(109 days)
The AlluraClarity Xper FD Series X-ray System is intended for use on human patients to perform:
- Vascular, cardiovascular and neurovascular imaging applications, including diagnostic, interventional and minimally invasive procedures. This includes, e.g., peripheral, cerebral, thoracic and abdominal angiography, as well as PTAs, stent placements, embolisations and thrombolysis.
- Cardiac imaging applications including diagnostics, interventional and minimally - invasive procedures (such as PTCA, stent placing, atherectomies), pacemaker implantations, and electrophysiology (EP).
- Non-vascular interventions such as drainages, biopsies and vertebroplasties procedures. .
Additionally:
- The AlluraClarity Xper FD Series X-ray System is compatible with a hybrid Operating -Room.
- FD10 is compatible with specified magnetic navigation systems.
The AlluraClarity Xper FD Series X-Ray System (AlluraClarity system) is a modular angiographic X-ray system, based on a set of components that can be combined into different single and biplane configurations to provide specialized angiography. Combined with a qualified, compatible OR table, the AlluraClarity system can also be used for imaging in the Hybrid OR. The AlluraClarity system is provided with ClarityIQ technology, which utilizes the advanced XRES4 noise reduction algorithms to reduce quantum noise in X-ray images.
This device is an X-ray system, and the provided documentation focuses on its software validation and clinical performance based on questionnaires and dose reports, rather than a typical AI/ML-driven diagnostic device with specific performance metrics like sensitivity and specificity. Therefore, the questions related to ground truth, expert adjudication, MRMC studies, and separate training/test sets are not directly applicable in the conventional sense for this type of submission.
Here's an attempt to answer the questions based on the available information:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are implicitly tied to "clinically acceptable" performance and successful utilization of the system for its indicated uses, as determined by physicians. There are no quantitative performance metrics such as sensitivity, specificity, or AUC provided in the document for the device's diagnostic capabilities, as the focus is on radiation dose reduction and image processing.
| Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|
| Clinically acceptable performance for fluoroscopy and acquisitions | All physicians indicated performance was "clinically acceptable" in questionnaires. |
| Successful utilization for intended clinical procedures | System was "successfully utilized" during clinical procedures covered by indications for use. |
| Ability to perform clinical tasks for all indicated applications | Physicians were "able to perform clinical tasks" with the system on all clinical applications. |
2. Sample Size for the Test Set and Data Provenance
- Sample Size: Not explicitly stated as a number of images or cases. The clinical performance data is based on "retrospective collected and analyzed clinical data," specifically "DICOM structured dose reports and customer satisfaction questionnaires." The number of questionnaires or dose reports reviewed is not provided.
- Data Provenance: Retrospective clinical data. The country of origin is not specified, but the manufacturer is Philips Medical Systems Netherlands B.V., so the data could originate from various international sites where Philips systems are used.
3. Number of Experts and Qualifications for Ground Truth
This question is not directly applicable in the context of this submission. The "ground truth" here is the physician's subjective assessment of the system's clinical acceptability and utility, rather than external verification of a disease state.
- Number of "Experts": Not specified. The document mentions "all physicians indicated...", implying multiple physicians participated in the questionnaires, but an exact number is not given.
- Qualifications of "Experts": The "experts" are the physicians who utilized the AlluraClarity System during clinical procedures and completed the satisfaction questionnaires. Their specific qualifications (e.g., area of specialty, years of experience) are not detailed.
4. Adjudication Method for the Test Set
Not applicable. There was no formal adjudication process for a "test set" in the sense of verifying diagnostic accuracy or discrepancies between readers. The assessment was based on individual physician feedback via questionnaires.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No. This document does not describe an MRMC comparative effectiveness study, nor does it quantify the improvement of human readers with or without AI assistance. The study focuses on the overall perceived clinical performance of the system as a whole, including its new image processing algorithms.
6. Standalone (Algorithm Only) Performance Study
No. The clinical performance data describes the performance of the integrated AlluraClarity Xper FD Series X-ray System, which includes the new image processing software (XRES4/ClarityIQ technology), not the algorithm in isolation.
7. Type of Ground Truth Used
The "ground truth" for the clinical performance assessment was expert consensus in the form of physician feedback/satisfaction questionnaires. This feedback directly addressed the "clinical acceptability" and "successful utilization" of the device for its indicated uses. While DICOM structured dose reports were also analyzed, they primarily provide objective data on dose, not clinical decision-making ground truth.
8. Sample Size for the Training Set
Not applicable. This device is an X-ray system with a new image processing algorithm, not a machine learning model that relies on a distinct "training set" in the conventional sense of supervised learning for classification or detection. The algorithms themselves would have been developed and tuned using various image data, but this is not characterized as a "training set" in the context of a clinical validation study's sample size.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as there is no mention of a distinct "training set" for the purpose of a clinical validation study with established ground truth. The XRES4 algorithms are described as "noise reduction algorithms," implying their development would involve signal processing and image quality metrics, rather than labeled clinical outcomes or pathology for training a diagnostic AI model.
§ 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.