(187 days)
CANON X-RAY DIGITAL CAMERA CXDI-11 is indicated for use in generating radiographic Images of human anatomy. It is intended to replace radiographic film/screen systems in all general purpose diagnostic procedures.
CANON X-RAY DIGITAL CAMERA CXDI-11 provides digital image capture for conventional film/screen radiographic examinations. The device is intended to replace radiographic film/screen systems in all general purpose diagnostic procedures.
CANON X-RAY DIGITAL CAMERA CXDI-11 is used to directly capture and convert conventional projection X-ray images to digital images. A sub-sampled image can be displayed on a preview monitor for viewing. The diagnostic image can be transmitted through a digital network for printing. The device provides digital image capture for conventional film/screen radiographic examinations. CANON X-RAY DIGITAL CAMERA CXDI-11 differs from traditional X-ray systems in that instead of exposing a film for subsequent wet chemical processing to create a hardcopy image, a device is used to capture the image in electronic form. The digital data are then used to produce diagnostic hardcopy and reference-softcopy images.
Here's a breakdown of the acceptance criteria and the study details for the Canon X-Ray Digital Camera CXDI-11, based on the provided text:
Acceptance Criteria and Device Performance
The provided document doesn't explicitly state "acceptance criteria" in a numerical or percentage format typically seen. Instead, the study's goal was to demonstrate that the image quality of the Canon Digital Radiography System (CXDI-11) was substantially equivalent to conventional x-ray film. This qualitative assessment of "substantial equivalence" is the de-facto acceptance criteria.
| Acceptance Criteria (Inferred from Study Goal) | Reported Device Performance (CXDI-11) |
|---|---|
| Substantial equivalence in image quality to conventional x-ray film. | Image quality consistently indicated as equivalent or of higher quality than analog film. |
Additional Performance Metrics (not explicitly linked to "acceptance criteria" but included in comparison):
| Metric | CXDI-11 Performance | Predicate Device (Screen-Film) Performance |
|---|---|---|
| MTF | MTF@2lp/mm 42% | MTF@2lp/mm 33% (Lanex 250/TMS-RA)(Kodak) |
| Dynamic Range | Approximately 4 digit (linear A/D: 14 bit, output data: 12 bit) - can utilize wider dynamic range to control image visualization. | Approximately 1.5 digit |
| Image Processing | Performs digital image processing, can optimize image visualization even after exposure. | Development of film, uses its own H character, gray-scale fixed by exposure condition. |
Study Details
-
Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not explicitly stated as a number of cases or images. The document mentions "various inpatient cases."
- Data Provenance: Not specified, but given the context of a 510(k) summary for a US market application, it's reasonable to infer that the data was likely from a US (or generally Western) clinical setting. It is a retrospective study as it involved evaluating "analog films... read twice."
-
Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
- Number of Experts: Not specified. The document states "Qualified readers evaluated both digital and analog films."
- Qualifications of Experts: Not explicitly stated, beyond being "Qualified readers." Typically, for imaging studies, these would be radiologists, but their specific experience level is not provided.
-
Adjudication Method for the Test Set:
- Not explicitly stated. The study involved "Qualified readers evaluated both digital and analog films." There's no mention of multiple readers reaching a consensus or any formal adjudication process beyond individual readers' assessments. The mention of readers reading analog films twice to assess consistency suggests individual reader scoring rather than a consensus approach for the primary equivalency comparison.
-
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:
- No, an MRMC comparative effectiveness study was not done in the context of human readers improving with AI assistance.
- This study was a comparison between a new digital radiography system (CXDI-11) and a conventional film/screen system, not an AI-assisted interpretation study. The CXDI-11 device is a capture device, not an AI interpretation tool.
-
If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, in essence, a comparison of the "standalone" performance of the imaging systems was done. The study's primary objective was to evaluate the image quality of films generated by the CXDI-11 compared to conventional film, as assessed by human readers. While human readers were involved in the assessment, the focus was on the inherent quality of the image produced by the device, not the reader's diagnostic performance with or without the device (beyond assessing image quality).
-
The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.):
- The "ground truth" for the comparison of image quality was based on expert subjective assessment by "qualified readers." They evaluated the images for "overall image quality, as well as for image quality with respect to specific anatomical areas." There's no mention of objective pathology or outcomes data being used to establish a 'true' diagnosis or lesion presence for the purpose of image quality assessment. The "ground truth" here is the perceived quality by experts.
-
The Sample Size for the Training Set:
- Not applicable / Not mentioned. The CXDI-11 is an X-ray digital camera, a hardware device for capturing images. It's not an AI algorithm that learns from a training set of data. The document describes a clinical evaluation study for image quality, not the development or training of an AI model.
-
How the Ground Truth for the Training Set was Established:
- Not applicable / Not mentioned. As explained above, there is no AI algorithm training set for this 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.