Search Results

The ArtPIX DRF is a digital image acquisition system to be used with integrated solid state detector, during radiography or fluoroscopy x-ray examination, to capture digitalize, review images according to DICOM protocol to be sent through network connection.

This device is not intended for mammography use.

The modified ArtPIX DRF is a dynamic digital radiography system including fluoroscopy and radiography capabilities.

The system application is based on Windows 10 operating system. The object-oriented software performs real-time image processing (based on parallel computing), and full procedures storage. The DICOM 3.0 IHE compliant connectivity provides the tools to transmit patient demographics, examinations and image data in digital format.

Parameters for X-ray exposure, review, post-processing operations and filming can be set up from a single console, significantly increasing clinical efficiency.

The modified ArtPix DRF operates in connection with the dynamic Pixium 2121, 3030, 4343 flat panel detectors and 2430, 3543 portable flat panel detectors (made by Thales of Moirans, France).

The modified ArtPix DRF is intended for OEMs and Integrators that will integrate the product with their R&F table as a digital supplement.

The provided text describes a Special 510(k) submission for the ArtPIX DRF, which is a modification of a previously cleared device, the Duet DRF (K103038). This type of submission focuses on demonstrating that the modified device remains substantially equivalent to the predicate device, implying that extensive, new clinical studies for acceptance criteria may not be performed if the changes do not introduce new safety or effectiveness concerns.

Based on the provided information, I can extract the following:

1. A table of acceptance criteria and the reported device performance

The document doesn't explicitly present a table of acceptance criteria with corresponding performance metrics in a way you might expect for a new device submission. Instead, it details that the modified ArtPIX DRF's performance and technological characteristics are substantially equivalent to its predicate device, the Duet DRF K103038. The acceptance criteria for the modified device are implicitly inferred from the performance characteristics of the predicate device and the new, integrated components, as well as adherence to various industry standards.

Here's an attempt to infer and present the acceptance criteria and device performance based on the comparison:

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The document primarily describes verification and validation (V&V) activities, which are typically technical assessments rather than extensive clinical studies. It mentions "software unit tests," "software test document," "system bench tests," and "measuring the image quality." It also states, "The (positive /negative) results were documented in the test document."

However, there is no specific sample size mentioned for a test set (e.g., number of patients or images). The data provenance is also not specified, as these appear to be internal design validation activities rather than
a clinical trial. The testing was performed by "CMT Medical Technologies Ltd." which is an Israeli company, so the testing data would likely originate from their facilities. The nature of the changes (integration of new, already cleared FPDs and hardware/software upgrades) suggests that rigorous clinical testing with human subjects was not deemed necessary for substantial equivalence given the predicate.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

The document does not mention using experts (e.g., radiologists) to establish ground truth for a test set. This is consistent with a "Special 510(k)" for device modifications where clinical performance is demonstrated via substantial equivalence to a predicate device and technical performance testing, rather than new clinical evaluations requiring expert reads.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

No adjudication method is mentioned, as no expert-based ground truthing or clinical study requiring adjudication is detailed.

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 was done. The device is an image acquisition and processing system, not an AI-assisted diagnostic tool.

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

The device is a digital image acquisition system with software for image processing and handling. Its performance is inherently linked to its ability to capture, digitize, review, and format images. The "system performance of the modified ArtPix DRF was validated by measuring the image quality." This would include the performance of the integrated detectors and the processing algorithms. While not explicitly called "standalone algorithm performance," the technical tests on image quality and system functionality without human interpretation are part of the stated V&V.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

The "ground truth" for the verification and validation activities appears to be based on technical performance specifications, industry standards (e.g., DQE, pixel pitch), and expected functional behavior of the system components. For image quality, it would be measured parameters against documented specifications. There's no indication of ground truth established by expert consensus, pathology, or outcomes data, as this was not a clinical efficacy study.

8. The sample size for the training set

The document discusses device modifications and V&V testing, not the development of a machine learning or AI algorithm that would typically require a "training set." Therefore, no training set size is applicable or mentioned.

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

As there is no mention of a training set or an AI/ML algorithm within the modifications described, this information is not applicable and not provided. The software modifications described primarily relate to supporting new hardware, updating the operating system and user interface, and incorporating previously cleared processing algorithms or standard DICOM functions.

