Search Results

Intended for use by a qualified/trained doctor or technologist. As part of a radiographic system, the KrystalRad 660 is intended to acquire digital radiographic images. It is suitable for all routine radiography exams, including specialist areas like intensive care, trauma, or pediatric work, excluding fluoroscopy, angiography and mammography.

This device is simply the combination of two cleared devices, the same Wireless Portable Detector as used in the FD-W I (K90062) marketed by Philips Medical Systems and the image processing software cleared in our K080522 DDR MAK Series. Alternately the image processing software is the same as in Omil'ision, K. 100403 made by Modern Module Inc. The Wireless Portable Detector consists of three main parts: Portable in radiography detector (x-ray sensitive part); Docking station which is directly connected to the radiographic workshow and a backup cable which can connect the decector to the docking station if the wireless connection cable which can connect the detector to the docking if the wireless connection cannot be used. Detector size: 35 x 43 cm (14 x 17") Image matrix size: 3000 pixels x 2400 pixels. Pixel size 144 um Image matrix size: 3000 pixels x 2400 pixels. Pixel size: 144 µm, 1mage resolution up to 3.5 LP/mm. The device is intended as an upgrade to existing film x-ray systems. It should be installed by a qualifics trained by a qualifics trained

The KrystalRad 660 Digital Radiographic Portable Retrofit System's acceptance criteria and study details are provided below based on the 510(k) summary.

1. Table of Acceptance Criteria and Reported Device Performance

The submission does not explicitly state acceptance criteria in quantitative terms (e.g., minimum sensitivity, fidelity metrics). Instead, it focuses on demonstrating substantial equivalence to predicate devices. The primary performance metric is the qualitative comparison of clinical images and integration testing.

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

The document states, "Clinical images were acquired and compared to our predicate images." However, it does not specify the sample size for the test set (number of images or patients).

The data provenance is not explicitly stated regarding its country of origin or whether it was retrospective or prospective. It only mentions "clinical images were acquired," which could imply prospective acquisition, but this is not confirmed.

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

The document does not provide information on the number of experts used or their qualifications to establish ground truth for the clinical images. The comparison is described simply as "compared to our predicate images," suggesting an internal comparison rather than a formal expert review process for ground truth.

4. Adjudication Method for the Test Set

The document does not describe any formal adjudication method for the test set. The statement "no significant differences between them" suggests a qualitative assessment without detailing a specific process like 2+1 or 3+1 consensus.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done or reported in this submission. The study focuses on demonstrating equivalence to predicate devices, not on comparing human reader performance with or without AI assistance.

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

The device is a hardware combination (digital X-ray panel and image processing software). The "performance" being evaluated is the image quality and functionality of this combined system itself. Therefore, the "standalone" performance in this context refers to the system acquiring images, which was done by collecting and comparing clinical images. It's not an "algorithm-only" performance in the sense of an AI diagnostic aid.

7. The Type of Ground Truth Used

The ground truth for the comparison was based on "our predicate images." This implies comparing images from the KrystalRad 660 system to images produced by the previously cleared predicate devices (Philips Wireless Portable Detector FD-W17 K090625 and the image processing software from K080582 DDR MAK Series or K100403 OmniVision). The "ground truth" is therefore the established image quality and clinical utility of the predicate devices.

8. The Sample Size for the Training Set

The device is a combination of two already cleared predicate devices. The "study" described is a comparison and integration test of this combination, not the development or training of a new algorithm. Therefore, there is no specific "training set" mentioned for the KrystalRad 660 as it's not a de novo AI algorithm requiring training. The image processing software itself (cleared under K080582 or K110040) would have had its own validation/training, but details are not provided here for KrystalRad 660.

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

As stated in point 8, there isn't a "training set" for the KrystalRad 660 as a new device. The ground truth for the predicate image processing software or detector would have been established during their original clearance, likely involving various methods (e.g., expert review, physical phantoms for image quality metrics), but these details are not provided in this submission for K112132. The KrystalRad 660 leverages the already established "ground truth" (i.e., safety and effectiveness) of its predicate components.

Ask a specific question about this device