(64 days)
The Digital Fluoroscopic Imaging System is indicated for use in generating fluoroscopic images of human anatomy for diagnostic and intervention angiography procedures. It is intended to replace fluoroscopic images obtained through the image intensifier technology. This device is not intended for mammography applications.
The Digital Fluoroscopic Imaging System is indicated for use in diagnostic and interventional angiographic procedures of human anatomy. It is intended to replace image intensifier fluoroscopic systems in all diagnostic or interventionnal procedures. This device is not intended for mammography applications.
The Digital Fluoroscopic Imaging System is designed to perform fluoroscopic x-ray examinations. The detector is comprised of amorphous silicon with a cesium iodide scintillator. The resulting digital image can be sent through a Fiber Channel link to an acquisition equipment then to network (in using DICOM) for applications such as post-processing, printing, viewing and archiving. Digital Fluoroscopic Imaging System consists of an angiographic monoplane positioner, a vascular table, an X-RAY system and a digital detector.
The GE Medical Systems Digital Fluoroscopic Imaging System (Innova 4100) was studied for its diagnostic capabilities compared to a predicate device, the Innova 2000. The primary goal was to demonstrate equivalent image diagnostic capability.
Here's a breakdown of the acceptance criteria and study details:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Explicit or Implied) | Reported Device Performance |
|---|---|
| Equivalent image diagnostic capability | "found that the digital images from the Innova 4100 had equivalent image diagnostic capability." |
2. Sample Size and Data Provenance
- Test Set Sample Size: 11 pairs of patient sequences. This relatively small number suggests a comparative efficacy study.
- Data Provenance: The study was conducted at three hospitals:
- Saint-Luke's Hospital (Bethlehem, Pennsylvania - US)
- Saint-Francis Hospital (Peoria, Illinois - US)
- Centre Paris Nord (Sarcelles - France)
This indicates a mix of retrospective and prospective data, given the comparison of existing Innova 2000 images with new Innova 4100 images. The involvement of different hospitals across different countries suggests a more diverse dataset than if it were confined to a single institution or country.
3. Number of Experts and Qualifications
- Number of Experts: 6 radiologists.
- Qualifications: Not explicitly stated beyond "radiologists." It's implied they are qualified to interpret angiographic images for diagnostic purposes.
4. Adjudication Method
- The document describes the radiologists "compared digital images" and "found that the digital images from the Innova 4100 had equivalent image diagnostic capability." This phrasing suggests a consensus or majority opinion among the radiologists, but a specific adjudication method (e.g., 2+1, 3+1) is not detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Yes, a clinical comparison study was done with 6 radiologists evaluating images.
- Effect Size of Human Readers with vs. without AI: Not applicable. This study does not involve AI assistance to human readers. It's a comparison of two different fluoroscopic imaging systems (Innova 2000 vs. Innova 4100) and their inherent diagnostic image quality.
6. Standalone Performance (Algorithm Only)
- Not applicable. This is a medical device clearance for an imaging system, not an artificial intelligence algorithm. The device itself is the entire system outputting images.
7. Type of Ground Truth Used
- Expert Consensus/Clinical Agreement: The "gold standard" for determining equivalent diagnostic capability was the collective evaluation and agreement of the 6 radiologists. There's no mention of pathology or long-term outcomes data being used as ground truth for this particular comparison.
8. Sample Size for the Training Set
- Not applicable. This device is a digital fluoroscopic imaging system, not an AI algorithm that requires a distinct training set. The "training" for the device would be its engineering and design, informed by established medical imaging principles and prior device iterations (like the Innova 2000).
9. How Ground Truth for the Training Set was Established
- Not applicable, as there is no specific "training set" in the context of an AI algorithm. The device's fundamental design is based on known physics, engineering principles, and clinical requirements for fluoroscopic imaging.
§ 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.