(67 days)
The LessRay® is intended for use in any application where a fluoroscope is incorporated to aid in diagnosis and treatment of disease.
I.essRay* is a software only device that is used to enhance the utility of low dose images by comparing them to a baseline image taken at a regular dose setting. A computer running LessRay" is interfaced to a fluoroscope with a video cable. The images produced by the fluoroscope are transmitted to a frame grabber in the computer where the images are enhanced and then displayed on the monitor of the computer running LessRay®. Each image is displayed by LessRay at the same time as the corresponding original image is displayed on the fluoroscope monitor(s).
The provided text describes a 510(k) summary for the LessRay® device, which is a software-only device designed to enhance low-dose fluoroscopic images. However, the submission K132970 is about a modification to a previously cleared device (K123226). The modification entails providing the software on a CD for user installation, rather than preloaded on a computer.
Crucially, the document explicitly states: "These modifications represent a minor device modification and do not affect the indications for use. To assess the impact of this change a risk analysis was conducted. Based on the risk analysis verification testing was performed to ensure proper functioning of the software on four computer platforms."
This means the performance data provided in this submission (K132970) focuses on the software's functionality on different hardware platforms after the modification, not on the clinical performance or effectiveness of the image enhancement algorithm itself. The clinical effectiveness and acceptance criteria for the image enhancement would have been part of the original 510(k) submission (K123226), which is not fully detailed here. Therefore, many of the requested details about acceptance criteria, sample sizes for test sets, expert qualifications, and ground truth for clinical performance cannot be extracted from this specific document.
The document states: "The algorithm used and the user experience are identical to that of the previously cleared version." and "Algorithm used to improve image quality - NO CHANGE from K123226". This implies that the clinical performance evaluation was done for K123226 and is considered unchanged.
Here's what can be extracted from the provided text for K132970, focusing on the modification rather than the original clinical performance:
1. A table of acceptance criteria and the reported device performance
For K132970, the acceptance criteria and performance relate to the software's ability to function correctly on various computer platforms after being installed by the end-user, as stated after the risk analysis. The document lists the specific hardware configurations tested.
| Acceptance Criteria (for the modification) | Reported Device Performance (for the modification) |
|---|---|
| Proper functioning of the software on specified computer platforms | "verification testing was performed to ensure proper functioning of the software on four computer platforms. Each of the four computer platforms tested meet the specifications of the LessRay® System as previously cleared." The specific platforms tested were: |
- ONYX 175z
- Sony VAIO L Series
- Maxant Mediport 3000
- Dell Precision M6700 |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set Sample Size: Four computer platforms were used for testing the software's functionality after installation.
- Data Provenance: Not specified, but given it's functional testing of software installation, it's likely internal testing by the manufacturer.
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)
Not applicable for this modification. The testing described is functional verification of software on different hardware, not a clinical evaluation requiring expert ground truth.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable. This was functional testing, not a clinical evaluation.
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
Not applicable for this modification. This study pertains to a minor software distribution change, not a re-evaluation of the image enhancement algorithm's clinical effectiveness. The original 510(k) (K123226) would likely have addressed this type of study if relevant.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not explicitly stated for K132970. The original submission (K123226) would have addressed the standalone performance of the image enhancement algorithm. The current submission focuses on the software's ability to run on various platforms after user installation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not applicable for the testing described in K132970, which is functional verification of software installation. For the image enhancement algorithm itself (from K123226), the document states the device "Improves quality of low does images" and "Displays reduced noise images", implying that subjective or objective measures of image quality (which would typically involve expert review or image quality metrics) were used as ground truth in the original clearance, but these details are not in K132970.
8. The sample size for the training set
Not mentioned in this document for the image enhancement algorithm, as this submission is for a modification, not the initial clearance of the algorithm. The software is described as using "data from prior images to improve quality of subsequent images" and "summation of prior full dose images with subsequent images", implying it is an adaptive/real-time processing rather than a 'trained' AI in the modern sense (e.g. deep learning requiring a large training dataset).
9. How the ground truth for the training set was established
Not mentioned. As above, this information would pertain to the original clearance (K123226) of the image enhancement algorithm, not the current modification. The description of the algorithm (summation of prior full dose images) suggests a traditional image processing approach rather than a machine learning one that requires a "training set" with ground truth in the typical sense.
§ 892.1650 Image-intensified fluoroscopic x-ray system.
(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. 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). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic 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. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.