(22 days)
DIAMOND-5A/6A/8A, is a stationary digital diagnostic x-ray system that is indicated for use in generating radiographic images of human anatomy. This device is not intended for mammographic applications.
DIAMOND-5A/6A/8A, system is a digital radiographic system. There are 3 power output configurations which are reflected in the model designation "5A/6A/8A". The models have 3 different output power ratings: 52kW, 68kW, 82kW. DIAMOND 5A/6A/8A. incorporates digital flat panel detector technology, along with an automatic motorized U-arm radiographic stand and mobile patient table that can fit into smaller rooms without the need of ceiling support structures for X-Ray tube suspensions. The digital flat panel digital detectors that are used in DIAMOND-5A/6A/8A, are the VAREX Model 4343Rv3 (Ethernet interface) and 4336Wv4 (wireless). The main components of the x-ray source are the tube assembly, motorized x-ray collimator, HV cable assembly and high frequency x-ray generator. A touch screen LCD based x-ray control console provides a user interface and technique selection. The automatic collimator supports high accuracy for selected x-ray field size over SID. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique setting, motorized radiographic stand positioning, x-ray collimation and post image processing for selected study. Also, removable high-resolution grids which have 100 and 180cm (40 and 72 inch) focal distance supplies excellent image quality per each SID. The integrated touch screen console located in the tube side, operator can easily control the radiographic techniques and stand positioning. Furthermore, the operator can verify the digital x-ray image on this screen. The GUI, automatically rotates corresponds to rotation angle of U-arm. The Radiographic stand has four motorized joints, and automatic positioning can be accomplished by preprogrammed data which can be easily reprogrammed by operator. Total of seven safety sensors are located over U-arm, detector and tube side to protect. against collision with patient or obstacles to control the speed or stop the positioning. Also, a mobile patient table with heavy patient load is provided for radiographic study which needs table. A remote-control is provided for remote motorized control of the stand, and the movement will stop as soon as the key is no longer pressed. The predicate device contains image handling software that was designed at the same time the product was originally developed. The subject device will replace the original image handling module with the RADMAX Digital Image Software cleared under K182537. This will improve the software changeability when a change is needed and also will improve cyber security since there was no documented cyber security plan at the time of the original product development. RADMAX can also perform system control such as the collimation size, filter selection, etc. for the GXR series x-ray generators.
The provided document, a 510(k) summary for the DRGEM Corporation's DIAMOND-5A/6A/8A digital X-ray system, describes the device, its indications for use, and a comparison to predicate devices, along with performance data. However, it does not include detailed acceptance criteria or a study design for evaluating the diagnostic performance of the device, particularly for an AI component.
The document primarily focuses on demonstrating substantial equivalence to a predicate device, specifically regarding:
- Physical and functional characteristics (e.g., power output, detectors, image management software features).
- Compliance with various international safety and electromagnetic compatibility (EMC) standards for medical electrical equipment and software lifecycle processes.
- Risk management and usability engineering.
Therefore, I cannot extract specific information about acceptance criteria for diagnostic performance (e.g., sensitivity, specificity, or reader improvement with AI assistance) or a detailed diagnostic performance study (e.g., MRMC study, expert ground truth establishment) because that information is not present in the provided text.
The Performance Data section explicitly states: "The DIAMOND-5A/6A/8A system, has been assessed and tested and has passed predetermined testing criteria. The Validation Test Plan was designed to evaluate input functions, output functions, and actions performed by the subject device and followed the process documented in the System Validation Test Plan. Nonclinical testing results are provided in the 510(k). Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met."
This phrasing suggests that the "testing criteria" and "acceptance criteria" referred to are for ensuring the functionality, safety, and compliance with standards of the X-ray system itself, and not necessarily for demonstrating specific diagnostic performance metrics (like the accuracy of an AI algorithm in detecting pathologies). The core of the submission seems to be the replacement of an older image handling module with "RADMAX Digital Image Software," and the impact of this change on the system's safety and efficacy, not the introduction of AI for diagnostic assistance.
Based on the provided text, the device is a stationary digital diagnostic x-ray system, and the "AI component" referred to in your prompt (if it were present) would likely be part of the "RADMAX Digital Image Software" if it contained any AI-driven diagnostic features beyond basic image processing. However, the document does not elaborate on such diagnostic AI features or their performance evaluation.
Hypothetical Answer (if the document had contained the requested information for an AI-powered diagnostic device):
(Please note: The following is a hypothetical answer structured as if the document provided details for an AI-powered diagnostic device, which it does not. I've used placeholder values where specific information about diagnostic performance would typically be found in such a submission.)
Acceptance Criteria and Study for AI-Powered Diagnostic Device (Hypothetical)
This document describes the validation of a stationary digital diagnostic X-ray system. While the submission primarily focuses on functional safety and feature equivalence, if it were an AI-powered diagnostic device, the following hypothetical information would be expected for a performance study.
1. Table of Acceptance Criteria and Reported Device Performance (Hypothetical)
| Performance Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Standalone Performance (AI Algorithm Only) | ||
| Sensitivity (for X-condition) | ≥ 90% | Y% |
| Specificity (for X-condition) | ≥ 85% | Z% |
| AUC (for X-condition) | ≥ 0.90 | 0.YY |
| Human-in-the-Loop Performance Change | ||
| Sensitivity (reader + AI vs. reader only) | Increase of ≥ 5% points | X% increase |
| Specificity (reader + AI vs. reader only) | No significant decrease (10 years of experience in diagnostic radiography, specializing in chest imaging (if applicable to the indication).] |
4. Adjudication Method for Test Set (Hypothetical)
- Method: [e.g., 2+1 Adjudication: Each case was initially reviewed independently by two experts. In cases of disagreement, a third, senior expert reviewed the case to establish the final ground truth. Alternatively, 3-reader consensus.]
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study (Hypothetical)
- Was an MRMC study done? [e.g., Yes]
- Effect Size of Human Reader Improvement: [e.g., The MRMC study demonstrated that human readers, when assisted by the AI algorithm, showed an average XX% improvement in sensitivity for detecting condition X (e.g., from 75% to 85%), while maintaining specificity. The study used methods such as observer performance studies (e.g., ROC analysis) to quantify this improvement.]
6. Standalone Algorithm Performance (Hypothetical)
- Was a standalone performance evaluation done? [e.g., Yes]
- Metrics: The algorithm demonstrated a standalone sensitivity of Y% and specificity of Z% for condition X on the test set. (As per the table above).
7. Type of Ground Truth Used (Hypothetical)
- Ground Truth Type: [e.g., Expert consensus (as described in point 4), confirmed by available clinical outcomes data and/or pathology reports where possible.]
8. Sample Size for Training Set (Hypothetical)
- Sample Size: [e.g., 10,000 cases]
9. How Ground Truth for Training Set was Established (Hypothetical)
- Method: [e.g., A combination of initial annotations by trained technicians or junior radiologists, followed by review and verification by a single or small panel of senior radiologists. Cases were sometimes cross-referenced with electronic health records for clinical context and pathology reports if available.]
§ 892.1680 Stationary x-ray system.
(a)
Identification. A stationary x-ray system is a permanently installed diagnostic system intended to generate and control x-rays for examination of various anatomical regions. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A radiographic contrast tray or radiology diagnostic kit intended for use with a stationary x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.