(29 days)
The DR 400 system is a GenRad X-ray imaging system used in hospitals, clinics and medical practices by physicists, radiographers and radiologists to make, process and view static X-ray radiographic images of the skeleton (including skull, spinal column and extremities), chest, abdomen and other body parts on adult and pediatic patients. Applications can be performed with the patient in the sitting, standing or lying position.
Agfa's DR 400 is not indicated for use in mammography.
Agfa's DR 400 is a solid state x-ray system, a direct radiography (DR) system (product code MQB) intended to capture images of the human body. It is a combination of Agfa's NX workstation and one or more flat-panel detectors or photo-stimulable imaging plates and a separate digitizer.
The provided documentation describes the Agfa DR 400 system, a digital radiography system. The submission aims to demonstrate substantial equivalence to predicate devices, rather than establishing acceptance criteria for a new clinical performance claim. Therefore, the information regarding specific acceptance criteria, corresponding device performance measurements, sample sizes for test/training sets, expert qualifications, and ground truth establishment, including MRMC studies or standalone algorithm performance, is not directly present in the provided text.
The document primarily focuses on demonstrating that the DR 400 is substantially equivalent to existing cleared devices (AGFA DX-D Imaging Package K122736 and Sedecal Optima URS K012546) due to similar intended use, technological characteristics, and performance.
However, based on the provided text, we can glean some information about the studies conducted to support the claim of equivalence:
Here's a breakdown of the available information:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly present a table of acceptance criteria with corresponding performance metrics like sensitivity, specificity, or image quality scores against a defined threshold. Instead, it relies on comparing the new device's characteristics and performance to legally marketed predicate devices.
The "PRODUCT COMPARISON TABLE" (Page 3-5) lists technological characteristics such as:
- Communications: DICOM
- Flat Panel or Image Plate: Flat Panel Detector (and Image Plate for new device)
- Detector Material: Gadolinium Oxysulfide (GOS) or Cesium Iodide (CsI) scintillator
- Detector Sizes: 17x17 in., 14x17 in.
- Active Matrix (14x17 in.): 2560 x 3072 (for K122736), 3320 x 3408 (for K012546)
- Pixel size: 139 μm (for K122736), 125 μm (for K012546)
- Dynamic Range: 14 bit (for K122736), 12 bit (for K012546)
- Maximum Image Acquisitions/hr.: 150 (for K122736), 100 - 180 (for K012546)
- Power Supply: 50-60 Hz, 100-240V auto ranging
- Operator Workstation: Agfa NX
- Image processing: MUSICA2 (for new device and K122736), Standard PC Software (for K012546)
- Operating system: Windows 7
- Display System: Separately cleared medical display
For most of these characteristics, the new device (DR 400) states "Same as predicates" or "Same as K122736," indicating that the acceptance criterion is equivalence to these existing devices.
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document mentions "Laboratory data and image quality evaluations" and "In-hospital image quality comparisons." However, specific sample sizes for test sets are not provided. The provenance (e.g., country of origin, retrospective/prospective) of this data is also not specified.
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)
The document states that "image quality evaluations conducted with independent radiologists confirm that performance is equivalent to the predicates." It also mentions "in-hospital image quality comparisons have been conducted with qualified independent radiologists." The exact number of radiologists or their specific qualifications (e.g., years of experience) are not provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not detail any specific adjudication method for the image quality evaluations. It only states that independent and qualified radiologists conducted the comparisons.
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
A multi-reader multi-case (MRMC) comparative effectiveness study, especially in the context of human readers improving with AI assistance, is not described or indicated in the provided text. The submission focuses on device equivalence, not on AI-assisted diagnostic improvements.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
While the device includes "optional image processing allows users to conveniently select image processing settings for different patient sizes and examinations" and "The image processing algorithms in the new device are identical to those used in the predicate (K122736)," and uses "MUSICA image processing software," there is no mention of a standalone algorithm performance study in the way typically seen for AI/CAD devices. The focus is on the integrated system's image quality being equivalent to predicates.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth for the image quality evaluations appears to be based on the assessment and comparison by qualified independent radiologists against images produced by the predicate devices. It is not explicitly stated if this involved a formal 'expert consensus' or if it was a direct comparison judgment. No mention of pathology or outcomes data is made in this context.
8. The sample size for the training set
The document does not specify any sample size for a training set. The submission refers to the image processing algorithms in the new device being "identical to those used in the predicate (K122736)," implying that any previous algorithm training would have been conducted for that predicate device, not for a new algorithm in the DR 400.
9. How the ground truth for the training set was established
As no training set is mentioned for the DR 400 as a new device with new algorithms, how ground truth was established for a training set is not applicable (N/A) from the provided text. The algorithms mentioned are already existing and cleared with the predicate device.
§ 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.