Search Results

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:

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):

1. 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."
2. Number of experts used to establish ground truth & qualifications: Not applicable/not stated, as no clinical ground truth establishment for AI performance is described.
3. Adjudication method for the test set: Not applicable/not stated.
4. MRMC comparative effectiveness study: Not mentioned. The document is for an imaging system, not an AI assistance tool for human readers.
5. Standalone (algorithm only) performance: Not mentioned, as it's a hardware system with software, not a pure AI algorithm.
6. Type of ground truth used: Not applicable/not stated for an AI/ML performance evaluation. Only "bench testing" is mentioned.
7. Sample size for the training set: Not applicable; no AI training set is mentioned.
8. 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.

Ask a specific question about this device

EOSedge is intended for use in general radiographic exams and applications, excluding the evaluation of lung nodules and exams involving fluoroscopy, 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 identical 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 follow-up pediatric exams. The two sets of detectors and X-ray tubes are identical between the predicate device and the subject device. The image acquisition can be performed with a MANUAL mode or an AUTO mode of patient examination. To select the area of interest (acquisition area), a vertical collimation is set using green lasers and to correctly position the patient in the EOSedge, a centering system is used based on red lasers. 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 describes a 510(k) premarket notification for the EOSedge™ system, an updated digital radiography system. The document focuses on demonstrating that the updated device is substantially equivalent to a previously cleared predicate device (EOS imaging's EOSedge System K192079).

Based on the provided text, the acceptance criteria and study proving the device meets these criteria are primarily based on bench testing and comparative analysis with a predicate device, rather than a clinical study evaluating diagnostic performance.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly tied to demonstrating substantial equivalence to the predicate device, implying that the updated device must perform at least as safely and effectively. The performance data section refers to conformity to various IEC standards and internal functional testing.

• Quantity: 2
• Type: Hybrid CdTe-CMOS dual energy photons counting X-ray detector
• Dimensions: Width 585 mm x 98 mm, Thickness 131 mm
• Weight: 131 000 gray levels)
• Nominal input voltage: 12 VDC – 20 A
• Temperature control: Internal check, Peltier + PWM, Ventilator system checked
• DQE type: RQA5 spectrum ~ 80%
• MTF type: ~70% @ 2lp / mm, ~25% @ 5lp / mm
• Pixel Depth: 17 bits (> 131 000 grey levels)
• Pixel Size: 100 µm
• Resolution: 3.7 lp/mm
• Typical Dynamic Range: > 100 dB |
  | Average Acquisition Time | Must be comparable or improved compared to predicate. | Current Device (EOSedge™): 7 seconds for a spine and 13 seconds for an entire body
  Predicate Device (EOSedge System K192079): 8 seconds for a spine and 15 seconds for an entire body (Improved performance stated for current device) |

2. Sample Size Used for the Test Set and Data Provenance

The document does not describe a clinical test set with patient data for evaluating diagnostic performance. The testing described is primarily bench testing and software verification/validation. Therefore, there are no details on sample size for a test set of patient images or their provenance (country of origin, retrospective/prospective). The assessment is based on technical specifications and comparison to the predicate device.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of those Experts

As there is no clinical test set for diagnostic performance described, there is no information on experts establishing ground truth for such a set. The ground truth for the engineering/technical tests would be the established specifications and accepted performance metrics for medical imaging devices, as defined by relevant IEC and FDA guidance.

4. Adjudication Method for the Test Set

Not applicable, as no clinical test set requiring expert adjudication is described in the provided text.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study was not explicitly done or described in the provided text. The submission focuses on demonstrating substantial equivalence through technical performance data and comparison to a predicate device, not on improved human reader performance with AI assistance. The device itself is an X-ray imaging system, not an AI diagnostic assistant.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

Not explicitly applicable in the context of an X-ray imaging system. The performance evaluated here is the image acquisition and processing capabilities of the X-ray device itself, which operates as a standalone system to produce images for human interpretation.

7. The Type of Ground Truth Used

The ground truth used for these tests is based on established engineering and performance standards for X-ray imaging devices (e.g., IEC standards, FDA guidance for solid-state X-ray imaging devices). For comparative purposes, the predicate device's cleared performance serves as a benchmark for substantial equivalence.

8. The Sample Size for the Training Set

Not applicable. The document describes a medical imaging device (hardware and software for image acquisition), not a machine learning algorithm that requires a training set of data for inference.

9. How the Ground Truth for the Training Set was Established

Not applicable, as there is no training set for a machine learning algorithm described.

Ask a specific question about this device

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 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 follow-up exams. The diagnostic images are stored in a local database and are displayed on a highresolution medical-quality non-diagnostic image can be transmitted through a DICOM compatible digital network for printing and archiving.

The provided text is a 510(k) summary for the EOS imaging's EOSedge System. It describes the device, its intended use, and compares it to a predicate device (EOS System K152788) to demonstrate substantial equivalence.

However, the document does not contain information about acceptance criteria for an AI/algorithm's performance, nor does it describe a study that proves a device meets such criteria. It focuses on the substantial equivalence of an X-ray imaging system to its predecessor, based on design, technical specifications, and general performance testing (bench testing for dosing and image quality).

Therefore, I cannot fulfill your request for information regarding acceptance criteria and a study proving an AI device meets them based on the provided text. The document is about a conventional X-ray imaging system, not an AI-driven device with specific performance metrics like sensitivity, specificity, or AUC established through clinical studies with ground truth.

The "Performance Data" section (page 4) states: "Bench performance testing were conducted based on FDA's Guidance for the Submission of 510/k)'s for Solid-State X-ray Imaging Devices (September 1, 2016), to verify that EOSedge performs according to specifications and is as safe and effective as the predicate device." This refers to engineering and image quality tests common for X-ray hardware, not an AI algorithm evaluation.

Ask a specific question about this device