Search Results

The software performs digital enhancement of a radiographic image generated by an x-ray device. The software can be used to process adult and pediatric x-ray images. This excludes mammography applications.

Eclipse software runs inside the ImageView product application software (also namely console software). The Eclipse image processing software II with Smart Noise Cancellation is similar to the predicate Eclipse image processing software (K180809). Eclipse with Smart Noise Cancellation is an optional feature that enhances projection radiography acquisitions captured from digital radiography imaging receptors (Computed Radiography (CR) and Direct Radiography (DR). The modified software is considered an extension of the software (it is not stand alone and is to be used only with the predicate device supports the Carestream DRX family of detectors, this includes all CR and DR detectors. The primary difference between the predicate and the subject device is the addition of a Smart Noise Cancellation module. The Smart Noise Cancellation module consists of a Convolutional Network (CNN) trained using clinical images with added simulated noise to represent reduced signal-to-noise acquisitions. Eclipse with Smart Noise Cancellation (modified device) incorporates enhanced noise reduction prior to executing Eclipse II image processing software.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Based on the provided text, the device Eclipse II with Smart Noise Cancellation is considered substantially equivalent to its predicate Eclipse II (K180809) due to modifications primarily centered around an enhanced noise reduction feature. The acceptance criteria and the study that proves the device meets these criteria are inferred from the demonstrated equivalence to the predicate device and the evaluation of the new Smart Noise Cancellation module.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly tied to the performance of the predicate device and the new feature's ability to maintain or improve upon key image quality attributes without introducing new safety or effectiveness concerns.

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

• Sample Size for Test Set: Not explicitly stated. The text mentions "a range of exams, detector types and exposure levels" for the clinical evaluation, and "clinical images with added simulated noise" for the CNN training.
• Data Provenance: Not explicitly stated. The text mentions "clinical images," implying real-world patient data, but does not specify the country of origin or whether it was retrospective or prospective.

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

• Number of Experts: Not explicitly stated. The text mentions a "clinical evaluation was performed by board certified radiologists." It does not specify the number involved.
• Qualifications of Experts: "Board certified radiologists." No specific years of experience are provided.

4. Adjudication Method for the Test Set

• Adjudication Method: Not explicitly stated. The text mentions images were evaluated using a "5-point visual difference scale (-2 to +2) tied to diagnostic confidence" and a "4-point RadLex scale" for overall diagnostic capability. It does not describe a method for resolving discrepancies among multiple readers, such as 2+1 or 3+1.

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

• MRMC Comparative Effectiveness Study: Yes, a clinical evaluation was performed by board-certified radiologists comparing the investigational software to the predicate software. While it doesn't explicitly use the term "MRMC," the description of a clinical evaluation by multiple radiologists comparing two versions of software suggests this type of study was conducted.
• Effect Size of Human Readers Improvement with AI vs. without AI Assistance: The text states, "The statistical test results and graphical summaries demonstrate that the investigational software delivers diagnostic quality images that exceed the quality of the predicate software over a range of exams, detector types and exposure levels." This indicates an improvement in diagnostic image quality with the new software (which incorporates AI - the CNN noise reduction), suggesting that human readers benefit from this enhancement. However, a specific effect size (e.g., AUC improvement, percentage increase in accuracy) is not provided in the summary.

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

• Standalone Performance: Partially. The "Ideal Observer Evaluation" seems to be a more objective, algorithm-centric assessment of detectability, stating that "detectability is preserved or improved with the investigational software." Also, the "Analysis of the Difference Images" checked for artifacts without human interpretation as the primary outcome. However, the overall "diagnostic quality" assessment was clinical, involving human readers.

7. The Type of Ground Truth Used

• Type of Ground Truth: The text implies a human expert consensus/evaluation as the primary ground truth for diagnostic quality. The "5-point visual difference scale" and "4-point RadLex scale" evaluated by "board certified radiologists" serve as the basis for assessing diagnostic image quality. For the "Ideal Observer Evaluation," the ground truth likely involved simulated lesions.

8. The Sample Size for the Training Set

• Training Set Sample Size: Not explicitly stated. The text mentions "clinical images with added simulated noise" were used to train the Convolutional Network (CNN).

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

• Ground Truth for Training Set: The ground truth for training the Smart Noise Cancellation module (a Convolutional Network) was established using "clinical images with added simulated noise to represent reduced signal-to-noise acquisitions." This suggests that the model was trained to learn the relationship between noisy images (simulated low SNR) and presumably clean or less noisy versions of those clinical images to perform noise reduction. The text doesn't specify how the "clean" versions were obtained or verified, but it implies a supervised learning approach where the desired noise-free output served as the ground truth.

Ask a specific question about this device

The device is designed to perform radiographic x-ray examinations on all pediatric and adult patient treatment areas.

The DRX-Revolution Mobile X-ray System is a diagnostic mobile x-ray system utilizing digital radiography (DR) technology. The system consists of a self-contained x-ray generator, image receptor(s), imaging display and software for acquiring medical diagnostic images outside of a standard stationary xray room. The DRX-Revolution system incorporates a flat-panel detector that can be used wirelessly for exams such as in-bed chest projections. The system can also be used to expose CR phosphor screens or films.

The Carestream DRX-Revolution Mobile X-ray System (K191025) underwent modifications compared to its predicate device (K120062). The primary changes include a different X-ray tube supplier, additional support for DRX Plus detectors, updated image acquisition software (ImageView), and a replaced high-voltage X-ray generator.

