(25 days)
The CareView 1800Cwe/ CareView 1500Cwe detector is indicated for digital imaging solution designed for providing general radiographic diagnosis of human anatomy. It is intended to replace radiographic film/screen systems in all general-purpose diagnostic procedures. This product is not intended for mammography applications.
The CareView 1800Cwe/ CareView 1500Cwe detector is a class of digital X-ray flat panel detector that has an imaging area of 430mm×430mm×356mm. The detector communicates with wireless and an optional wired communication feature (Giga-bit Ethernet communication mode via connecting the power box).
The detector functions by intercepting X-ray photons. Then the scintillator emits visible spectrum photons that illuminate an array of photo detectors (a-Si) that create electrical signals. The electrical signals are then digitally converted to display an image on the monitor.
The detector should be connected to a computer and X-ray generator to digitize X-ray images and transfer radiography diagnostics. The x-ray generator, an essential part of a full x-ray system, is not part of the subject medical device.
The software that supports the functions of the digital detector CareView 1800Cwe/ CareView 1500Cwe is unchanged from the predicate. And the API for the digital detector CareView 1800Cwe/ CareView 1500Cwe is the same as that for the predicate device. Besides, there are only minor differences between the firmware for the CareView 1800Cwe/ CareView 1500Cwe and predicate device except to support battery supply and wireless communication.
Generally, CareView 1800Cwe is the same as the cleared product, CareView 1800Le except the wireless function. And CareView 1500Cwe is the same as the cleared product, CareView 1800Le except the wireless function and dimension.
The provided text is a 510(k) summary for an X-ray Flat Panel Detector (CareView 1800Cwe / CareView 1500Cwe). It describes the device and its intended use, and argues for substantial equivalence to a predicate device (CareView 1800Le).
However, the document does not contain specific acceptance criteria or a detailed study of the device's clinical performance against such criteria for AI/algorithm performance. It primarily focuses on demonstrating substantial equivalence to a predicate device regarding safety and effectiveness from a regulatory perspective.
The document discusses "technological characteristics" which include physical specifications, image quality metrics (MTF, DQE, spatial resolution), and operational parameters. These are compared between the proposed device and the predicate device. For example:
- Spatial Resolution: Both proposed and predicate devices measure 3.57 line pair/mm.
- MTF: For 1lp/mm, the proposed device has "~63%" while the predicate device has "≥63%". Similar values are given for 2lp/mm and 3lp/mm.
- DQE: For 0lp/mm, the proposed device has "~62%" while the predicate device has "≥62%". Similar values are given for 1lp/mm and 3lp/mm.
These are technical specifications and performance indicators for the hardware component (the X-ray flat panel detector itself) and are used to show that the new device performs comparably to the predicate device.
The document does not describe a study involving human readers, AI assistance, or an algorithm-only standalone performance evaluation for diagnostic accuracy. It is not a clinical study on diagnostic performance with AI. The context is regulatory clearance for an X-ray detector, which is a hardware component for imaging, not an AI-powered diagnostic tool.
Therefore, most of the information requested in your prompt regarding acceptance criteria, study details, sample sizes, experts, adjudication, MRMC studies, standalone algorithm performance, and ground truth for AI models cannot be extracted from this document, as it is not relevant to the content provided.
The document explicitly states: "The software that supports the functions of the digital detector CareView 1800Cwe/ CareView 1500Cwe is unchanged from the predicate. And the API for the digital detector CareView 1800Cwe/ CareView 1500Cwe is the same as that for the predicate device. Besides, there are only minor differences between the firmware for the CareView 1800Cwe/ CareView 1500Cwe and predicate device except to support battery supply and wireless communication." This indicates that the core image processing algorithm, if any, is largely the same as the predicate device.
To answer your prompt based only on the provided text:
Acceptance Criteria and Device Performance Study for CareRay Digital Medical Technology Co., Ltd. X-ray Flat Panel Detectors (CareView 1800Cwe / CareView 1500Cwe)
The provided document describes the substantial equivalence determination for an X-ray Flat Panel Detector, a hardware component for medical imaging. It does not detail specific acceptance criteria or a dedicated study for Artificial Intelligence (AI) or software-based diagnostic performance. The performance metrics discussed relate to the physical characteristics and image quality of the X-ray detector hardware.
