(305 days)
The device is designed to perform general radiography x-ray examinations on all pediatric and all adult patients, in all patient treatment areas.
Treatment areas are defined as professional health care facility environments where operators with medical training are continually present during patients' examinations.
The !M1 mobile X-ray system is a diagnostic mobile x-ray system utilizing digital radiography (DR) technology. The device consists of a self-contained x-ray generator, image receptor(s), imaging display and software for acquiring medical diagnostic images both inside and outside of a standard stationary x-ray room. The !M1 system incorporates a flat-panel detector(s) that can be used wirelessly for exams such as in-bed projections. The system can also be used to expose CR phosphor screens or film.
The provided FDA 510(k) clearance letter and documentation describe a submission for an updated mobile X-ray system, !M1. However, the document primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed study proving the device meets specific performance acceptance criteria for an AI/algorithm-based medical device.
The clearance is for a mobile X-ray system and its components (generators, X-ray tubes, collimators, and new lines of digital detectors and associated imaging software), not an AI algorithm for diagnostic interpretation that would typically have specific performance metrics like sensitivity, specificity, or AUC against a ground truth.
Therefore, many of the requested items related to AI/algorithm performance (e.g., sample size for test set, number of experts, adjudication method, MRMC studies, standalone performance, ground truth for training/test sets, training set sample size) are not applicable or not provided in this type of 510(k) submission for an imaging device itself. The "performance" being improved here refers to the image acquisition capabilities (DQE, MTF, pixel size, kV, mAs, kW) of the new hardware components, not the output of a diagnostic AI algorithm.
Based on the provided document, here's what can be extracted:
Acceptance Criteria and Reported Device Performance
The "acceptance criteria" for this device are largely implied by demonstrating that the new components (collimator, generator, X-ray tube, software, and detectors) either maintain or improve upon the technical specifications and image quality parameters of the predicate device, while maintaining the same Indications for Use. The "study" proving this largely relies on non-clinical testing and compliance with relevant performance standards for X-ray equipment and image quality.
| Parameter (Acceptance Criteria - Implicit) | Reported Device Performance | Comments / Context |
|---|---|---|
| !M1 Mobile X-ray Unit: | ||
| Collimator Type | Motorized, single layer | Modified from manual to motorized, an improvement in functionality. |
| Max kV | 133 kV | Increased from 125 kV, an improvement in capability. |
| Max mAs | 400 mAs | Increased from 320 mAs, an improvement in capability. |
| Max kW | 40 kW | Increased from 32 kW, an improvement in capability. |
| Konica Minolta Detectors: | ||
| DQE (at 0 cycle/mm) | 72% | Improved from 51-65%, demonstrating better Detective Quantum Efficiency, meaning better dose efficiency. |
| MTF (at 1 cycle/mm) | 62% | Improved from 53-55%, demonstrating better Modulation Transfer Function, meaning better image sharpness/resolution. |
| Pixel size | 100/200 μm | Modified. Some predicate detectors had 175 μm. Newer detectors offer 100/200 μm, allowing for higher resolution imaging modes when 100 μm is used. |
| Canon Detectors: | ||
| DQE (e.g., at 0.5 lp/mm, 0 lp/mm) | 58% - 67% | Ranges. Predicate DQE was 0.6 @ 0 lp/mm. Subject device DQEs are reported at 0.5 lp/mm and 0 lp/mm, making direct comparison difficult without knowing the conditions. However, the range suggests comparable or improved performance depending on the specific model. |
| Pixel size | 125 μm, 140 μm | Modified. Some predicate CXDI detectors were 125μm. The subject device introduces 140 μm for CXDI-Pro, suggesting varied offerings while maintaining or improving overall image quality. |
| Spatial resolution (MTF@2lp/mm) | 35% - 45% | Improved for some models (CXDI-Elite: 45%) compared to predicate's 0.35 @ 0 lp/mm (a different metric, suggesting improved detail rendition). |
| Vieworks Detectors: | New manufacturer and detector models integrated. Performance specifications are provided for these new additions. This shows they meet acceptable performance levels for inclusion. | |
| DQE (at 1 lp/mm) | 41.5 - 53 | These are provided as specific values for the new detectors. There's no direct "predicate" for these specific detectors as they are new additions, but they meet the performance standards expected for cleared detectors. |
| MTF (at 1 lp/mm) | 52 - 76 | As above, values for new detectors, assessed for acceptable performance. |
| Pixel size | 99 μm, 140 μm, 124 μm | Varied pixel sizes offered by the new Vieworks detectors, extending options available. The 99 μm is smaller than previous options, implying potential for higher spatial resolution. |
| Spatial resolution | 3.5 lp/mm - 5 lp/mm | Provided as line pairs per millimeter (lp/mm), indicating the ability to resolve fine details. These values are typical for general radiographic detectors and demonstrate compliance with expected performance for the intended use. |
Study Details (As applicable to an X-ray System 510(k))
-
Sample size used for the test set and the data provenance:
This 510(k) is for an X-ray imaging system and its components, not a diagnostic AI algorithm. Therefore, there isn't a "test set" of patient cases in the context of an AI study.- Test Data: The testing involves non-clinical verification and validation of hardware performance (e.g., kV, mAs, kW measurements, image quality metrics like DQE, MTF, and spatial resolution using phantoms or test targets) and software functionality.
- Provenance: Not explicitly stated, implied to be internal testing by the manufacturers (Solutions for tomorrow AB, Konica Minolta, Canon Inc., Vieworks Co., Ltd) in their development and quality assurance processes. This is typical for device component integration.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Not applicable (N/A). Ground truth in this context refers to the measured physical properties and image quality metrics of the X-ray system components, not clinical diagnoses made by experts. For example, DQE and MTF are measured using standardized methods and phantoms, not adjudicated by clinical experts. -
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
N/A. This is relevant for clinical studies where human readers establish ground truth for diagnostic AI. Here, performance is verified through engineering and physics measurements. -
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:
N/A. This is not an AI diagnostic assistance device. It's an X-ray imaging system. -
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
N/A. Not an AI diagnostic algorithm. -
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
For the components of the X-ray system, the "ground truth" consists of physical measurements and standardized tests of parameters such as:- Output of the X-ray generator (kV, mAs, kW).
- Image quality metrics of the detectors (DQE, MTF, pixel size, spatial resolution) measured using phantoms and established procedures (e.g., IEC standards).
- Functionality of the collimator.
- Compliance with electrical and radiation safety standards (EN 60601 series).
-
The sample size for the training set:
N/A. The document does not describe an AI algorithm that requires a "training set" of patient data in the conventional sense. The "software" mentioned is operational imaging software, not a deep learning model for image interpretation. -
How the ground truth for the training set was established:
N/A. See point 7.
In summary, the provided document details a 510(k) submission for an updated mobile X-ray system and its components. The "acceptance criteria" and "proof" relate to meeting the performance specifications for hardware and integrated software functionality, and compliance with medical device standards, rather than the diagnostic performance of an AI algorithm.
§ 892.1720 Mobile x-ray system.
(a)
Identification. A mobile x-ray system is a transportable device system intended to be used to generate and control x-ray for diagnostic procedures. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.