(46 days)
The SmartLight Digital Film Viewer System is a radiographic film illuminator designed to automatically adapt film-viewing conditions to compensate for known physical and psychophysical limitations in human visual perception when reading radiographic films.
The Digital Film Viewer is a radiographic film illuminator with the following new indications for use:
- The Digital Film Viewer substantially improves the ability to detect and discern radiographic objects recorded on film compared to unmasked and masked light boxes.
- The Digital Film Viewer substantially improves the ability to detect and discern clinical information recorded on radiographic film compared to unmasked and masked light boxes.
- The Digital Film Viewer mitigates the age-dependent degradation in the ability to detect or discern radiographic objects recorded on film for readers over 30 years of age, as experienced on unmasked and masked light boxes.
The Digital Film Viewer is a radiographic film illuminator designed to automatically adapt film-viewing conditions to compensate for known physical and psychophysical limitations in human visual perception when reading radiographic films.
The device senses the size, location, and density of films mounted on its faceplate and automatically adapts film-viewing conditions, as described below:
- Adaptive Light Intensity The device automatically adapts the intensity of the back illumination system according to film density. Back light intensity ranges from 500-10,000 nits.
- Masking The device enables electro-optical collimation of the back illumination such that those parts of the faceplate covered by films are illuminated, while the rest of the faceplate remains dark, eliminating extraneous glare.
- Film Scatter Suppression The device incorporates an optical grid, which projects light in the forward direction to suppress optical scatter within the film (Callier effect).
- Ambient Light The device reduces the ambient light level when films are mounted on its faceplate.
- Pupil Diameter The device emits a dark blue light from its faceplate to control pupil dilation.
The provided text does not contain detailed information about specific acceptance criteria or a comprehensive study report with the requested metrics. It primarily focuses on the device description, intended use, and substantial equivalence determination for regulatory clearance.
However, based on the information available, I can extract and infer some points regarding the claims made about device performance, which would typically be linked to acceptance criteria in a detailed study.
Here's an attempt to answer your questions based on the provided text, acknowledging where information is missing:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't provide a quantitative table of acceptance criteria. However, it states the "new indications for use" which implicitly serve as performance claims that a study would aim to prove. The reported performance is a qualitative statement of improvement.
| Acceptance Criteria (Implied from Intended Use) | Reported Device Performance |
|---|---|
| Substantially improve the ability to detect and discern radiographic objects recorded on film compared to unmasked and masked light boxes. | "The study data demonstrate substantial and significant improvement in observer ability to detect and discern radiographic information recorded on film, when using the Digital Film Viewer compared to either an unmasked or masked light box." |
| Substantially improve the ability to detect and discern clinical information recorded on radiographic film compared to unmasked and masked light boxes. | "The study data demonstrate substantial and significant improvement in observer ability to detect and discern radiographic information recorded on film, when using the Digital Film Viewer compared to either an unmasked or masked light box." (This statement consolidates both "radiographic objects" and "clinical information" as the text uses "radiographic information" to cover both.) |
| Mitigate age-dependent degradation in the ability to detect or discern radiographic objects recorded on film for readers over 30 years of age. | "The study data demonstrate substantial and significant improvement in observer ability to detect and discern radiographic information recorded on film, when using the Digital Film Viewer compared to either an unmasked or masked light box." (While the study is stated to show overall significant improvement, the specific mitigation of age-dependent degradation is claimed but not explicitly detailed as a separate outcome.) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample size for test set: "a large number of observers" is mentioned. The exact number is not specified.
- Data provenance: Not specified (e.g., country of origin, retrospective or prospective). However, the study is described as a "controlled, statistical study," implying a prospective design for performance evaluation.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
This information is not provided in the text. The document refers to "observer ability to detect and discern radiographic information," which implies human observers were involved in the study itself, but it does not detail how the ground truth for the test cases was established (e.g., who determined the presence or absence of specific radiographic objects or clinical information that observers were asked to find).
4. Adjudication Method for the Test Set
This information is not provided in the text.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
Yes, a comparative effectiveness study involving multiple readers was performed. The text states:
- "The new indications for use relate to device performance and are based on data from a controlled, statistical study of a large number of observers."
- The study compared performance "when using the Digital Film Viewer compared to either an unmasked or masked light box."
Effect Size: The text states "substantial and significant improvement." However, specific quantitative effect sizes (e.g., AUC increase, sensitivity/specificity gains) or metrics on how much human readers improved with the AI (device) vs. without the AI are not provided.
6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance
This device is a film illuminator designed to enhance human viewing of radiographic films. It "automatically adapts film-viewing conditions to compensate for known physical and psychophysical limitations in human visual perception when reading radiographic films."
Therefore, it is not a standalone AI algorithm. Its stated purpose is to improve human performance, meaning a "human-in-the-loop" is integral to its function and evaluation.
7. Type of Ground Truth Used
This information is not explicitly provided. Given the nature of a radiographic film illuminator improving "detection and discernment," the ground truth for cases in the study would likely involve:
- Expert consensus: Multiple radiologists or clinicians confirming the definitive presence or absence of specific objects/findings.
- Pathology or surgical correlation: For certain definitive findings.
- Clinical outcomes data: Though less likely for immediate detection tasks on an illuminator, it could be used for confirming clinical significance.
The document states "observer ability to detect and discern radiographic information," which suggests a 'reference standard' was used to determine what was truly present or absent on the films.
8. Sample Size for the Training Set
The device is described as a "Digital Film Viewer" that uses electro-optical and physical mechanisms to adapt viewing conditions. It's not a machine learning model in the modern sense that typically has a "training set" to learn from data. The device's adaptive mechanisms (e.g., adaptive light intensity, masking, film scatter suppression) are based on pre-programmed rules and optical principles, not on being "trained" on a dataset.
Therefore, the concept of a "training set" for this device is not applicable.
9. How the Ground Truth for the Training Set Was Established
As explained in point 8, there is no "training set" for this type of device. Its functionalities are engineered and implemented based on known principles of human visual perception and physics, not through machine learning.
§ 892.1890 Radiographic film illuminator.
(a)
Identification. A radiographic film illuminator is a device containing a visible light source covered with a translucent front that is intended to be used to view medical radiographs.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 892.9.