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly define "acceptance criteria" in the context of a clinical performance study with AI. Instead, it presents technological characteristics of the proposed device (CareView 1800Cwe / CareView 1500Cwe) and compares them to a predicate device (CareView 1800Le) to demonstrate substantial equivalence. The "performance" here refers to physical and imaging specifications of the detector.
| Item | Proposed Device (CareView 1800Cwe / CareView 1500Cwe) | Predicate Device (CareView 1800Le) |
|---|---|---|
| Image Matrix Size | 3072 x 3072 pixels (1800Cwe) / 3072 x 2560 pixels (1500Cwe) | 3072 x 3072 pixels |
| Pixel Pitch | 140µm | 140µm |
| Effective Imaging Area | 430 mm x 430 mm (1800Cwe) / 430 mm x 356 mm (1500Cwe) | 430 mm x 430 mm |
| Grayscale | 16 bit, 65536 grayscale | 16 bit, 65536 grayscale |
| Spatial Resolution | 3.57 line pair/mm | 3.57 line pair/mm |
| MTF (@ 1lp/mm) | ~63% (@ RQA5, 27µGy) | ≥63% (@ RQA5, 30μGy) |
| MTF (@ 2lp/mm) | ~35% (@ RQA5, 27µGy) | ≥35% (@ RQA5, 30μGy) |
| MTF (@ 3lp/mm) | ~17% (@ RQA5, 27µGy) | ≥17% (@ RQA5, 30μGy) |
| DQE (@ 0lp/mm) | ~62% (@ RQA5, 27µGy) | ≥62% (@ RQA5, 30μGy) |
| DQE (@ 1lp/mm) | ~45% (@ RQA5, 27µGy) | ≥45% (@ RQA5, 30μGy) |
| DQE (@ 3lp/mm) | ~17% (@ RQA5, 27µGy) | ≥17% (@ RQA5, 30μGy) |
The document states, "The difference of wireless function and dimension don't affect the technological parameters and clinical images." This implies that the performance metrics of the proposed device are considered equivalent to or meeting the predicate device's performance, which serves as the "acceptance" standard for these technical parameters.
2. Sample size used for the test set and the data provenance
The document discusses "Nonclinical and clinical considerations" stating that "The proposed device (CareView 1800Cwe/ CareView 1500Cwe) and predicate device (CareView 1800Le) share most of primary product specifications including intended use, technology, material, and imaging principle, power supply method etc." It concludes that the differences "don't affect the technological parameters and clinical images."
This implies that the "test set" for assessing substantial equivalence primarily involved technical evaluation and comparison to the predicate device's established performance, rather than a separate clinical dataset for diagnostic accuracy evaluation with a new algorithm. No specific sample size for a clinical image test set or data provenance (country, retrospective/prospective) is provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. The document does not describe a clinical study requiring expert-established ground truth for diagnostic accuracy. The evaluation is focused on the hardware's technical specifications.
4. Adjudication method for the test set
Not applicable. No clinical test set requiring adjudication is described.
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 document does not describe any MRMC study or AI assistance. The device is an X-ray flat panel detector, not an AI diagnostic tool.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Not applicable. The document focuses on the X-ray detector hardware. It states the software and API are "unchanged from the predicate" and firmware has "minor differences" to support wireless communication and battery supply. There is no mention of a standalone algorithm for diagnostic interpretation.
7. The type of ground truth used
Not applicable. The evaluation is based on technical specifications and established performance of the predicate device, not on diagnostic ground truth (e.g., pathology, outcomes data).
8. The sample size for the training set
Not applicable. This document does not describe an AI/ML algorithm that required a training set. The device is an X-ray detector.
9. How the ground truth for the training set was established
Not applicable. This document does not describe an AI/ML algorithm that required a training set with established ground truth.
§ 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.