Ask a specific question about this device

These radiographic systems are intended for use by a qualified/trained physician or technician on both adult and pediatric subjects for taking diagnostic x-rays. Not for mammography, interventional, or fluoroscopy use.

The Amrad Systems are permanently-installed diagnostic x-ray systems for general purpose radiographic imaging for use in hospitals, clinics, and medical practices. They are intended to produce diagnostic x-ray images of human anatomy. The Amrad Systems enable radiographic exposures of the whole body including: skull, chest, abdomen, and extremities, and may be used on pediatric, adult, and bariatric patients. Exposures may be taken with the patient sitting, standing, or in the prone position. The resultant images are evaluated by a radiologist within the diagnostic process prior to the development of a treatment plan. It is not intended for fluoroscopy, angiography, or mammography. The Amrad Systems typically include a tube support, x-ray generator, x-ray tube, radiographic wall stand, and collimator. An FDA cleared digital imaging system is included.

The provided text describes a 510(k) premarket notification for Amrad Medical Digital Radiography Systems, asserting their substantial equivalence to a legally marketed predicate device. This submission does not contain a study that proves the device meets specific acceptance criteria in the way a clinical performance study for an AI/ML medical device would.

Instead, the submission focuses on demonstrating that the new devices are functionally equivalent and technologically similar to a previously cleared predicate device, and that their individual components (like the digital panels) have already received FDA clearance. Therefore, the following information, typically found in AI/ML performance studies, is largely not applicable or not provided in this document.

However, I can extract the acceptance criteria (or rather, the basis for substantial equivalence) and what performance was reported in relation to the submission.

Here's a breakdown based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

• Tube crane/stand: Similar Functionality (Predicate has overhead, new devices have U-Arm, Floor Stand, or Wall/Floor Stand).
• Wall stand: Same (manual or motorized).
• Table: Same or Similar Functionality.
• X-ray tube: Similar Functionality (150 kVp 0.6/1.2mm focal spots).
• Collimator: Similar Functionality (Ralco R221 or R225 vs. Collimare).
• X-ray Generator: Identical Functionality (40, 50, 65, or 80 kW models).
• Wireless detector: Greater convenience (new device includes Cleared Wi-Fi, predicate does not explicitly mention).
• Fixed detector: Similar Functionality (new device uses THALES/CMT K162224 ArtPix Mobile EZ2GO using Pixium Portable 3543 EZ and 2430 EZ Wireless Detectors; predicate uses Varian PaxScan 4343R and 4336R panels cleared in K093066 and K130318).
• Conventional film/screen systems or CR cassettes: Similar Functionality (both can still be used).
• Operator console: Similar Functionality ("Same").
• Power Source: Same (AC LINE). |
  | Safety: Device must adhere to recognized safety standards (EMC, mechanical, electrical). | Mitigated Risks: EMC, mechanical safety, and electrical safety were evaluated according to various FDA-recognized consensus standards. Identified risks were mitigated. All components bear UL or ETL certification labels. |
  | Imaging Performance: Imaging components previously cleared by FDA. | Phantoms Used: "We did collect and evaluate digital images using standardized phantoms." Clinical study not required because imaging components already received FDA clearance. |

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

• Test Set Sample Size: Not applicable. This submission doesn't describe a performance study with a test set in the context of AI/ML evaluation. It uses phantoms for image evaluation.
• Data Provenance: Not applicable.

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

• Not applicable. Ground truth establishment for a diagnostic study is not described.

4. Adjudication method for the test set:

• Not applicable.

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, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This submission is for a general radiography system, not an AI-powered diagnostic aid.

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

• Not applicable. The device is a radiographic system, not an algorithm. The software and digital panels are part of the system and were previously cleared by FDA.

7. The type of ground truth used:

• Not explicitly defined in the context of a diagnostic dataset. The "ground truth" for the submission's purpose is related to compliance with safety standards and the performance of previously cleared imaging components, evaluated via:
  • Comparison to a predicate device's established performance.
  • Evaluation of digital images using standardized phantoms.

8. The sample size for the training set:

• Not applicable. This document does not describe the development or training of an AI/ML algorithm.

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

• Not applicable.

Ask a specific question about this device