body parts. The software is intended for use with BM lesions with a diameter of ≥10 mm. TAIMedImg DeepMets uses an artificial intelligence algorithm to contour images and offers automated segmentation for Gross Tumor Volume (GTV) contours of brain metastases. The software is an adjunctive tool and not intended for replacing the users’ current standard practice of manual contouring process. All automatic output generated by the software shall be thoroughly reviewed by a trained medical professional prior to delivering any therapy or treatment. The physician retains the ultimate responsibility for making the final diagnosis and treatment decision. TAIMedImg DeepMets is intended to be used by medical professionals trained in the use of the device. Only DICOM images of adult patients are considered valid input. DeepMets does not support DICOM images of patients that have one of the following exclusions: (i) presence of prior craniotomy, (ii) patients with clinical imaging […]

K250427, FDA decision document · source

The product code's definition, from FDA's classification record. To provide semi-automatic or fully-automated radiological image processing and analysis tools for radiation therapy. Software implementing artificial intelligence (AI) including nonadaptive machine learning algorithms trained with clinical and/or artificial radiological images. In these devices, the algorithm training images typically impact device performance. AI based radiological image processing software is intended to be used in the workflow of radiation therapy. Adaptive AI algorithms are not within the scope of this product code. Primary radiation dose calculation or plan optimization for treatment planning 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.

Adverse-event reports in MAUDE, by product code

As of , MAUDE held 0 reports filed against devices carrying product code QKB. 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.

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 QKB, in Radiology, or cleared in 2025. 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.

Show me on one of my files →

This device is authorized for a stated use. See a record read against what it must prove, on your own file.

Show me on my files