(108 days)
The BioVision (Plus/ +)Digital Specimen Radiography (DSR) System is a cabinet digital X-ray imaging system intended to generate and control X-rays for examination of harvested specimens from various anatomical regions, and to provide rapid verification that the correct tissue has been excised.
Performing the verification directly in the same biopsy procedure room enables cases to be completed faster, thus limiting the time the patient needs to be under examination. Specimen radiography can potentially limit the number of patient recalls. This device is intended to be operated wherever the medical professionals deem appropriate, including a surgical suite or a room adjacent to a surgical suite.
The BioVision(Plus) Digital Specimen Radiography (DSR) System is a standalone cabinet digital X-ray imaging system designed to provide rapid verification that the correct tissue has been excised.
Performing the verification directly in the same procedure room enables cases to be completed faster, thus limiting the time the patient needs to be under examination. Specimen radiography can potentially limit the number of patient recalls.
The BioVision(Plus) Digital Specimen Radiography (DSR) System employs the use of Faxitron Bioptics Vision image acquisition software. The Vision software handles the digital X-ray image acquisition, calibration, image display, image analysis and manipulation, patient database, image archiving, and transmittal.
The provided text describes the BioVision(Plus) Digital Specimen Radiography (DSR) System and its comparison to a predicate device, the BioVision Digital Specimen Radiography System (K091558). However, it does not describe a study that uses AI or machine learning algorithms, nor does it provide acceptance criteria and performance data in the context of an AI device.
Instead, this document is a 510(k) summary for a medical device that uses X-ray technology. The "study" referenced is a series of non-clinical performance data tests to demonstrate substantial equivalence to a predicate device.
Given that the request asks for details related to AI/ML device studies (e.g., sample size for training data, number of experts, adjudication methods for ground truth, MRMC studies), and the provided text describes an X-ray imaging device without any mention of AI/ML, I cannot fulfill the request as specified.
However, I can extract the information provided regarding the device's technical specifications and the non-clinical testing performed to establish substantial equivalence.
Here's an attempt to answer the questions based only on the information available in the provided text, recognizing that many requested fields regarding AI/ML studies are not applicable:
Acceptance Criteria and Study for BioVision(Plus) Digital Specimen Radiography (DSR) System
The provided document describes the BioVision(Plus) DSR System as an X-ray imaging device, not an AI/ML device. Therefore, many of the requested fields regarding AI/ML study design are not applicable or not present in the text. The "acceptance criteria" here refer to performance standards and substantial equivalence to a predicate device, rather than diagnostic performance metrics of an AI algorithm.
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state "acceptance criteria" in the format of defined thresholds. Instead, it details that the device was tested to perform "as well as" the predicate device and to comply with specific regulations and standards.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Image Quality (Spatial Resolution) - as good as predicate | Verified with line pair gauge and America College Radiology phantom |
| Image Quality (Contrast Resolution) - as good as predicate | Verified using a Small Field Low Contrast Phantom |
| Radiation Safety - Compliance with 21 CFR 1020.40 | Conforms to 21 CFR 1020.40; radiation emission does not exceed 0.5 mR/hr. |
| Electrical Safety - Compliance with UL 61010-1, 3rd Edition | Meets and exceeds the requirements of UL 61010-1, 3rd Edition |
| Software Performance - All functionality, hazard addressing | Verification testing during coding; Alpha validation for all functionality |
| Substantial Equivalence to Predicate Device | Performance testing and validation studies document substantial equivalence |
2. Sample size used for the test set and the data provenance
The document describes non-clinical performance and validation testing, not a clinical study with a "test set" of patient data in the typical sense for AI/ML.
- Sample size for test set: Not applicable for a non-clinical device performance test. The testing involved phantoms (line pair gauge, America College Radiology phantom, Small Field Low Contrast Phantom) and engineering validation.
- Data provenance: Not applicable. The testing was non-clinical, involving device performance measurements rather than patient data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. Ground truth, in the context of an AI/ML diagnostic device, involves expert interpretation of patient data or pathology. This document describes performance testing of an X-ray generator and imaging system using phantoms and engineering methods.
4. Adjudication method for the test set
Not applicable. There was no clinical "test set" requiring expert adjudication.
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
Not applicable. This device is a standalone X-ray imaging system, not an AI-assisted diagnostic tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The device itself is a "standalone" X-ray imaging system. The performance testing was of the system's ability to generate and capture images to a specified quality, without human-in-the-loop performance assessment related to diagnostic accuracy. The system's "algorithm" here refers to its internal software for image acquisition, calibration, display, and manipulation, not an AI algorithm for diagnosis.
7. The type of ground truth used
For the non-clinical performance tests, the "ground truth" was established by:
- Known physical properties of phantoms: For spatial resolution (line pair gauge) and contrast resolution (Small Field Low Contrast Phantom).
- Engineering specifications and regulatory standards: For radiation safety (21 CFR 1020.40) and electrical safety (UL 61010-1).
- Design specifications and verification/validation results: For software functionality and hazard mitigation.
8. The sample size for the training set
Not applicable. This is not an AI/ML device, so there is no "training set."
9. How the ground truth for the training set was established
Not applicable. There is no training set for an AI/ML algorithm.
§ 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.