Here's an analysis of the acceptance criteria and the study proving adherence:

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample size used for the test set and the data provenance:

• Sample Size: Not explicitly stated as a number of images or cases. The document mentions a "Phantom Imaging study."
• Data Provenance: The study was a "Phantom Imaging study," which implies the use of test phantoms rather than real patient data. This is typically done in a controlled laboratory environment. The country of origin is not specified but given Carestream's location (Rochester, New York), it is likely the US. The study type is retrospective, as it's bench testing to compare a modified device to an already marketed predicate.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• This information is not provided in the document. As the study was a non-clinical "phantom imaging study" evaluating technical image quality attributes, it might not have involved human expert readers establishing diagnostic ground truth in the traditional sense. The evaluation likely relied on quantitative measurements of image quality metrics.

4. Adjudication method for the test set:

• This information is not provided as the study was a phantom imaging study focusing on technical image quality. Adjudication methods like 2+1 or 3+1 are typically used in clinical studies with human readers interpreting medical images.

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, an MRMC comparative effectiveness study was not done. The submission explicitly states: "Clinical testing was not required to establish substantial equivalence. Bench testing was sufficient to assess the device safety and effectiveness." This device is a mobile X-ray system, not an AI-powered diagnostic software.

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

• Yes, in a sense, a "standalone" evaluation of the device's image quality was performed through the "Phantom Imaging study" and DQE/MTF data. This tested the device's inherent capability to produce images without direct human interpretation for diagnostic purposes, focusing on technical image quality attributes rather than diagnostic accuracy.

7. The type of ground truth used:

• The ground truth used was based on technical image quality attributes such as detail, sharpness, noise, and appearance of artifacts, as evaluated through a "Phantom Imaging study" and by DQE/MTF data. This is an objective technical assessment against established metrics for image quality, rather than a clinical ground truth like pathology or expert consensus on a diagnosis.

8. The sample size for the training set:

• This information is not applicable/not provided. This device is a hardware X-ray system with standard image processing software, not an AI/Machine Learning algorithm that undergoes a "training" phase with a large dataset. The "ImageView" software is a web-based application to improve usability, and its image processing is stated to be the same as previously cleared versions.

9. How the ground truth for the training set was established:

• This information is not applicable/not provided for the same reasons as point 8.

Ask a specific question about this device

The device is intended to be used for x-ray computed tomography and projection x-ray imaging of upper and lower extremities of adult patients and pediatric patients aged 12 and over.

The Carestream Health Onsight 3D Extremity System is a medical x-ray imaging device designed to acquire three-dimensional, volumetric CT data of patient extremities (feet, ankles, lower leg, knees, hands, wrists, arms and elbows). The device is configured as a "cone beam computed tomography" system (CBCT) in that the x-ray field covers the whole anatomy of interest (~25cm in length) and the data is acquired with a single rotation of the detector and x-ray source (actually a short scan of 180 degrees plus "fan angle" for a total of 216.5 degrees) with no patient motion through the irradiation field. The device is intended for use in a range of different locations including officebased medical practice, hospital departments and other imaging facilities. The system is also capable of acquiring standard two-dimensional projection radiographs of the same body parts.

Here's a breakdown of the acceptance criteria and the study details for the Carestream Health OnSight 3D Extremity System, based on the provided document:

Acceptance Criteria and Device Performance

The document states that predefined acceptance criteria were met, but it does not explicitly list the quantitative acceptance criteria. Instead, it generally indicates that the device's performance was evaluated against the predicate and reference devices and found to be "statistically equivalent to or better than."

Study Details

1. Sample Size and Data Provenance

• Test Set Sample Size: Not explicitly stated. The document mentions a "clinical study" and "Reader Study" but does not provide the number of cases or images included in the test set.
• Data Provenance: Not explicitly stated. The document describes a "clinical study," which generally implies prospective data collection, but no details on the country of origin are provided.

2. Number of Experts and Qualifications

• Number of Experts: Not explicitly stated. The document refers to a "Reader Study," which implies multiple readers, but the exact number is not given.
• Qualifications of Experts: Not explicitly stated. The document does not provide details on the specialty or experience level of the readers.

3. Adjudication Method

• Not explicitly stated. The document mentions a "Reader Study" to determine diagnostic capability but does not describe any specific adjudication method used for discrepancies between readers, if any.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was an MRMC study done? Yes, a "Reader Study" was performed to compare the diagnostic capability of the OnSight 3D Extremity System against reference devices.
• Effect Size (Improvement with AI vs. without AI assistance): Not applicable. This study compared the diagnostic capability of the OnSight device's images to images from existing reference devices, not the improvement of human readers with AI assistance versus without AI assistance. The OnSight 3D Extremity System itself generates the images, and the study assesses the diagnostic quality of those images.

5. Standalone Performance Study

• Was a standalone study done? Yes, the "Reader Study" assessed the diagnostic capability of the images produced by the OnSight 3D Extremity System. This implies an evaluation of the algorithm's output (the images) for diagnostic quality.

6. Type of Ground Truth Used

• Not explicitly stated. Given that the study evaluated "diagnostic capability" and compared to reference devices, it is highly likely that the ground truth was established by expert consensus or comparison to a gold standard diagnosis, but the specific method (e.g., pathology, clinical follow-up) is not detailed.

7. Sample Size for Training Set

• Not applicable. The document describes a clinical study and bench testing for a medical imaging device (a CT system) that generates images, rather than an AI/ML algorithm that is trained on a dataset. Therefore, there is no mention of a training set for an AI model.

8. How Ground Truth for Training Set was Established

• Not applicable, as there is no mention of a training set for an AI model.

Ask a specific question about this device