(200 days)
The intended use of the device YSIO X.pree is to visualize anatomical structures of human beings by converting an X-ray pattern into a visible image.
The device is a digital X-ray system to generate X-ray images from the whole body including the skull, chest, abdomen, and extremities. The acquired images support medical professionals to make diagnostic and/or therapeutic decisions.
YSIO X.pree is not for mammography examinations.
The YSIO X.pree is a radiography X-ray system. It is designed as a modular system with components such as a ceiling suspension with an X-ray tube, Bucky wall stand, Bucky table, X-ray generator, portable wireless, and fixed integrated detectors that may be combined into different configurations to meet specific customer needs.
The following modifications have been made to the cleared predicate device:
- -New Camera Model in Collimator
- -New Auto Collimation Function: Auto Long-Leg/Full-Spine
- -Two new wireless detectors
The provided text is a 510(k) summary for the YSIO X.pree X-ray system. It describes the device, its intended use, and comparisons to predicate and reference devices. However, it does not contain the detailed clinical study information typically required to directly answer all aspects of your request regarding acceptance criteria and performance metrics for an AI/CADe device.
Specifically, the document mentions:
- A "Customer Use Test (CUT)" was performed at the "Universitätsklinikum Augsburg, Germany," focusing on "System function and performance-related clinical workflow, Image quality, Ease of use, Overall performance and stability."
- "The results of the clinical test stated that the intended use of the system was met, and the clinical need covered."
- "All images acquired with the new detectors were sufficiently acceptable for radiographic usage."
This summary indicates that new features, particularly the "Auto Collimation Function: Auto Long-Leg/Full-Spine" which is AI-based (taken from the MULTIX Impact algorithm, K213700), underwent testing. However, the FDA 510(k) summary does not include the specific acceptance criteria with reported performance against those criteria, nor detailed information about the study design (sample size, ground truth establishment, expert qualifications, etc.) for the AI-based auto collimation feature. The "Customer Use Test" appears to be a general usability and performance test for the overall system and new detectors, rather than a rigorous performance study for an AI algorithm with specific quantitative metrics.
Therefore, I cannot fully complete the table and answer all questions with the provided text. I can only extract what is present.
Here's a breakdown of what can be extracted and what cannot:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not provide a table of explicit acceptance criteria for the AI-based auto collimation function with corresponding quantitative performance metrics (e.g., accuracy, precision for delimiting regions of interest). It only states that the overall system and new detectors' images were "sufficiently acceptable for radiographic usage" and that the "intended use of the system was met, and the clinical need covered."
| Acceptance Criteria | Reported Device Performance |
|---|---|
| For overall system and new detectors (from Customer Use Test): | |
| System function and performance-related clinical workflow met criteria | Intended use of the system was met, and the clinical need covered. |
| Image quality acceptable | All images acquired with the new detectors were sufficiently acceptable for radiographic usage. |
| Ease of use acceptable | Not explicitly quantified, but implied by overall "intended use met." |
| Overall performance and stability acceptable | Not explicitly quantified, but implied by overall "intended use met." |
| For AI-based Auto Collimation (Auto Long-Leg/Full-Spine): | Information Not Provided in Text |
2. Sample size used for the test set and the data provenance:
- Test set sample size for AI-based auto collimation: Not specified in the provided text.
- Data Provenance: The Customer Use Test (CUT) was performed at "Universitätsklinikum Augsburg, Germany." This suggests prospective data collection in a clinical setting in Germany for the general system and new detectors. It is not explicitly stated if the AI-based auto collimation performance was evaluated on this specific dataset, or if a separate dataset (and its provenance) was used for validating the AI. Given the AI algorithm was "taken over" from the MULTIX Impact (K213700) and that previous 510(k) for that device might contain more details.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not specified for any specific ground truth establishment (especially for the AI-based auto collimation). The "Customer Use Test" involved clinical evaluation, implying healthcare professionals (presumably radiologists or radiographers) were involved, but their number and specific qualifications for establishing ground truth for AI performance are not detailed.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not specified.
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:
- No MRMC comparative effectiveness study is described for the AI-based auto collimation. The document focuses on device safety and substantial equivalence to a predicate, not enhancement of human reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not explicitly detailed. The AI auto collimation feature is integrated into the workflow, implying it assists, but a standalone technical performance study for the AI component itself is not described with quantitative results. The statement that the "Multix Impact algorithm has been taken over" suggests that its performance characteristics might have been established during the clearance of the MULTIX Impact (K213700), but those details are not in this document.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not specified for the AI-based auto collimation. For the general system usability and image quality, the "Customer Use Test" implies a clinical assessment, likely representing expert (clinician) judgment.
8. The sample size for the training set:
- Not specified. The document states that the AI algorithm was "taken over" from the MULTIX Impact. This implies the training was done previously for the MULTIX Impact, but the size of that training set is not provided here.
9. How the ground truth for the training set was established:
- Not specified, for the same reasons as in point 8.
§ 892.1680 Stationary x-ray system.
(a)
Identification. A stationary x-ray system is a permanently installed diagnostic system intended to generate and control x-rays for examination of various anatomical regions. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A radiographic contrast tray or radiology diagnostic kit intended for use with a stationary x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.