(28 days)
This is a stationary digital x-ray system for general radiography and RSA (Roentgen Stereophotogrammetric Analysis procedures.) Not for mammography.
The Halifax SR Suite is compromised of two regulatory approved X-Ray imaging systems; the two systems are integrated through a synchronization switch. The switch allows the two X-Ray imaging systems to fire simultaneously, providing a pair of X-Ray images from different perspectives to be taken at the exact same time. This process allows for Roentgen Stereophotogrammetric Analysis (RSA). RSA is a stereo x-ray technique that enables measurements more precise than single plane radiography based on phantom precision studies. The resulting level of precision provides measurements of joint replacement stability. The components are: 1: Stand. 2: Tube housings, 3: Collimators, 4: Reference Box Cover, 5: SR reference box, 6: Detector Plates, 7: SR Support Arm. The SR Suite employs the software cleared in K042383, the RSA-CMS.
Here's an analysis of the acceptance criteria and the study conducted for the Halifax Biomedical Inc. SR Suite 1.0, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document focuses on demonstrating substantial equivalence to predicate devices and detailing the technical specifications and testing for the SR Suite 1.0, particularly its RSA capabilities. It doesn't explicitly state quantitative acceptance criteria in the typical sense (e.g., "sensitivity must be > X%, specificity > Y%") for a diagnostic AI device. Instead, the acceptance is based on the performance of the RSA component (precision) and overall safety and effectiveness compared to predicate devices for general radiography.
Therefore, the "acceptance criteria" listed below are derived from the performance claims and testing detailed in the submission, treated as the target performance the device met for demonstrating safety and effectiveness.
| Characteristic / Acceptance Criteria | Reported Device Performance |
|---|---|
| RSA Precision (Bench Testing using Phantoms) | |
| Translational Precision (X-axis) | x = 0.0018mm |
| Translational Precision (Y-axis) | y = 0.0017mm |
| Translational Precision (Z-axis) | z = 0.0039 mm |
| Combined Precision (using rotating carbon fiber plate) | 0.005mm |
| General Radiography Performance | |
| Safety and Effectiveness (compared to predicate devices) | The results of bench, clinical, and standards testing indicate that the new device is as safe and effective as the predicate devices. Risk analysis has been performed. |
| Compliance with Safety and EMC Standards | External laboratory safety and EMC testing was performed to standards IEC 60601 + Am1& 2 and IEC 60601-1-2. (Implies compliance was met) |
| Effective Doses for RSA Examinations | Internal laboratory testing was performed to determine Effective Doses for RSA Examinations. (Implies determination was successful and likely within acceptable limits, though specific values are not provided as acceptance criteria) |
| Software Validation & Risk Analysis | Performed. (Implies successful completion and acceptable risk profile) |
| Total System Performance (Clinical Image Validation) | Clinical images were obtained to validate total system performance. (Implies satisfactory performance during clinical validation) |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: For the RSA precision bench testing, the translational precision was evaluated by taking 10 repeated measures of a carbon fiber phantom box. The combined precision was evaluated using a rotating carbon fiber plate (no specific number of repeated measures stated, but implied to be sufficient for precision calculation). For "clinical images... to validate total system performance," no specific number or sample size of clinical images is provided.
- Data Provenance:
- Bench Testing (Phantoms): This data is laboratory-generated using physical phantoms (carbon fiber phantom box, rotating carbon fiber plate). This is not patient data; it's an engineered test environment.
- Clinical Images: The document states that "Clinical images were obtained to validate total system performance." No information is provided regarding the country of origin of this data or if it was retrospective or prospective. Given the context of a 510(k) submission for a medical device that includes general radiography and RSA procedures, these clinical images would typically be from human subjects, but specifics are lacking.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
For the RSA precision testing, the "ground truth" is established by the known physical properties and measurements within the phantoms themselves (e.g., expected inter-bead distances). Therefore, no human experts were used to establish ground truth for this aspect of the test set.
For the "clinical images... to validate total system performance," the document does not specify if or how experts were involved in establishing ground truth, nor their number or qualifications. This validation likely focused on image quality and the system's ability to produce images suitable for RSA and general radiography, rather than a diagnostic performance evaluation against an expert-established ground truth.
4. Adjudication Method for the Test Set
As the primary "test set" described is a phantom study, there was no adjudication method involving human reviewers or experts. The ground truth was inherent in the phantom design and physical measurements. For the "clinical images" validation, no information about adjudication is provided.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, an MRMC comparative effectiveness study is not described in the provided document. The submission focuses on the technical precision of the RSA system and demonstrating substantial equivalence for general radiography, not on quantifying the improvement of human readers with AI assistance. The SR Suite 1.0 is primarily a diagnostic imaging system with specialized RSA capabilities, not an AI-assisted diagnostic interpretation tool in the typical sense of a CAD system.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
Yes, the RSA precision testing using phantoms represents a standalone performance evaluation of the system's ability to measure movement with high accuracy. The reported translational and combined precisions (e.g., 0.0018mm, 0.005mm) are purely algorithmic/system outputs based on image acquisition and software processing without human-in-the-loop diagnostic interpretation. The RSA-CMS software, which performs the RSA analysis, operates in a standalone capacity to generate these measurements.
7. The Type of Ground Truth Used
- Bench Testing (RSA Precision): The ground truth was physical measurements/properties inherent to the phantoms. For example, the ground truth for "inter-bead distance" is a known, precise physical separation within the phantom.
- Clinical Images Validation: The document does not explicitly state the type of ground truth used for validating total system performance with clinical images. It likely involved qualitative assessment of image quality and suitability for intended procedures, rather than a definitive diagnostic outcome or pathology.
8. The Sample Size for the Training Set
The document does not mention a training set in the context of machine learning or AI models. The RSA-CMS software mentioned is described as having been "cleared in K042383" and "designed specifically to perform Roentgen Stereophotogrammetric Analysis," implying a deterministic algorithm based on biophysical principles of RSA, rather than a machine learning model that requires a training set.
9. How the Ground Truth for the Training Set Was Established
Since no training set is described for a machine learning model, this question is not applicable. The underlying principles of Roentgen Stereophotogrammetric Analysis (RSA) are based on established physics and geometry, which would have informed the deterministic design of the RSA-CMS software.
§ 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.