Search Results

Registration and Fusion (Basic and Extended) is indicated for the simultaneous visualization of multiple medical images of the same patient. The application can assist the user in visually matching and comparing anatomical studies taken at different times or acquired via different imaging modalities (Basic: CT-CT, CT-MR, MR-MR, Extended: CT-PET, MR-PET) as well as assist in making measurements. It is primarily used in the fields of diagnostic radiology, neurology and oncology.

Medical Data Registration and Fusion R 1.0 is a PACS plug-in (accessory). It is an image analysis software package that establishes the geometrical relationship between different DICOM 3.0 compliant 3-D medical data sets from PET, MR and CT imaging (registration"). The matched images are displayed (fusion') by either the use of semitransparent overlays or by displaying them side-by-side. Registration and fusion facilitates the comparison of PET/CT, PET/MRI, CT/CT, MRI/MRI, CT/MRI image data sets for use in: The general radiology department for various lesions. The oncology department for various cancerous lesions. The neurology department for various lesions. The rigid registration used in the application, aims to help the clinician navigate to the same anatomical location in both image sets. The Medical Data Registration and Fusion software runs on Agfa's PACS workstations (Impax 5.3 and 6.3 workstations).

The provided 510(k) summary for Agfa's Registration and Fusion software does not contain specific acceptance criteria or a detailed study proving the device meets those criteria in the way typically expected for a medical AI/CAD device.

Instead, this submission focuses on demonstrating substantial equivalence to a predicate device (Mirage 5.5, K043441) by highlighting similar indications, intended use, and technological characteristics. The "Testing" section is extremely brief and only states: "Registration and Fusion has been tested for compatibility with Agfa's Impax® PACS Systems." This implies functional testing and integration testing, rather than a clinical performance study with predefined acceptance criteria.

The information sought in your request (sample sizes, expert qualifications, adjudication methods, MRMC studies, standalone performance, ground truth types and establishment for training sets) is not present in this 510(k) summary. This is common for devices like PACS accessories that primarily provide visualization and registration tools, where the safety and effectiveness are often derived from the predicate device and the basic functionality of the software.

Therefore, I cannot populate the table or answer the specific questions as the required information is not disclosed in the provided document.

Summary of available information regarding acceptance criteria and study:

The document states:

• Acceptance Criteria: Not explicitly defined or listed in terms of clinical performance metrics (e.g., sensitivity, specificity, accuracy). The implicit acceptance criteria revolve around functional compatibility with Agfa PACS systems and achieving substantial equivalence to the predicate device in terms of intended use and technological characteristics.
• Study Proving Acceptance: The document mentions "testing for compatibility with Agfa's Impax® PACS Systems." This suggests internal functional and integration testing, but not a formal clinical performance study with human readers, ground truth, or statistical analysis of diagnostic accuracy.

Regarding the specific questions you asked:

1. A table of acceptance criteria and the reported device performance:

   • Acceptance Criteria: Not explicitly stated.
   • Reported Device Performance: Not reported in terms of clinical metrics. The performance described is functional (image registration and fusion capabilities).

2. Sample sizes used for the test set and the data provenance: Not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided, as a formal test set with expert-established ground truth for diagnostic performance is not described.

4. Adjudication method for the test set: Not provided.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not done/not reported. This device is a visualization and registration tool, not an AI/CAD system designed to directly improve diagnostic accuracy in that manner.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not done/not reported for diagnostic performance. The device's function (registration and fusion) is inherently an assist to a human user.

7. The type of ground truth used: Not provided.

8. The sample size for the training set: Not applicable/not provided. This device is not described as an AI/machine learning system that requires a training set in the typical sense. It performs rule-based image registration and fusion.

9. How the ground truth for the training set was established: Not applicable/not provided.

Ask a specific question about this device