(237 days)
EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, angiography, and mammography.
EOSedge allows the radiographic acquisition of either one or two orthogonal X-ray images, for diagnostic purposes, in one single scan of the whole body or a reduced area of investigation of a patient, in the upright or seated position. The Micro Dose feature is indicated for assessing global skeletal deformities in follow-up pediatric exams.
The EOSedge™ system is a digital radiography system comprised of an acquisition workstation, a gantry including an electrical cabinet housing the system power and communication controls, and an acquisition software to obtain diagnostic images. Two sets of detectors and X-ray tubes are positioned orthogonally to generate frontal and lateral images simultaneously by scanning the patient over the area of interest. If desired, the Micro Dose feature enables image acquisition for assessing global skeletal deformities in pediatric follow-up exams.
The diagnostic images are stored in a local database and are displayed on a high-resolution medical-quality non-diagnostic monitor. The diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.
The provided text outlines the substantial equivalence of the EOSedge device to its predicate, rather than detailing a specific clinical study with AI assistance demonstrating performance against acceptance criteria for an AI/ML powered device. The document describes changes to an existing, cleared device (EOSedge, K202394), primarily the activation of a dual-energy detection mode within already integrated detectors.
Therefore, the information required to fully answer the question regarding acceptance criteria and a study proving a device meets these criteria for an AI/ML powered device is largely not present in the provided text. The document focuses on showing the modified EOSedge is substantially equivalent to the cleared EOSedge system, implying that the previous clearances and tests are sufficient.
However, based on the provided text, I can infer and extract some relevant (though limited) information regarding performance testing that aligns with aspects of an AI/ML device, particularly concerning image quality and software:
Acceptance Criteria and Reported Device Performance (Inferred from "Performance Data" and "Technological Characteristics" sections):
- No specific acceptance criteria for AI/ML performance metrics (e.g., sensitivity, specificity, AUC) are stated. The performance data section focuses on general device standards and image quality.
- The document does not detail specific "reported device performance" in terms of clinical accuracy or an AI model's output metrics. It states that the device "performs according to specifications and is as safe and effective as the predicate device."
Here's a table synthesizing the types of performance criteria and the general statement of performance, as can be extracted from the document:
| Acceptance Criteria Type | Reported Device Performance Statement |
|---|---|
| General Safety | Conforms to IEC 60601-1 (Medical electrical equipment - General requirements for basic safety and essential performance) |
| Image Quality | • Bench testing to confirm appropriate dosing and image quality. |
| • IEC 62220-1-1 (Determination of the detective quantum efficiency) Conformance. | |
| • Pixel Depth: 17 bits (> 131,000 gray levels) | |
| • Pixel Size: 100 μm | |
| • Resolution: 3.7 lp/mm | |
| • Typical Dynamic Range: > 100 dB | |
| Software Functionality | Software verification and validation testing conducted; performs according to specifications. |
Since the document is a 510(k) summary focused on demonstrating substantial equivalence of a modified X-ray system, it does not contain the detailed information typically found in a clinical study report for an AI/ML-powered diagnostic device.
Missing Information (for an AI/ML powered device, based on the provided text):
- Sample sizes used for the test set and data provenance: Not explicitly stated for any clinical performance evaluation of an AI component. The document mentions "bench testing."
- Number of experts used to establish ground truth & qualifications: Not applicable/not stated, as no clinical ground truth establishment for AI performance is described.
- Adjudication method for the test set: Not applicable/not stated.
- MRMC comparative effectiveness study: Not mentioned. The document is for an imaging system, not an AI assistance tool for human readers.
- Standalone (algorithm only) performance: Not mentioned, as it's a hardware system with software, not a pure AI algorithm.
- Type of ground truth used: Not applicable/not stated for an AI/ML performance evaluation. Only "bench testing" is mentioned.
- Sample size for the training set: Not applicable; no AI training set is mentioned.
- How ground truth for the training set was established: Not applicable; no AI training set is mentioned.
In conclusion, the provided text is a regulatory filing for an X-ray imaging system (EOSedge) demonstrating substantial equivalence to a predicate device, focusing on hardware and software modifications. It does not describe an AI/ML device, nor does it present clinical study data for AI performance against defined acceptance criteria. The "Performance Data" section primarily addresses compliance with general X-ray system standards (IEC 60601-1, IEC 62220-1-1) and software verification/validation, concluding that the modified device is as safe and effective as its predecessor.
§ 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.