Search Results

The EXSYS DEXi is a diagnostic X-ray system intended for use in generating radiographic images of human anatomy for general purpose. The system obtains necessary information of patient's anatomical structure by an image processing (workstation) after process of examination using radiation exposure with DR. This system is not intended for mammography applications.

The EXSYS DEXi is a diagnostic X-ray system intended for use in generating radiographic images of human anatomy for general purpose. The system obtains necessary information of patient's anatomical structure by an image processing (workstation) after process of examination using radiation exposure with DR. This system is not intended for mammography applications.

The EXSYS DEXi composed of a x-ray generator, tube, collimator, tube stand, bucky stand, patient table, flat panel detector and console.

This FDA 510(k) summary does not contain information about acceptance criteria and device performance as it pertains to AI/ML or image analysis aspects. The document focuses on the substantial equivalence of the modified EXSYS DEXi diagnostic X-ray system to a previously cleared predicate device (K233530) based on hardware and software updates, and compliance with general safety and performance standards for X-ray systems.

Specifically, the document refers to non-clinical data and verification and validation testing demonstrating compliance with various international and FDA-recognized consensus standards (e.g., IEC 60601 series for medical electrical equipment, ISO 14971 for risk management, IEC 62304 for medical device software, UL ANSI 2900-1 and IEC 81001-5-1 for cybersecurity). It states, "The test results support that all the specifications have met the acceptance criteria. Verification and validation testing were found acceptable to support the claim of substantial equivalence." However, it does not provide a table of acceptance criteria with reported device performance metrics in an AI/ML context, nor does it describe specific studies that would typically prove such performance (e.g., standalone performance studies, MRMC studies, details on ground truth establishment for a diagnostic algorithm, sample sizes for test/training sets relevant to AI performance).

The "technological characteristics" table (Table 1) compares design parameters of the subject device (new models of EXSYS DEXi) with the predicate device, highlighting additions like new collimators, mechanical parts, detectors, and software (EConsole2). The discussion column for these additions generally states, "The system has been tested and there is 'No negative impact on safety or efficacy' and there are no new potential or increased safety risks concerning this difference." This refers to overall system safety and performance in line with a general X-ray system, not specific AI/ML diagnostic performance.

Therefore, based on the provided document, the following information cannot be extracted:

1. A table of acceptance criteria and the reported device performance (for AI-specific functions): Not provided. The document states general compliance with standards and "test results support that all the specifications have met the acceptance criteria," but does not detail these criteria or performance metrics specific to an AI component's diagnostic accuracy, sensitivity, specificity, etc.
2. Sample size used for the test set and the data provenance: Not provided for AI/ML performance evaluation.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided for AI/ML performance evaluation.
4. Adjudication method for the test set: Not provided for AI/ML performance evaluation.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size: Not mentioned.
6. If a standalone (algorithm only without human-in-the-loop performance) was done: Not mentioned.
7. The type of ground truth used: Not specified for AI/ML performance evaluation.
8. The sample size for the training set: Not provided for AI/ML performance evaluation.
9. How the ground truth for the training set was established: Not provided for AI/ML performance evaluation.

The document states, "Clinical studies are unnecessary to validate the safety and effectiveness of the Stationary x-ray system, EXSYS DEXi, the subject of this 510(k) notification," further indicating that specific performance data from clinical trials or detailed AI algorithm validation studies (which typically involve such criteria) are not included in this submission summary. The software updates mentioned (EConsole2) were previously cleared via K240243, suggesting that any specific performance data for that software might be found in its own 510(k) submission, but not in this document.

Ask a specific question about this device

The EXPD 4343S Digital X-ray detector is indicated for use in generating radiographic images of human anatomy. This device is intended to replace film or screen based radiographic systems in all general purpose diagnostic procedures on general populations. This device is not intended for mammography applications.

The EXPD 4343S Detector is a square plate-shaped indirect conversion device that converts incoming X-rays into visible light. This visible light is subsequently captured by an optical sensor, which produces an electric charge representation of the spatial distribution of the incoming X-ray quanta. Through thin film transistors, the charges are transformed into a modulated electrical signal is amplified, then changed from an analog to digital form (from voltage to signal) so that it can be printed out, sent for remote viewing, or saved as an electronic data file for later viewing. The subject device features two matrix arrays strategically positioned in an overlapping configuration within the housing, facilitating the generation of multiple images with a single exposure. Array #1 works similarly to the predicate device by detecting incident X-ray photons and converting them into electrical signals. Simultaneously, Array #2 captures unabsorbed X-rays from Array #1 after passing through it. As a consequence of this configuration, the subject device has the capacity to produce three distinct images: a Standard image produced by Array #1, a second image (a soft tissue image) obtained by processing the Standard image using Console software, and a third image (a bone image) generated by processing the image obtained from Array #2.

The provided text describes a 510(k) summary for the EXPD 4343S Digital X-ray detector, claiming substantial equivalence to a predicate device (EXPD 4343P). However, the document does not contain specific acceptance criteria or a detailed study proving the device meets those criteria with quantitative values.

Instead, it presents a comparison of technological characteristics and states that:

• "an overall assessment of the subject device's essential performance revealed that it is basically on the equivalent level with the predicate device."
• "the clinical image evaluation was performed to assess the device's clinical performance and average score of evaluation results by two experienced physicians demonstrated that the device is prove to be effective in clinical practice."
• "The result showed that images acquired by the subject device were generally in diagnostic quality, and evaluators stated that the device proved to be effective use in clinical practice."

Without specific numerical acceptance criteria and a structured study result, it's impossible to fill out the requested table and answer many of the specific questions.

Based on the information available, here's what can be extracted and what remains unknown:

Acceptance Criteria and Device Performance (Based on available comparative data)

While no explicit acceptance criteria are provided in the sense of pass/fail thresholds, the document implies that the device's performance is deemed acceptable if it is "basically on the equivalent level" to the predicate device and found to be "effective in clinical practice" and "of diagnostic quality" by physicians.

Study Details (Inferred and Missing Information)

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

   • Sample Size: Not specified. The document states "Chest PA imaging sets used for evaluation".
   • Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). It just mentions "Chest PA imaging sets".

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

   • Number of Experts: Two experienced physicians.
   • Qualifications: "experienced physicians." No further detail regarding their specialty (e.g., radiologist) or years of experience is provided.

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

   • Adjudication Method: Not specified. It mentions an "average score of evaluation results" and that "visual system was adapted with each physician's overall assessment," which suggests independent assessment followed by some form of averaging or consensus, but the specific method is not detailed.

4. 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:

   • MRMC Study: No, an MRMC study was not conducted as described for AI assistance. The study described is a clinical image evaluation of the device's output by physicians, not an evaluation of AI assistance to human readers. The device itself is an X-ray detector, not an AI diagnostic tool.

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

   • Standalone Performance: Not applicable in the context of an X-ray detector's primary performance. The "soft tissue image" and "bone image" are generated by processing, which implies an algorithm, but the performance evaluation described is of the final image quality and diagnostic effectiveness by human readers. There is no mention of a quantitative standalone performance evaluation of these derived images in terms of specific diagnostic tasks.

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

   • Ground Truth: Expert assessment/consensus from the two experienced physicians on the "diagnostic quality" and "effectiveness in clinical practice" of the images generated by the device. It is not based on pathology or outcomes data.

7. The sample size for the training set:

   • Training Set Sample Size: Not applicable. This document is for an X-ray detector, not an AI algorithm that requires a training set. The "soft tissue" and "bone" image processing is fundamental to the detector's output, not a separate AI application.

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

   • Training Set Ground Truth: Not applicable, as no training set for an AI algorithm is mentioned.

Summary of what's provided vs. what's missing:

The document provides basic comparative technical specifications and a high-level qualitative summary of a clinical image evaluation. It lacks detailed quantitative results, specific acceptance criteria for image quality, detailed expert qualifications, sample sizes, and adjudication methods that would be expected in a rigorous study for an AI-enabled diagnostic device. Given that the device is a digital X-ray detector, the focus of the provided information is on demonstrating the equivalence of its imaging capabilities to a predicate device, rather than the performance of a diagnostic AI algorithm.

Ask a specific question about this device